diff --git "a/scannet/insseg-pg-spunet-base/train.log" "b/scannet/insseg-pg-spunet-base/train.log" new file mode 100644--- /dev/null +++ "b/scannet/insseg-pg-spunet-base/train.log" @@ -0,0 +1,12520 @@ +[2025-02-22 10:46:07,257 INFO train.py line 128 2775932] => Loading config ... +[2025-02-22 10:46:07,258 INFO train.py line 130 2775932] Save path: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1 +[2025-02-22 10:46:07,489 INFO train.py line 131 2775932] Config: +weight = 'exp/scannet/pretrain-gs-v4-spunet-base-m5/model/model_last.pth' +resume = False +evaluate = True +test_only = False +seed = 61524582 +save_path = 'exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1' +num_worker = 24 +batch_size = 12 +batch_size_val = None +batch_size_test = None +epoch = 800 +eval_epoch = 100 +clip_grad = None +sync_bn = False +enable_amp = True +empty_cache = False +empty_cache_per_epoch = False +find_unused_parameters = False +mix_prob = 0 +param_dicts = None +hooks = [ + dict(type='CheckpointLoader', keywords='module.', replacement='module.'), + dict(type='IterationTimer', warmup_iter=2), + dict(type='CustomInformationWriter', interval=50), + dict( + type='InsSegEvaluator', + segment_ignore_index=(-1, 0, 1), + instance_ignore_index=-1), + dict(type='CheckpointSaver', save_freq=None) +] +train = dict(type='DefaultTrainer') +test = dict(type='SemSegTester', verbose=True) +class_names = [ + 'wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', 'door', + 'window', 'bookshelf', 'picture', 'counter', 'desk', 'curtain', + 'refridgerator', 'shower curtain', 'toilet', 'sink', 'bathtub', + 'otherfurniture' +] +num_classes = 20 +segment_ignore_index = (-1, 0, 1) +model = dict( + type='PG-v1m1', + backbone=dict( + type='SpUNet-v1m1', + in_channels=6, + num_classes=0, + channels=(32, 64, 128, 256, 256, 128, 96, 96), + layers=(2, 3, 4, 6, 2, 2, 2, 2)), + backbone_out_channels=96, + semantic_num_classes=20, + semantic_ignore_index=-1, + segment_ignore_index=(-1, 0, 1), + instance_ignore_index=-1, + cluster_thresh=1.5, + cluster_closed_points=300, + cluster_propose_points=100, + cluster_min_points=50) +optimizer = dict(type='AdamW', lr=0.006, weight_decay=0.05) +scheduler = dict( + type='OneCycleLR', + max_lr=0.006, + pct_start=0.05, + anneal_strategy='cos', + div_factor=10.0, + final_div_factor=1000.0) +dataset_type = 'ScanNetDataset' +data_root = 'data/scannet' +data = dict( + num_classes=20, + ignore_index=-1, + names=[ + 'wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table', 'door', + 'window', 'bookshelf', 'picture', 'counter', 'desk', 'curtain', + 'refridgerator', 'shower curtain', 'toilet', 'sink', 'bathtub', + 'otherfurniture' + ], + train=dict( + type='ScanNetDataset', + split='train', + data_root='data/scannet', + transform=[ + dict(type='ToTensor'), + dict(type='CenterShift', apply_z=True), + dict( + type='RandomDropout', + dropout_ratio=0.2, + dropout_application_ratio=0.5), + dict( + type='RandomRotate', + angle=[-1, 1], + axis='z', + center=[0, 0, 0], + p=0.5), + dict( + type='RandomRotate', + angle=[-0.015625, 0.015625], + axis='x', + p=0.5), + dict( + type='RandomRotate', + angle=[-0.015625, 0.015625], + axis='y', + p=0.5), + dict(type='RandomScale', scale=[0.9, 1.1]), + dict(type='RandomFlip', p=0.5), + dict(type='RandomJitter', sigma=0.005, clip=0.02), + dict( + type='ElasticDistortion', + distortion_params=[[0.2, 0.4], [0.8, 1.6]]), + dict(type='ChromaticAutoContrast', p=0.2, blend_factor=None), + dict(type='ChromaticTranslation', p=0.95, ratio=0.1), + dict(type='ChromaticJitter', p=0.95, std=0.05), + dict( + type='GridSample', + grid_size=0.02, + hash_type='fnv', + mode='train', + return_grid_coord=True, + keys=('coord', 'color', 'normal', 'segment', 'instance')), + dict(type='SphereCrop', sample_rate=0.8, mode='random'), + dict(type='NormalizeColor'), + dict( + type='InstanceParser', + segment_ignore_index=(-1, 0, 1), + instance_ignore_index=-1), + dict( + type='Collect', + keys=('coord', 'grid_coord', 'segment', 'instance', + 'instance_centroid', 'bbox'), + feat_keys=('color', 'normal')) + ], + test_mode=False, + loop=8), + val=dict( + type='ScanNetDataset', + split='val', + data_root='data/scannet', + transform=[ + dict(type='ToTensor'), + dict(type='CenterShift', apply_z=True), + dict( + type='Copy', + keys_dict=dict( + coord='origin_coord', + segment='origin_segment', + instance='origin_instance')), + dict( + type='GridSample', + grid_size=0.02, + hash_type='fnv', + mode='train', + return_grid_coord=True, + keys=('coord', 'color', 'normal', 'segment', 'instance')), + dict(type='CenterShift', apply_z=False), + dict(type='NormalizeColor'), + dict( + type='InstanceParser', + segment_ignore_index=(-1, 0, 1), + instance_ignore_index=-1), + dict( + type='Collect', + keys=('coord', 'grid_coord', 'segment', 'instance', + 'origin_coord', 'origin_segment', 'origin_instance', + 'instance_centroid', 'bbox'), + feat_keys=('color', 'normal'), + offset_keys_dict=dict( + offset='coord', origin_offset='origin_coord')) + ], + test_mode=False), + test=dict()) +num_worker_per_gpu = 6 +batch_size_per_gpu = 3 +batch_size_val_per_gpu = 1 +batch_size_test_per_gpu = 1 + +[2025-02-22 10:46:07,489 INFO train.py line 132 2775932] => Building model ... +[2025-02-22 10:46:08,020 INFO train.py line 225 2775932] Num params: 39167639 +[2025-02-22 10:46:08,204 INFO train.py line 134 2775932] => Building writer ... +[2025-02-22 10:46:08,206 INFO train.py line 235 2775932] Tensorboard writer logging dir: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1 +[2025-02-22 10:46:08,206 INFO train.py line 136 2775932] => Building train dataset & dataloader ... +[2025-02-22 10:46:08,208 INFO defaults.py line 68 2775932] Totally 1201 x 8 samples in train set. +[2025-02-22 10:46:08,208 INFO train.py line 138 2775932] => Building val dataset & dataloader ... +[2025-02-22 10:46:08,209 INFO defaults.py line 68 2775932] Totally 312 x 1 samples in val set. +[2025-02-22 10:46:08,209 INFO train.py line 140 2775932] => Building optimize, scheduler, scaler(amp) ... +[2025-02-22 10:46:08,210 INFO train.py line 144 2775932] => Building hooks ... +[2025-02-22 10:46:08,210 INFO misc.py line 214 2775932] => Loading checkpoint & weight ... +[2025-02-22 10:46:08,210 INFO misc.py line 216 2775932] Loading weight at: exp/scannet/pretrain-gs-v4-spunet-base-m5/model/model_last.pth +[2025-02-22 10:46:08,708 INFO misc.py line 221 2775932] Loading layer weights with keyword: module., replace keyword with: module. +[2025-02-22 10:46:08,713 INFO misc.py line 238 2775932] Missing keys: ['module.bias_head.0.weight', 'module.bias_head.0.bias', 'module.bias_head.1.weight', 'module.bias_head.1.bias', 'module.bias_head.1.running_mean', 'module.bias_head.1.running_var', 'module.bias_head.3.weight', 'module.bias_head.3.bias', 'module.seg_head.weight', 'module.seg_head.bias'] +[2025-02-22 10:46:08,714 INFO train.py line 151 2775932] >>>>>>>>>>>>>>>> Start Training >>>>>>>>>>>>>>>> +[2025-02-22 10:46:29,520 INFO hook.py line 109 2775932] Train: [1/100][50/800] Data 0.002 (0.003) Batch 0.139 (0.139) Remain 03:05:24 loss: 2.4481 Lr: 6.02083e-04 +[2025-02-22 10:46:37,007 INFO hook.py line 109 2775932] Train: [1/100][100/800] Data 0.002 (0.003) Batch 0.129 (0.145) Remain 03:12:33 loss: 1.3476 Lr: 6.08327e-04 +[2025-02-22 10:46:44,532 INFO hook.py line 109 2775932] Train: [1/100][150/800] Data 0.004 (0.003) Batch 0.153 (0.147) Remain 03:15:06 loss: 1.9806 Lr: 6.18725e-04 +[2025-02-22 10:46:51,754 INFO hook.py line 109 2775932] Train: [1/100][200/800] Data 0.002 (0.003) Batch 0.162 (0.146) Remain 03:14:15 loss: 1.2249 Lr: 6.32927e-04 +[2025-02-22 10:46:58,852 INFO hook.py line 109 2775932] Train: [1/100][250/800] Data 0.001 (0.003) Batch 0.126 (0.145) Remain 03:13:01 loss: 1.5502 Lr: 6.51493e-04 +[2025-02-22 10:47:06,412 INFO hook.py line 109 2775932] Train: [1/100][300/800] Data 0.003 (0.003) Batch 0.150 (0.146) Remain 03:14:14 loss: 0.9756 Lr: 6.74144e-04 +[2025-02-22 10:47:13,605 INFO hook.py line 109 2775932] Train: [1/100][350/800] Data 0.002 (0.003) Batch 0.140 (0.146) Remain 03:13:40 loss: 0.9120 Lr: 7.00846e-04 +[2025-02-22 10:47:20,539 INFO hook.py line 109 2775932] Train: [1/100][400/800] Data 0.002 (0.003) Batch 0.149 (0.145) Remain 03:12:20 loss: 0.6333 Lr: 7.31558e-04 +[2025-02-22 10:47:27,739 INFO hook.py line 109 2775932] Train: [1/100][450/800] Data 0.002 (0.003) Batch 0.138 (0.145) Remain 03:12:04 loss: 1.1610 Lr: 7.66232e-04 +[2025-02-22 10:47:34,747 INFO hook.py line 109 2775932] Train: [1/100][500/800] Data 0.004 (0.003) Batch 0.135 (0.144) Remain 03:11:19 loss: 0.4362 Lr: 8.04816e-04 +[2025-02-22 10:47:41,874 INFO hook.py line 109 2775932] Train: [1/100][550/800] Data 0.002 (0.003) Batch 0.126 (0.144) Remain 03:10:58 loss: 1.7599 Lr: 8.47248e-04 +[2025-02-22 10:47:49,006 INFO hook.py line 109 2775932] Train: [1/100][600/800] Data 0.003 (0.003) Batch 0.167 (0.144) Remain 03:10:41 loss: 0.6825 Lr: 8.93464e-04 +[2025-02-22 10:47:56,008 INFO hook.py line 109 2775932] Train: [1/100][650/800] Data 0.003 (0.003) Batch 0.133 (0.144) Remain 03:10:08 loss: 0.0217 Lr: 9.43393e-04 +[2025-02-22 10:48:03,046 INFO hook.py line 109 2775932] Train: [1/100][700/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 03:09:44 loss: 0.4796 Lr: 9.96958e-04 +[2025-02-22 10:48:10,261 INFO hook.py line 109 2775932] Train: [1/100][750/800] Data 0.002 (0.003) Batch 0.126 (0.144) Remain 03:09:41 loss: -0.1975 Lr: 1.05408e-03 +[2025-02-22 10:48:17,358 INFO hook.py line 109 2775932] Train: [1/100][800/800] Data 0.002 (0.003) Batch 0.113 (0.144) Remain 03:09:25 loss: -0.0322 Lr: 1.11466e-03 +[2025-02-22 10:48:17,358 INFO misc.py line 135 2775932] Train result: loss: 0.9465 seg_loss: 1.2897 bias_l1_loss: 0.4623 bias_cosine_loss: -0.8055 +[2025-02-22 10:48:17,360 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 10:48:24,699 INFO evaluator.py line 595 2775932] Test: [1/78] Loss 0.3486 +[2025-02-22 10:48:24,895 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.1985 +[2025-02-22 10:48:24,959 INFO evaluator.py line 595 2775932] Test: [3/78] Loss 0.0860 +[2025-02-22 10:48:25,026 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3345 +[2025-02-22 10:48:25,107 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.1240 +[2025-02-22 10:48:25,150 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0604 +[2025-02-22 10:48:25,401 INFO evaluator.py line 595 2775932] Test: [7/78] Loss 0.0361 +[2025-02-22 10:48:25,436 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3167 +[2025-02-22 10:48:25,566 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0029 +[2025-02-22 10:48:25,680 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.7529 +[2025-02-22 10:48:25,904 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1795 +[2025-02-22 10:48:26,005 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0916 +[2025-02-22 10:48:26,068 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.2484 +[2025-02-22 10:48:26,139 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.4227 +[2025-02-22 10:48:26,206 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7835 +[2025-02-22 10:48:26,266 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3033 +[2025-02-22 10:48:26,429 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.2059 +[2025-02-22 10:48:26,505 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.3564 +[2025-02-22 10:48:26,631 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1780 +[2025-02-22 10:48:26,682 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0629 +[2025-02-22 10:48:26,842 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.1607 +[2025-02-22 10:48:26,988 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3836 +[2025-02-22 10:48:27,045 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.4005 +[2025-02-22 10:48:27,103 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.2188 +[2025-02-22 10:48:27,164 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0746 +[2025-02-22 10:48:27,214 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.0956 +[2025-02-22 10:48:27,324 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4824 +[2025-02-22 10:48:27,415 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.4687 +[2025-02-22 10:48:27,473 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.0834 +[2025-02-22 10:48:27,547 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.0825 +[2025-02-22 10:48:28,101 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.0469 +[2025-02-22 10:48:28,201 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.3123 +[2025-02-22 10:48:28,236 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.1991 +[2025-02-22 10:48:28,312 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0062 +[2025-02-22 10:48:28,341 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3199 +[2025-02-22 10:48:28,451 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.5362 +[2025-02-22 10:48:28,518 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.0727 +[2025-02-22 10:48:28,638 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.3019 +[2025-02-22 10:48:28,759 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2446 +[2025-02-22 10:48:28,969 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7813 +[2025-02-22 10:48:29,143 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.8815 +[2025-02-22 10:48:29,193 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.8675 +[2025-02-22 10:48:29,230 INFO evaluator.py line 595 2775932] Test: [43/78] Loss 0.3247 +[2025-02-22 10:48:29,467 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.3153 +[2025-02-22 10:48:29,519 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.3468 +[2025-02-22 10:48:29,574 INFO evaluator.py line 595 2775932] Test: [46/78] Loss 0.2654 +[2025-02-22 10:48:29,657 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8325 +[2025-02-22 10:48:29,764 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.2628 +[2025-02-22 10:48:29,873 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.8834 +[2025-02-22 10:48:29,944 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3956 +[2025-02-22 10:48:30,005 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.9019 +[2025-02-22 10:48:30,121 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.2055 +[2025-02-22 10:48:30,158 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.3099 +[2025-02-22 10:48:30,234 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3036 +[2025-02-22 10:48:30,315 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.3993 +[2025-02-22 10:48:30,356 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.3953 +[2025-02-22 10:48:30,495 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.2354 +[2025-02-22 10:48:30,532 INFO evaluator.py line 595 2775932] Test: [58/78] Loss 0.6191 +[2025-02-22 10:48:30,768 INFO evaluator.py line 595 2775932] Test: [59/78] Loss 0.1655 +[2025-02-22 10:48:30,869 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2881 +[2025-02-22 10:48:30,929 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.5868 +[2025-02-22 10:48:30,984 INFO evaluator.py line 595 2775932] Test: [62/78] Loss 0.0258 +[2025-02-22 10:48:31,144 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1708 +[2025-02-22 10:48:31,238 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5872 +[2025-02-22 10:48:31,300 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.5731 +[2025-02-22 10:48:31,415 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1928 +[2025-02-22 10:48:31,564 INFO evaluator.py line 595 2775932] Test: [67/78] Loss 0.0308 +[2025-02-22 10:48:31,636 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.3661 +[2025-02-22 10:48:31,677 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.5241 +[2025-02-22 10:48:31,730 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1710 +[2025-02-22 10:48:31,881 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.5289 +[2025-02-22 10:48:31,912 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2596 +[2025-02-22 10:48:31,955 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3257 +[2025-02-22 10:48:32,032 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3556 +[2025-02-22 10:48:32,228 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.2108 +[2025-02-22 10:48:32,300 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.4986 +[2025-02-22 10:48:32,469 INFO evaluator.py line 595 2775932] Test: [77/78] Loss 0.0194 +[2025-02-22 10:48:32,547 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4008 +[2025-02-22 10:48:44,537 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 10:48:44,537 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 10:48:44,537 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 10:48:44,537 INFO evaluator.py line 547 2775932] cabinet : 0.0729 0.2019 0.4261 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] bed : 0.2435 0.6505 0.7908 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] chair : 0.6300 0.8123 0.8904 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] sofa : 0.0805 0.3021 0.8068 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] table : 0.1692 0.3985 0.6575 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] door : 0.1518 0.3400 0.4833 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] window : 0.0220 0.0689 0.2779 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] bookshelf : 0.0000 0.0000 0.0039 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] picture : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] counter : 0.0000 0.0000 0.0017 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] desk : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] curtain : 0.0000 0.0000 0.0002 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] refridgerator : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] shower curtain : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] toilet : 0.0000 0.0000 0.2277 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] sink : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] bathtub : 0.0000 0.0000 0.0000 +[2025-02-22 10:48:44,538 INFO evaluator.py line 547 2775932] otherfurniture : 0.1355 0.3116 0.4936 +[2025-02-22 10:48:44,538 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 10:48:44,538 INFO evaluator.py line 554 2775932] average : 0.0836 0.1714 0.2811 +[2025-02-22 10:48:44,538 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 10:48:44,538 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 10:48:44,600 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.1714 +[2025-02-22 10:48:44,600 INFO misc.py line 164 2775932] Currently Best AP50: 0.1714 +[2025-02-22 10:48:44,600 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 10:48:52,954 INFO hook.py line 109 2775932] Train: [2/100][50/800] Data 0.002 (0.005) Batch 0.167 (0.147) Remain 03:14:33 loss: 0.5031 Lr: 1.17861e-03 +[2025-02-22 10:49:00,221 INFO hook.py line 109 2775932] Train: [2/100][100/800] Data 0.002 (0.004) Batch 0.138 (0.146) Remain 03:12:58 loss: -0.0943 Lr: 1.24584e-03 +[2025-02-22 10:49:07,790 INFO hook.py line 109 2775932] Train: [2/100][150/800] Data 0.002 (0.006) Batch 0.151 (0.148) Remain 03:15:05 loss: 0.0754 Lr: 1.31623e-03 +[2025-02-22 10:49:15,258 INFO hook.py line 109 2775932] Train: [2/100][200/800] Data 0.147 (0.006) Batch 0.328 (0.148) Remain 03:15:23 loss: 0.1090 Lr: 1.38969e-03 +[2025-02-22 10:49:22,453 INFO hook.py line 109 2775932] Train: [2/100][250/800] Data 0.002 (0.005) Batch 0.169 (0.147) Remain 03:14:04 loss: -0.1776 Lr: 1.46609e-03 +[2025-02-22 10:49:29,920 INFO hook.py line 109 2775932] Train: [2/100][300/800] Data 0.002 (0.005) Batch 0.152 (0.148) Remain 03:14:21 loss: 0.1373 Lr: 1.54532e-03 +[2025-02-22 10:49:36,857 INFO hook.py line 109 2775932] Train: [2/100][350/800] Data 0.002 (0.005) Batch 0.135 (0.146) Remain 03:12:31 loss: 0.0313 Lr: 1.62726e-03 +[2025-02-22 10:49:44,018 INFO hook.py line 109 2775932] Train: [2/100][400/800] Data 0.003 (0.004) Batch 0.129 (0.146) Remain 03:11:51 loss: -0.0187 Lr: 1.71178e-03 +[2025-02-22 10:49:51,123 INFO hook.py line 109 2775932] Train: [2/100][450/800] Data 0.003 (0.004) Batch 0.150 (0.146) Remain 03:11:08 loss: 0.7444 Lr: 1.79875e-03 +[2025-02-22 10:49:58,173 INFO hook.py line 109 2775932] Train: [2/100][500/800] Data 0.003 (0.004) Batch 0.149 (0.145) Remain 03:10:24 loss: 0.4195 Lr: 1.88803e-03 +[2025-02-22 10:50:05,352 INFO hook.py line 109 2775932] Train: [2/100][550/800] Data 0.003 (0.004) Batch 0.145 (0.145) Remain 03:10:06 loss: -0.0973 Lr: 1.97950e-03 +[2025-02-22 10:50:12,376 INFO hook.py line 109 2775932] Train: [2/100][600/800] Data 0.003 (0.004) Batch 0.141 (0.145) Remain 03:09:28 loss: -0.1662 Lr: 2.07300e-03 +[2025-02-22 10:50:20,149 INFO hook.py line 109 2775932] Train: [2/100][650/800] Data 0.004 (0.004) Batch 0.164 (0.145) Remain 03:10:27 loss: 0.0569 Lr: 2.16839e-03 +[2025-02-22 10:50:27,293 INFO hook.py line 109 2775932] Train: [2/100][700/800] Data 0.003 (0.004) Batch 0.114 (0.145) Remain 03:10:05 loss: -0.3673 Lr: 2.26553e-03 +[2025-02-22 10:50:34,296 INFO hook.py line 109 2775932] Train: [2/100][750/800] Data 0.003 (0.004) Batch 0.132 (0.145) Remain 03:09:30 loss: 0.1430 Lr: 2.36427e-03 +[2025-02-22 10:50:41,140 INFO hook.py line 109 2775932] Train: [2/100][800/800] Data 0.002 (0.004) Batch 0.109 (0.144) Remain 03:08:43 loss: -0.2856 Lr: 2.46444e-03 +[2025-02-22 10:50:41,141 INFO misc.py line 135 2775932] Train result: loss: 0.1238 seg_loss: 0.5725 bias_l1_loss: 0.4060 bias_cosine_loss: -0.8547 +[2025-02-22 10:50:41,142 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 10:50:48,636 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.4671 +[2025-02-22 10:50:49,925 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.1170 +[2025-02-22 10:50:49,984 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2238 +[2025-02-22 10:50:50,051 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3475 +[2025-02-22 10:50:50,110 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.2772 +[2025-02-22 10:50:50,163 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8795 +[2025-02-22 10:50:50,427 INFO evaluator.py line 595 2775932] Test: [7/78] Loss 0.3325 +[2025-02-22 10:50:50,460 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3459 +[2025-02-22 10:50:50,596 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0205 +[2025-02-22 10:50:50,654 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 1.1174 +[2025-02-22 10:50:50,894 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0214 +[2025-02-22 10:50:50,996 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.4000 +[2025-02-22 10:50:51,063 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.5494 +[2025-02-22 10:50:51,163 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7944 +[2025-02-22 10:50:51,257 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8025 +[2025-02-22 10:50:51,341 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3245 +[2025-02-22 10:50:51,498 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.0721 +[2025-02-22 10:50:51,592 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.3837 +[2025-02-22 10:50:51,758 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2350 +[2025-02-22 10:50:51,828 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0819 +[2025-02-22 10:50:51,981 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4335 +[2025-02-22 10:50:52,169 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4340 +[2025-02-22 10:50:52,266 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0475 +[2025-02-22 10:50:52,326 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0544 +[2025-02-22 10:50:52,398 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0452 +[2025-02-22 10:50:52,478 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.2331 +[2025-02-22 10:50:52,612 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4337 +[2025-02-22 10:50:52,703 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8771 +[2025-02-22 10:50:52,799 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.3465 +[2025-02-22 10:50:52,893 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3701 +[2025-02-22 10:50:53,571 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.2268 +[2025-02-22 10:50:53,698 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7505 +[2025-02-22 10:50:53,755 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4613 +[2025-02-22 10:50:53,861 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1177 +[2025-02-22 10:50:53,900 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5347 +[2025-02-22 10:50:54,022 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1325 +[2025-02-22 10:50:54,086 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3635 +[2025-02-22 10:50:54,212 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4027 +[2025-02-22 10:50:54,349 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5714 +[2025-02-22 10:50:54,560 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0767 +[2025-02-22 10:50:54,721 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4802 +[2025-02-22 10:50:54,800 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.4547 +[2025-02-22 10:50:54,837 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5134 +[2025-02-22 10:50:55,082 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.2874 +[2025-02-22 10:50:55,134 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.0682 +[2025-02-22 10:50:55,177 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2900 +[2025-02-22 10:50:55,280 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8665 +[2025-02-22 10:50:55,393 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0723 +[2025-02-22 10:50:55,497 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3145 +[2025-02-22 10:50:55,581 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3710 +[2025-02-22 10:50:55,649 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0468 +[2025-02-22 10:50:55,769 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0320 +[2025-02-22 10:50:55,819 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5400 +[2025-02-22 10:50:55,915 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.7464 +[2025-02-22 10:50:56,028 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.5501 +[2025-02-22 10:50:56,077 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.3261 +[2025-02-22 10:50:56,191 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0147 +[2025-02-22 10:50:56,232 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0888 +[2025-02-22 10:50:56,461 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0606 +[2025-02-22 10:50:56,558 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0980 +[2025-02-22 10:50:56,626 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8128 +[2025-02-22 10:50:56,678 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2135 +[2025-02-22 10:50:56,834 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1979 +[2025-02-22 10:50:56,937 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5163 +[2025-02-22 10:50:57,001 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3156 +[2025-02-22 10:50:57,121 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.6842 +[2025-02-22 10:50:57,281 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3741 +[2025-02-22 10:50:57,358 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1712 +[2025-02-22 10:50:57,407 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.5992 +[2025-02-22 10:50:57,456 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.3650 +[2025-02-22 10:50:57,593 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.3415 +[2025-02-22 10:50:57,629 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2298 +[2025-02-22 10:50:57,692 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3283 +[2025-02-22 10:50:57,785 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.9405 +[2025-02-22 10:50:57,973 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3361 +[2025-02-22 10:50:58,043 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2577 +[2025-02-22 10:50:58,208 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.1501 +[2025-02-22 10:50:58,296 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3636 +[2025-02-22 10:51:10,867 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 10:51:10,867 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 10:51:10,867 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] cabinet : 0.1085 0.2672 0.5462 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] bed : 0.2390 0.5457 0.6840 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] chair : 0.6189 0.7822 0.8472 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] sofa : 0.2984 0.5815 0.7463 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] table : 0.2490 0.3999 0.5330 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] door : 0.1862 0.3839 0.5565 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] window : 0.0709 0.1957 0.4516 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] bookshelf : 0.1152 0.3896 0.6972 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] picture : 0.1155 0.2371 0.3585 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] counter : 0.0110 0.0567 0.2922 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] desk : 0.0218 0.0929 0.5537 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] curtain : 0.1598 0.3366 0.6020 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] refridgerator : 0.0413 0.1284 0.2519 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] shower curtain : 0.3658 0.6539 0.7884 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] toilet : 0.6480 0.9483 0.9997 +[2025-02-22 10:51:10,867 INFO evaluator.py line 547 2775932] sink : 0.1202 0.4296 0.7902 +[2025-02-22 10:51:10,868 INFO evaluator.py line 547 2775932] bathtub : 0.5291 0.7742 0.8710 +[2025-02-22 10:51:10,868 INFO evaluator.py line 547 2775932] otherfurniture : 0.2225 0.3694 0.5609 +[2025-02-22 10:51:10,868 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 10:51:10,868 INFO evaluator.py line 554 2775932] average : 0.2290 0.4207 0.6184 +[2025-02-22 10:51:10,868 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 10:51:10,868 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 10:51:10,944 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4207 +[2025-02-22 10:51:10,944 INFO misc.py line 164 2775932] Currently Best AP50: 0.4207 +[2025-02-22 10:51:10,944 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 10:51:20,037 INFO hook.py line 109 2775932] Train: [3/100][50/800] Data 0.003 (0.008) Batch 0.153 (0.151) Remain 03:16:51 loss: 0.1584 Lr: 2.56591e-03 +[2025-02-22 10:51:27,401 INFO hook.py line 109 2775932] Train: [3/100][100/800] Data 0.002 (0.008) Batch 0.149 (0.149) Remain 03:14:23 loss: 0.4505 Lr: 2.66851e-03 +[2025-02-22 10:51:34,603 INFO hook.py line 109 2775932] Train: [3/100][150/800] Data 0.003 (0.006) Batch 0.138 (0.147) Remain 03:12:04 loss: 0.1275 Lr: 2.77209e-03 +[2025-02-22 10:51:41,764 INFO hook.py line 109 2775932] Train: [3/100][200/800] Data 0.002 (0.005) Batch 0.133 (0.146) Remain 03:10:37 loss: 0.4230 Lr: 2.87647e-03 +[2025-02-22 10:51:48,740 INFO hook.py line 109 2775932] Train: [3/100][250/800] Data 0.002 (0.005) Batch 0.127 (0.145) Remain 03:08:42 loss: -0.0275 Lr: 2.98152e-03 +[2025-02-22 10:51:55,894 INFO hook.py line 109 2775932] Train: [3/100][300/800] Data 0.003 (0.004) Batch 0.134 (0.145) Remain 03:08:12 loss: 0.1851 Lr: 3.08705e-03 +[2025-02-22 10:52:03,249 INFO hook.py line 109 2775932] Train: [3/100][350/800] Data 0.002 (0.004) Batch 0.139 (0.145) Remain 03:08:33 loss: -0.0402 Lr: 3.19291e-03 +[2025-02-22 10:52:10,457 INFO hook.py line 109 2775932] Train: [3/100][400/800] Data 0.002 (0.004) Batch 0.111 (0.145) Remain 03:08:18 loss: 0.0422 Lr: 3.29894e-03 +[2025-02-22 10:52:17,488 INFO hook.py line 109 2775932] Train: [3/100][450/800] Data 0.002 (0.004) Batch 0.149 (0.144) Remain 03:07:33 loss: -0.0171 Lr: 3.40497e-03 +[2025-02-22 10:52:24,677 INFO hook.py line 109 2775932] Train: [3/100][500/800] Data 0.004 (0.004) Batch 0.165 (0.144) Remain 03:07:22 loss: -0.0182 Lr: 3.51084e-03 +[2025-02-22 10:52:31,862 INFO hook.py line 109 2775932] Train: [3/100][550/800] Data 0.003 (0.004) Batch 0.136 (0.144) Remain 03:07:10 loss: 0.1718 Lr: 3.61638e-03 +[2025-02-22 10:52:39,225 INFO hook.py line 109 2775932] Train: [3/100][600/800] Data 0.003 (0.004) Batch 0.134 (0.145) Remain 03:07:22 loss: -0.0767 Lr: 3.72143e-03 +[2025-02-22 10:52:46,522 INFO hook.py line 109 2775932] Train: [3/100][650/800] Data 0.003 (0.004) Batch 0.151 (0.145) Remain 03:07:24 loss: -0.0009 Lr: 3.82583e-03 +[2025-02-22 10:52:53,648 INFO hook.py line 109 2775932] Train: [3/100][700/800] Data 0.003 (0.004) Batch 0.142 (0.144) Remain 03:07:05 loss: -0.2062 Lr: 3.92943e-03 +[2025-02-22 10:53:00,997 INFO hook.py line 109 2775932] Train: [3/100][750/800] Data 0.003 (0.004) Batch 0.156 (0.145) Remain 03:07:11 loss: -0.3758 Lr: 4.03205e-03 +[2025-02-22 10:53:08,041 INFO hook.py line 109 2775932] Train: [3/100][800/800] Data 0.003 (0.004) Batch 0.107 (0.144) Remain 03:06:45 loss: -0.1472 Lr: 4.13354e-03 +[2025-02-22 10:53:08,043 INFO misc.py line 135 2775932] Train result: loss: 0.0312 seg_loss: 0.5041 bias_l1_loss: 0.3886 bias_cosine_loss: -0.8614 +[2025-02-22 10:53:08,044 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 10:53:15,200 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.3783 +[2025-02-22 10:53:15,488 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0016 +[2025-02-22 10:53:15,936 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.1000 +[2025-02-22 10:53:16,009 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.2690 +[2025-02-22 10:53:16,064 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.2189 +[2025-02-22 10:53:16,117 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9369 +[2025-02-22 10:53:16,387 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.1108 +[2025-02-22 10:53:16,415 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.1738 +[2025-02-22 10:53:16,575 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.1401 +[2025-02-22 10:53:16,636 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2947 +[2025-02-22 10:53:16,895 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2402 +[2025-02-22 10:53:17,009 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0029 +[2025-02-22 10:53:17,075 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.4367 +[2025-02-22 10:53:17,164 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.5254 +[2025-02-22 10:53:17,249 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8561 +[2025-02-22 10:53:17,306 INFO evaluator.py line 595 2775932] Test: [16/78] Loss 0.9328 +[2025-02-22 10:53:17,443 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.3446 +[2025-02-22 10:53:17,535 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.3889 +[2025-02-22 10:53:17,687 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.5015 +[2025-02-22 10:53:17,754 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.6771 +[2025-02-22 10:53:17,896 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.2392 +[2025-02-22 10:53:18,075 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4650 +[2025-02-22 10:53:18,153 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1641 +[2025-02-22 10:53:18,202 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0180 +[2025-02-22 10:53:18,255 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0051 +[2025-02-22 10:53:18,310 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.1759 +[2025-02-22 10:53:18,467 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.6006 +[2025-02-22 10:53:18,610 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.4074 +[2025-02-22 10:53:18,684 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.0849 +[2025-02-22 10:53:18,759 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4155 +[2025-02-22 10:53:19,549 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.0814 +[2025-02-22 10:53:19,675 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 2.0237 +[2025-02-22 10:53:19,707 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4380 +[2025-02-22 10:53:19,807 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0790 +[2025-02-22 10:53:19,838 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5574 +[2025-02-22 10:53:19,962 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2992 +[2025-02-22 10:53:20,033 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3531 +[2025-02-22 10:53:20,173 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.1254 +[2025-02-22 10:53:20,340 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6075 +[2025-02-22 10:53:20,562 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0166 +[2025-02-22 10:53:20,724 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6555 +[2025-02-22 10:53:20,776 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.4528 +[2025-02-22 10:53:20,816 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.3394 +[2025-02-22 10:53:21,109 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.2064 +[2025-02-22 10:53:21,160 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.0456 +[2025-02-22 10:53:21,209 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.1103 +[2025-02-22 10:53:21,305 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4284 +[2025-02-22 10:53:21,421 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.3419 +[2025-02-22 10:53:21,533 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.5509 +[2025-02-22 10:53:21,608 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.5074 +[2025-02-22 10:53:21,694 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.3626 +[2025-02-22 10:53:21,813 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0294 +[2025-02-22 10:53:21,871 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6171 +[2025-02-22 10:53:21,965 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1418 +[2025-02-22 10:53:22,057 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.5005 +[2025-02-22 10:53:22,098 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5631 +[2025-02-22 10:53:22,223 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0577 +[2025-02-22 10:53:22,262 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0764 +[2025-02-22 10:53:22,481 INFO evaluator.py line 595 2775932] Test: [59/78] Loss 0.2404 +[2025-02-22 10:53:22,605 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0925 +[2025-02-22 10:53:22,682 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.7109 +[2025-02-22 10:53:22,734 INFO evaluator.py line 595 2775932] Test: [62/78] Loss 0.0550 +[2025-02-22 10:53:22,893 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.3603 +[2025-02-22 10:53:23,108 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.9296 +[2025-02-22 10:53:23,183 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.7747 +[2025-02-22 10:53:23,298 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0303 +[2025-02-22 10:53:23,445 INFO evaluator.py line 595 2775932] Test: [67/78] Loss 0.1680 +[2025-02-22 10:53:23,519 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5467 +[2025-02-22 10:53:23,565 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.5445 +[2025-02-22 10:53:23,636 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0488 +[2025-02-22 10:53:23,795 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.5734 +[2025-02-22 10:53:23,826 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2475 +[2025-02-22 10:53:23,882 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3868 +[2025-02-22 10:53:23,971 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3363 +[2025-02-22 10:53:24,177 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3197 +[2025-02-22 10:53:24,249 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.3574 +[2025-02-22 10:53:24,413 INFO evaluator.py line 595 2775932] Test: [77/78] Loss 0.1238 +[2025-02-22 10:53:24,494 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4120 +[2025-02-22 10:53:37,085 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 10:53:37,086 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 10:53:37,086 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] cabinet : 0.0614 0.1709 0.4096 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] bed : 0.2562 0.5557 0.7182 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] chair : 0.5167 0.7271 0.8191 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] sofa : 0.1927 0.3777 0.6113 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] table : 0.2650 0.4594 0.5758 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] door : 0.1560 0.3341 0.4695 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] window : 0.0660 0.1791 0.4352 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] bookshelf : 0.0092 0.0447 0.2300 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] picture : 0.1482 0.2737 0.3859 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] counter : 0.0117 0.0435 0.2218 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] desk : 0.0087 0.0419 0.3362 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] curtain : 0.0747 0.2140 0.4484 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] refridgerator : 0.2005 0.3089 0.3623 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] shower curtain : 0.3429 0.5621 0.6562 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] toilet : 0.5529 0.9078 0.9594 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] sink : 0.0825 0.2627 0.4766 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] bathtub : 0.4586 0.7288 0.8064 +[2025-02-22 10:53:37,086 INFO evaluator.py line 547 2775932] otherfurniture : 0.2449 0.4127 0.5780 +[2025-02-22 10:53:37,086 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 10:53:37,086 INFO evaluator.py line 554 2775932] average : 0.2027 0.3669 0.5278 +[2025-02-22 10:53:37,086 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 10:53:37,086 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 10:53:37,159 INFO misc.py line 164 2775932] Currently Best AP50: 0.4207 +[2025-02-22 10:53:37,160 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 10:53:45,603 INFO hook.py line 109 2775932] Train: [4/100][50/800] Data 0.002 (0.003) Batch 0.135 (0.144) Remain 03:06:07 loss: -0.4393 Lr: 4.23374e-03 +[2025-02-22 10:53:52,751 INFO hook.py line 109 2775932] Train: [4/100][100/800] Data 0.003 (0.003) Batch 0.123 (0.143) Remain 03:05:19 loss: -0.0962 Lr: 4.33251e-03 +[2025-02-22 10:54:00,063 INFO hook.py line 109 2775932] Train: [4/100][150/800] Data 0.003 (0.003) Batch 0.274 (0.144) Remain 03:06:24 loss: 0.0809 Lr: 4.42776e-03 +[2025-02-22 10:54:07,007 INFO hook.py line 109 2775932] Train: [4/100][200/800] Data 0.004 (0.003) Batch 0.130 (0.143) Remain 03:04:28 loss: 0.0423 Lr: 4.52322e-03 +[2025-02-22 10:54:14,223 INFO hook.py line 109 2775932] Train: [4/100][250/800] Data 0.003 (0.003) Batch 0.130 (0.143) Remain 03:04:42 loss: -0.2465 Lr: 4.61680e-03 +[2025-02-22 10:54:21,334 INFO hook.py line 109 2775932] Train: [4/100][300/800] Data 0.003 (0.003) Batch 0.152 (0.143) Remain 03:04:21 loss: 0.7151 Lr: 4.70835e-03 +[2025-02-22 10:54:28,776 INFO hook.py line 109 2775932] Train: [4/100][350/800] Data 0.002 (0.003) Batch 0.166 (0.144) Remain 03:05:17 loss: -0.2422 Lr: 4.79772e-03 +[2025-02-22 10:54:36,010 INFO hook.py line 109 2775932] Train: [4/100][400/800] Data 0.004 (0.003) Batch 0.172 (0.144) Remain 03:05:18 loss: 0.0274 Lr: 4.88479e-03 +[2025-02-22 10:54:43,305 INFO hook.py line 109 2775932] Train: [4/100][450/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 03:05:27 loss: -0.1410 Lr: 4.96941e-03 +[2025-02-22 10:54:50,414 INFO hook.py line 109 2775932] Train: [4/100][500/800] Data 0.002 (0.003) Batch 0.137 (0.144) Remain 03:05:04 loss: -0.3210 Lr: 5.05145e-03 +[2025-02-22 10:54:57,891 INFO hook.py line 109 2775932] Train: [4/100][550/800] Data 0.002 (0.003) Batch 0.147 (0.145) Remain 03:05:35 loss: 0.4287 Lr: 5.13079e-03 +[2025-02-22 10:55:05,094 INFO hook.py line 109 2775932] Train: [4/100][600/800] Data 0.003 (0.003) Batch 0.144 (0.144) Remain 03:05:25 loss: 0.2162 Lr: 5.20731e-03 +[2025-02-22 10:55:12,568 INFO hook.py line 109 2775932] Train: [4/100][650/800] Data 0.003 (0.004) Batch 0.158 (0.145) Remain 03:05:47 loss: 0.0305 Lr: 5.28089e-03 +[2025-02-22 10:55:19,784 INFO hook.py line 109 2775932] Train: [4/100][700/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 03:05:37 loss: 0.6967 Lr: 5.35141e-03 +[2025-02-22 10:55:27,021 INFO hook.py line 109 2775932] Train: [4/100][750/800] Data 0.003 (0.004) Batch 0.121 (0.145) Remain 03:05:29 loss: -0.2193 Lr: 5.41876e-03 +[2025-02-22 10:55:33,951 INFO hook.py line 109 2775932] Train: [4/100][800/800] Data 0.002 (0.003) Batch 0.127 (0.144) Remain 03:04:52 loss: 0.0640 Lr: 5.48285e-03 +[2025-02-22 10:55:33,952 INFO misc.py line 135 2775932] Train result: loss: 0.0156 seg_loss: 0.4943 bias_l1_loss: 0.3867 bias_cosine_loss: -0.8654 +[2025-02-22 10:55:33,952 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 10:55:41,217 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.5525 +[2025-02-22 10:55:41,459 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0027 +[2025-02-22 10:55:41,514 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.1055 +[2025-02-22 10:55:41,950 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3857 +[2025-02-22 10:55:42,009 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.0316 +[2025-02-22 10:55:42,062 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9917 +[2025-02-22 10:55:42,363 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.1517 +[2025-02-22 10:55:42,399 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.2560 +[2025-02-22 10:55:42,554 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.1870 +[2025-02-22 10:55:42,611 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.8900 +[2025-02-22 10:55:42,851 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3066 +[2025-02-22 10:55:42,959 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.3620 +[2025-02-22 10:55:43,028 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.6591 +[2025-02-22 10:55:43,112 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.5640 +[2025-02-22 10:55:43,199 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 1.0860 +[2025-02-22 10:55:43,261 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3428 +[2025-02-22 10:55:43,410 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.0264 +[2025-02-22 10:55:43,494 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.6049 +[2025-02-22 10:55:43,691 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4607 +[2025-02-22 10:55:43,771 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0322 +[2025-02-22 10:55:43,928 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4461 +[2025-02-22 10:55:44,090 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.6441 +[2025-02-22 10:55:44,173 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.4078 +[2025-02-22 10:55:44,235 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0291 +[2025-02-22 10:55:44,307 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.2527 +[2025-02-22 10:55:44,381 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.0748 +[2025-02-22 10:55:44,520 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.5655 +[2025-02-22 10:55:44,612 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0914 +[2025-02-22 10:55:44,696 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.3304 +[2025-02-22 10:55:44,787 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.0972 +[2025-02-22 10:55:45,547 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.2495 +[2025-02-22 10:55:45,651 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.6939 +[2025-02-22 10:55:45,692 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4095 +[2025-02-22 10:55:45,795 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.6402 +[2025-02-22 10:55:45,833 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4801 +[2025-02-22 10:55:45,970 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2498 +[2025-02-22 10:55:46,040 INFO evaluator.py line 595 2775932] Test: [37/78] Loss 0.0204 +[2025-02-22 10:55:46,180 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.3686 +[2025-02-22 10:55:46,321 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8387 +[2025-02-22 10:55:46,541 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.4142 +[2025-02-22 10:55:46,752 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 1.3295 +[2025-02-22 10:55:46,804 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0245 +[2025-02-22 10:55:46,848 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4879 +[2025-02-22 10:55:47,101 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.2768 +[2025-02-22 10:55:47,145 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.1034 +[2025-02-22 10:55:47,184 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2834 +[2025-02-22 10:55:47,281 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8111 +[2025-02-22 10:55:47,411 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.1828 +[2025-02-22 10:55:47,511 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.4979 +[2025-02-22 10:55:47,592 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.7394 +[2025-02-22 10:55:47,655 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.6758 +[2025-02-22 10:55:47,790 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.4292 +[2025-02-22 10:55:47,828 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.0060 +[2025-02-22 10:55:47,931 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 3.4065 +[2025-02-22 10:55:48,049 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.5965 +[2025-02-22 10:55:48,100 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.4345 +[2025-02-22 10:55:48,220 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0889 +[2025-02-22 10:55:48,260 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0483 +[2025-02-22 10:55:48,503 INFO evaluator.py line 595 2775932] Test: [59/78] Loss 0.2500 +[2025-02-22 10:55:48,623 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0735 +[2025-02-22 10:55:48,691 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.1973 +[2025-02-22 10:55:48,756 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.1581 +[2025-02-22 10:55:48,905 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.4704 +[2025-02-22 10:55:49,015 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7448 +[2025-02-22 10:55:49,075 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4552 +[2025-02-22 10:55:49,194 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0195 +[2025-02-22 10:55:49,357 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2367 +[2025-02-22 10:55:49,431 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5527 +[2025-02-22 10:55:49,481 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6544 +[2025-02-22 10:55:49,536 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1710 +[2025-02-22 10:55:49,688 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.4238 +[2025-02-22 10:55:49,723 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2710 +[2025-02-22 10:55:49,782 INFO evaluator.py line 595 2775932] Test: [73/78] Loss 0.0534 +[2025-02-22 10:55:49,889 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 3.9713 +[2025-02-22 10:55:50,115 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3777 +[2025-02-22 10:55:50,191 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.5365 +[2025-02-22 10:55:50,387 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.0016 +[2025-02-22 10:55:50,480 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4091 +[2025-02-22 10:56:04,295 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 10:56:04,295 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 10:56:04,295 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] cabinet : 0.0501 0.1659 0.4320 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] bed : 0.2921 0.6487 0.7811 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] chair : 0.6418 0.8305 0.8932 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] sofa : 0.2432 0.4735 0.7487 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] table : 0.1961 0.3798 0.5108 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] door : 0.1122 0.2499 0.3912 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] window : 0.0615 0.1584 0.4159 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] bookshelf : 0.0495 0.2140 0.5474 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] picture : 0.1690 0.3076 0.3957 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] counter : 0.0000 0.0000 0.0259 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] desk : 0.0067 0.0411 0.4277 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] curtain : 0.1045 0.2070 0.3697 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] refridgerator : 0.1923 0.3424 0.4071 +[2025-02-22 10:56:04,295 INFO evaluator.py line 547 2775932] shower curtain : 0.3628 0.5922 0.6195 +[2025-02-22 10:56:04,296 INFO evaluator.py line 547 2775932] toilet : 0.7697 0.9655 0.9819 +[2025-02-22 10:56:04,296 INFO evaluator.py line 547 2775932] sink : 0.1993 0.4684 0.8262 +[2025-02-22 10:56:04,296 INFO evaluator.py line 547 2775932] bathtub : 0.5265 0.7327 0.8387 +[2025-02-22 10:56:04,296 INFO evaluator.py line 547 2775932] otherfurniture : 0.2323 0.4177 0.6156 +[2025-02-22 10:56:04,296 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 10:56:04,296 INFO evaluator.py line 554 2775932] average : 0.2339 0.3997 0.5683 +[2025-02-22 10:56:04,296 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 10:56:04,296 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 10:56:04,374 INFO misc.py line 164 2775932] Currently Best AP50: 0.4207 +[2025-02-22 10:56:04,375 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 10:56:12,701 INFO hook.py line 109 2775932] Train: [5/100][50/800] Data 0.002 (0.003) Batch 0.134 (0.146) Remain 03:06:55 loss: -0.1049 Lr: 5.54357e-03 +[2025-02-22 10:56:19,840 INFO hook.py line 109 2775932] Train: [5/100][100/800] Data 0.003 (0.003) Batch 0.124 (0.144) Remain 03:04:35 loss: 0.3799 Lr: 5.60083e-03 +[2025-02-22 10:56:27,061 INFO hook.py line 109 2775932] Train: [5/100][150/800] Data 0.002 (0.004) Batch 0.138 (0.144) Remain 03:04:29 loss: -0.2675 Lr: 5.65453e-03 +[2025-02-22 10:56:34,267 INFO hook.py line 109 2775932] Train: [5/100][200/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 03:04:16 loss: 0.2412 Lr: 5.70461e-03 +[2025-02-22 10:56:41,788 INFO hook.py line 109 2775932] Train: [5/100][250/800] Data 0.003 (0.004) Batch 0.169 (0.146) Remain 03:05:42 loss: -0.0112 Lr: 5.75098e-03 +[2025-02-22 10:56:48,795 INFO hook.py line 109 2775932] Train: [5/100][300/800] Data 0.002 (0.003) Batch 0.134 (0.145) Remain 03:04:25 loss: 0.1073 Lr: 5.79356e-03 +[2025-02-22 10:56:55,869 INFO hook.py line 109 2775932] Train: [5/100][350/800] Data 0.003 (0.003) Batch 0.137 (0.144) Remain 03:03:43 loss: -0.0644 Lr: 5.83230e-03 +[2025-02-22 10:57:03,096 INFO hook.py line 109 2775932] Train: [5/100][400/800] Data 0.002 (0.003) Batch 0.157 (0.144) Remain 03:03:39 loss: -0.1111 Lr: 5.86713e-03 +[2025-02-22 10:57:10,324 INFO hook.py line 109 2775932] Train: [5/100][450/800] Data 0.003 (0.003) Batch 0.150 (0.144) Remain 03:03:35 loss: -0.2039 Lr: 5.89800e-03 +[2025-02-22 10:57:17,569 INFO hook.py line 109 2775932] Train: [5/100][500/800] Data 0.003 (0.003) Batch 0.131 (0.144) Remain 03:03:32 loss: 0.1144 Lr: 5.92487e-03 +[2025-02-22 10:57:24,593 INFO hook.py line 109 2775932] Train: [5/100][550/800] Data 0.003 (0.003) Batch 0.142 (0.144) Remain 03:02:58 loss: -0.2272 Lr: 5.94768e-03 +[2025-02-22 10:57:31,778 INFO hook.py line 109 2775932] Train: [5/100][600/800] Data 0.002 (0.003) Batch 0.119 (0.144) Remain 03:02:49 loss: -0.3275 Lr: 5.96641e-03 +[2025-02-22 10:57:38,942 INFO hook.py line 109 2775932] Train: [5/100][650/800] Data 0.003 (0.003) Batch 0.139 (0.144) Remain 03:02:38 loss: 0.3335 Lr: 5.98103e-03 +[2025-02-22 10:57:46,157 INFO hook.py line 109 2775932] Train: [5/100][700/800] Data 0.003 (0.003) Batch 0.139 (0.144) Remain 03:02:33 loss: 0.3125 Lr: 5.99151e-03 +[2025-02-22 10:57:53,426 INFO hook.py line 109 2775932] Train: [5/100][750/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 03:02:33 loss: -0.0390 Lr: 5.99783e-03 +[2025-02-22 10:58:00,462 INFO hook.py line 109 2775932] Train: [5/100][800/800] Data 0.002 (0.003) Batch 0.105 (0.144) Remain 03:02:10 loss: -0.0813 Lr: 6.00000e-03 +[2025-02-22 10:58:00,463 INFO misc.py line 135 2775932] Train result: loss: -0.0279 seg_loss: 0.4693 bias_l1_loss: 0.3743 bias_cosine_loss: -0.8715 +[2025-02-22 10:58:00,464 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 10:58:07,890 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.4471 +[2025-02-22 10:58:08,081 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.4139 +[2025-02-22 10:58:08,138 INFO evaluator.py line 595 2775932] Test: [3/78] Loss 0.0755 +[2025-02-22 10:58:08,434 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.2557 +[2025-02-22 10:58:08,537 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3320 +[2025-02-22 10:58:08,589 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.1267 +[2025-02-22 10:58:08,894 INFO evaluator.py line 595 2775932] Test: [7/78] Loss 0.0071 +[2025-02-22 10:58:08,929 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3266 +[2025-02-22 10:58:09,073 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.1088 +[2025-02-22 10:58:09,145 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.7143 +[2025-02-22 10:58:09,427 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.4892 +[2025-02-22 10:58:09,535 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1628 +[2025-02-22 10:58:09,614 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.8262 +[2025-02-22 10:58:09,702 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3322 +[2025-02-22 10:58:09,784 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 1.0550 +[2025-02-22 10:58:09,874 INFO evaluator.py line 595 2775932] Test: [16/78] Loss 0.0356 +[2025-02-22 10:58:10,029 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.3646 +[2025-02-22 10:58:10,123 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.4696 +[2025-02-22 10:58:10,319 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2964 +[2025-02-22 10:58:10,382 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2122 +[2025-02-22 10:58:10,541 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.3343 +[2025-02-22 10:58:10,731 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.6511 +[2025-02-22 10:58:10,807 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.5074 +[2025-02-22 10:58:10,856 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0243 +[2025-02-22 10:58:10,912 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1500 +[2025-02-22 10:58:10,975 INFO evaluator.py line 595 2775932] Test: [26/78] Loss 0.0940 +[2025-02-22 10:58:11,119 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 1.2304 +[2025-02-22 10:58:11,208 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.2779 +[2025-02-22 10:58:11,287 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.2443 +[2025-02-22 10:58:11,364 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.0490 +[2025-02-22 10:58:12,166 INFO evaluator.py line 595 2775932] Test: [31/78] Loss 0.0236 +[2025-02-22 10:58:12,286 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.1501 +[2025-02-22 10:58:12,332 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5386 +[2025-02-22 10:58:12,434 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2202 +[2025-02-22 10:58:12,473 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3280 +[2025-02-22 10:58:12,605 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.4575 +[2025-02-22 10:58:12,700 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.1930 +[2025-02-22 10:58:12,823 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.2964 +[2025-02-22 10:58:12,964 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7865 +[2025-02-22 10:58:13,171 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.5715 +[2025-02-22 10:58:13,347 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.9804 +[2025-02-22 10:58:13,398 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.5862 +[2025-02-22 10:58:13,460 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4727 +[2025-02-22 10:58:13,758 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.1221 +[2025-02-22 10:58:13,796 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.0297 +[2025-02-22 10:58:13,838 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2586 +[2025-02-22 10:58:13,935 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7192 +[2025-02-22 10:58:14,091 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.2837 +[2025-02-22 10:58:14,208 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.8120 +[2025-02-22 10:58:14,296 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2388 +[2025-02-22 10:58:14,366 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 1.3111 +[2025-02-22 10:58:14,506 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.4218 +[2025-02-22 10:58:14,565 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6099 +[2025-02-22 10:58:14,707 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 3.6996 +[2025-02-22 10:58:14,831 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.5529 +[2025-02-22 10:58:14,876 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5944 +[2025-02-22 10:58:15,028 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.4959 +[2025-02-22 10:58:15,068 INFO evaluator.py line 595 2775932] Test: [58/78] Loss 0.1795 +[2025-02-22 10:58:15,347 INFO evaluator.py line 595 2775932] Test: [59/78] Loss 0.0886 +[2025-02-22 10:58:15,456 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0824 +[2025-02-22 10:58:15,534 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.5610 +[2025-02-22 10:58:15,625 INFO evaluator.py line 595 2775932] Test: [62/78] Loss 0.0646 +[2025-02-22 10:58:15,808 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.3300 +[2025-02-22 10:58:15,919 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.9848 +[2025-02-22 10:58:15,991 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.9725 +[2025-02-22 10:58:16,115 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.4996 +[2025-02-22 10:58:16,327 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.1410 +[2025-02-22 10:58:16,412 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.3019 +[2025-02-22 10:58:16,464 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.5125 +[2025-02-22 10:58:16,524 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0931 +[2025-02-22 10:58:16,667 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.5068 +[2025-02-22 10:58:16,706 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2307 +[2025-02-22 10:58:16,764 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3984 +[2025-02-22 10:58:16,893 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 4.2601 +[2025-02-22 10:58:17,086 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3099 +[2025-02-22 10:58:17,156 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.7863 +[2025-02-22 10:58:17,312 INFO evaluator.py line 595 2775932] Test: [77/78] Loss 0.0135 +[2025-02-22 10:58:17,389 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.2009 +[2025-02-22 10:58:31,697 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 10:58:31,697 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 10:58:31,697 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] cabinet : 0.1137 0.3049 0.5717 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] bed : 0.2000 0.4756 0.7245 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] chair : 0.5442 0.7578 0.8390 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] sofa : 0.2228 0.4968 0.7224 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] table : 0.2495 0.4480 0.5486 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] door : 0.1171 0.2777 0.4207 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] window : 0.0204 0.0551 0.1580 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] bookshelf : 0.1155 0.3801 0.7042 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] picture : 0.2248 0.3578 0.4916 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] counter : 0.0325 0.1030 0.3843 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] desk : 0.0145 0.0683 0.4425 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] curtain : 0.0193 0.0805 0.2985 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] refridgerator : 0.2242 0.4074 0.4436 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] shower curtain : 0.3526 0.5182 0.7079 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] toilet : 0.7407 0.9828 0.9828 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] sink : 0.2443 0.6051 0.7986 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] bathtub : 0.3202 0.5090 0.6758 +[2025-02-22 10:58:31,697 INFO evaluator.py line 547 2775932] otherfurniture : 0.2409 0.4040 0.6151 +[2025-02-22 10:58:31,697 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 10:58:31,697 INFO evaluator.py line 554 2775932] average : 0.2221 0.4018 0.5850 +[2025-02-22 10:58:31,697 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 10:58:31,697 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 10:58:31,770 INFO misc.py line 164 2775932] Currently Best AP50: 0.4207 +[2025-02-22 10:58:31,771 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 10:58:40,102 INFO hook.py line 109 2775932] Train: [6/100][50/800] Data 0.002 (0.003) Batch 0.154 (0.145) Remain 03:03:18 loss: 0.0269 Lr: 5.99999e-03 +[2025-02-22 10:58:47,367 INFO hook.py line 109 2775932] Train: [6/100][100/800] Data 0.003 (0.003) Batch 0.126 (0.145) Remain 03:03:29 loss: -0.1464 Lr: 5.99997e-03 +[2025-02-22 10:58:54,472 INFO hook.py line 109 2775932] Train: [6/100][150/800] Data 0.004 (0.003) Batch 0.135 (0.144) Remain 03:02:06 loss: -0.2126 Lr: 5.99994e-03 +[2025-02-22 10:59:01,718 INFO hook.py line 109 2775932] Train: [6/100][200/800] Data 0.002 (0.003) Batch 0.143 (0.144) Remain 03:02:15 loss: 0.0775 Lr: 5.99990e-03 +[2025-02-22 10:59:08,792 INFO hook.py line 109 2775932] Train: [6/100][250/800] Data 0.002 (0.003) Batch 0.147 (0.144) Remain 03:01:25 loss: 0.1483 Lr: 5.99984e-03 +[2025-02-22 10:59:15,930 INFO hook.py line 109 2775932] Train: [6/100][300/800] Data 0.003 (0.003) Batch 0.142 (0.144) Remain 03:01:06 loss: 0.0046 Lr: 5.99977e-03 +[2025-02-22 10:59:23,401 INFO hook.py line 109 2775932] Train: [6/100][350/800] Data 0.002 (0.004) Batch 0.151 (0.144) Remain 03:02:03 loss: 0.2220 Lr: 5.99969e-03 +[2025-02-22 10:59:30,732 INFO hook.py line 109 2775932] Train: [6/100][400/800] Data 0.002 (0.004) Batch 0.151 (0.145) Remain 03:02:17 loss: -0.2796 Lr: 5.99959e-03 +[2025-02-22 10:59:37,943 INFO hook.py line 109 2775932] Train: [6/100][450/800] Data 0.003 (0.003) Batch 0.143 (0.145) Remain 03:02:05 loss: 0.6288 Lr: 5.99948e-03 +[2025-02-22 10:59:45,196 INFO hook.py line 109 2775932] Train: [6/100][500/800] Data 0.002 (0.004) Batch 0.128 (0.145) Remain 03:02:02 loss: -0.2100 Lr: 5.99936e-03 +[2025-02-22 10:59:52,410 INFO hook.py line 109 2775932] Train: [6/100][550/800] Data 0.003 (0.004) Batch 0.145 (0.145) Remain 03:01:52 loss: -0.2177 Lr: 5.99923e-03 +[2025-02-22 10:59:59,785 INFO hook.py line 109 2775932] Train: [6/100][600/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 03:02:03 loss: 1.2635 Lr: 5.99908e-03 +[2025-02-22 11:00:07,111 INFO hook.py line 109 2775932] Train: [6/100][650/800] Data 0.004 (0.004) Batch 0.147 (0.145) Remain 03:02:05 loss: 0.0541 Lr: 5.99892e-03 +[2025-02-22 11:00:14,176 INFO hook.py line 109 2775932] Train: [6/100][700/800] Data 0.004 (0.003) Batch 0.142 (0.145) Remain 03:01:38 loss: -0.2337 Lr: 5.99875e-03 +[2025-02-22 11:00:21,417 INFO hook.py line 109 2775932] Train: [6/100][750/800] Data 0.002 (0.003) Batch 0.140 (0.145) Remain 03:01:31 loss: -0.2737 Lr: 5.99857e-03 +[2025-02-22 11:00:28,272 INFO hook.py line 109 2775932] Train: [6/100][800/800] Data 0.001 (0.003) Batch 0.112 (0.144) Remain 03:00:48 loss: -0.2314 Lr: 5.99837e-03 +[2025-02-22 11:00:28,273 INFO misc.py line 135 2775932] Train result: loss: -0.0867 seg_loss: 0.4349 bias_l1_loss: 0.3582 bias_cosine_loss: -0.8798 +[2025-02-22 11:00:28,274 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:00:35,791 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.5045 +[2025-02-22 11:00:35,991 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0243 +[2025-02-22 11:00:36,055 INFO evaluator.py line 595 2775932] Test: [3/78] Loss 0.0383 +[2025-02-22 11:00:36,127 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3384 +[2025-02-22 11:00:36,193 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3777 +[2025-02-22 11:00:36,265 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7920 +[2025-02-22 11:00:36,573 INFO evaluator.py line 595 2775932] Test: [7/78] Loss 0.0155 +[2025-02-22 11:00:36,617 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3368 +[2025-02-22 11:00:36,746 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.2813 +[2025-02-22 11:00:36,806 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.5553 +[2025-02-22 11:00:37,068 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2500 +[2025-02-22 11:00:37,168 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0664 +[2025-02-22 11:00:37,258 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4341 +[2025-02-22 11:00:37,345 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2639 +[2025-02-22 11:00:37,434 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5972 +[2025-02-22 11:00:37,502 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.1630 +[2025-02-22 11:00:37,667 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.0430 +[2025-02-22 11:00:37,753 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.3774 +[2025-02-22 11:00:37,916 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4846 +[2025-02-22 11:00:37,982 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0921 +[2025-02-22 11:00:38,149 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4369 +[2025-02-22 11:00:38,329 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4309 +[2025-02-22 11:00:38,400 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.4648 +[2025-02-22 11:00:38,463 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0958 +[2025-02-22 11:00:38,534 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.1983 +[2025-02-22 11:00:38,597 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3010 +[2025-02-22 11:00:38,734 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4969 +[2025-02-22 11:00:38,839 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6606 +[2025-02-22 11:00:38,913 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.3166 +[2025-02-22 11:00:38,988 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3808 +[2025-02-22 11:00:39,780 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.1624 +[2025-02-22 11:00:39,908 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.1564 +[2025-02-22 11:00:39,953 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5931 +[2025-02-22 11:00:40,052 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2381 +[2025-02-22 11:00:40,096 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3620 +[2025-02-22 11:00:40,216 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.3778 +[2025-02-22 11:00:40,305 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4277 +[2025-02-22 11:00:40,446 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.3562 +[2025-02-22 11:00:40,607 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4865 +[2025-02-22 11:00:40,854 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1326 +[2025-02-22 11:00:41,018 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5162 +[2025-02-22 11:00:41,072 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1671 +[2025-02-22 11:00:41,115 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4360 +[2025-02-22 11:00:41,394 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4400 +[2025-02-22 11:00:41,450 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.0107 +[2025-02-22 11:00:41,507 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4042 +[2025-02-22 11:00:41,608 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7741 +[2025-02-22 11:00:41,727 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.1882 +[2025-02-22 11:00:41,838 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.8081 +[2025-02-22 11:00:41,916 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2212 +[2025-02-22 11:00:41,988 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.9477 +[2025-02-22 11:00:42,120 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.1193 +[2025-02-22 11:00:42,163 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6717 +[2025-02-22 11:00:42,256 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.9835 +[2025-02-22 11:00:42,353 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6220 +[2025-02-22 11:00:42,396 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5852 +[2025-02-22 11:00:42,525 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.2142 +[2025-02-22 11:00:42,571 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0964 +[2025-02-22 11:00:42,804 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0614 +[2025-02-22 11:00:42,929 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0959 +[2025-02-22 11:00:42,994 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.9200 +[2025-02-22 11:00:43,052 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2192 +[2025-02-22 11:00:43,247 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.6971 +[2025-02-22 11:00:43,362 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.8724 +[2025-02-22 11:00:43,436 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.8731 +[2025-02-22 11:00:43,556 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1437 +[2025-02-22 11:00:43,727 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.0208 +[2025-02-22 11:00:43,809 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2747 +[2025-02-22 11:00:43,866 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6566 +[2025-02-22 11:00:43,919 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1287 +[2025-02-22 11:00:44,062 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1402 +[2025-02-22 11:00:44,100 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3027 +[2025-02-22 11:00:44,160 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.4326 +[2025-02-22 11:00:44,254 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8971 +[2025-02-22 11:00:44,476 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3631 +[2025-02-22 11:00:44,567 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1012 +[2025-02-22 11:00:44,746 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.0989 +[2025-02-22 11:00:44,853 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3451 +[2025-02-22 11:00:59,683 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:00:59,683 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:00:59,683 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] cabinet : 0.1093 0.2759 0.5519 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] bed : 0.2995 0.6940 0.7876 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] chair : 0.6370 0.8096 0.8722 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] sofa : 0.2768 0.5172 0.7868 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] table : 0.2394 0.4157 0.5429 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] door : 0.1651 0.3450 0.5062 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] window : 0.0661 0.1425 0.2893 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] bookshelf : 0.1687 0.4639 0.6882 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] picture : 0.1863 0.3395 0.4392 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] counter : 0.0185 0.0761 0.3042 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] desk : 0.0205 0.0745 0.3901 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] curtain : 0.0765 0.1468 0.3098 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] refridgerator : 0.1992 0.3247 0.3247 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] shower curtain : 0.4353 0.6247 0.7275 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] toilet : 0.7944 0.9788 0.9788 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] sink : 0.1926 0.4562 0.7754 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] bathtub : 0.4257 0.6352 0.7737 +[2025-02-22 11:00:59,683 INFO evaluator.py line 547 2775932] otherfurniture : 0.2977 0.4569 0.5958 +[2025-02-22 11:00:59,683 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:00:59,683 INFO evaluator.py line 554 2775932] average : 0.2560 0.4321 0.5914 +[2025-02-22 11:00:59,683 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:00:59,684 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:00:59,760 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4321 +[2025-02-22 11:00:59,761 INFO misc.py line 164 2775932] Currently Best AP50: 0.4321 +[2025-02-22 11:00:59,762 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:01:09,070 INFO hook.py line 109 2775932] Train: [7/100][50/800] Data 0.003 (0.009) Batch 0.150 (0.151) Remain 03:09:08 loss: -0.1176 Lr: 5.99816e-03 +[2025-02-22 11:01:16,388 INFO hook.py line 109 2775932] Train: [7/100][100/800] Data 0.002 (0.006) Batch 0.130 (0.149) Remain 03:06:00 loss: -0.2279 Lr: 5.99793e-03 +[2025-02-22 11:01:23,661 INFO hook.py line 109 2775932] Train: [7/100][150/800] Data 0.003 (0.005) Batch 0.146 (0.148) Remain 03:04:32 loss: -0.2536 Lr: 5.99770e-03 +[2025-02-22 11:01:30,945 INFO hook.py line 109 2775932] Train: [7/100][200/800] Data 0.003 (0.006) Batch 0.142 (0.147) Remain 03:03:50 loss: -0.2064 Lr: 5.99745e-03 +[2025-02-22 11:01:38,064 INFO hook.py line 109 2775932] Train: [7/100][250/800] Data 0.002 (0.005) Batch 0.154 (0.146) Remain 03:02:31 loss: -0.0528 Lr: 5.99719e-03 +[2025-02-22 11:01:45,280 INFO hook.py line 109 2775932] Train: [7/100][300/800] Data 0.003 (0.005) Batch 0.149 (0.146) Remain 03:02:01 loss: 0.0364 Lr: 5.99691e-03 +[2025-02-22 11:01:52,621 INFO hook.py line 109 2775932] Train: [7/100][350/800] Data 0.007 (0.004) Batch 0.141 (0.146) Remain 03:02:04 loss: -0.1518 Lr: 5.99662e-03 +[2025-02-22 11:01:59,774 INFO hook.py line 109 2775932] Train: [7/100][400/800] Data 0.003 (0.004) Batch 0.169 (0.146) Remain 03:01:30 loss: -0.0776 Lr: 5.99632e-03 +[2025-02-22 11:02:06,882 INFO hook.py line 109 2775932] Train: [7/100][450/800] Data 0.002 (0.004) Batch 0.124 (0.145) Remain 03:00:54 loss: 0.1923 Lr: 5.99601e-03 +[2025-02-22 11:02:14,199 INFO hook.py line 109 2775932] Train: [7/100][500/800] Data 0.003 (0.004) Batch 0.127 (0.145) Remain 03:00:55 loss: -0.4365 Lr: 5.99568e-03 +[2025-02-22 11:02:21,243 INFO hook.py line 109 2775932] Train: [7/100][550/800] Data 0.004 (0.004) Batch 0.143 (0.145) Remain 03:00:17 loss: 0.1097 Lr: 5.99534e-03 +[2025-02-22 11:02:28,336 INFO hook.py line 109 2775932] Train: [7/100][600/800] Data 0.003 (0.004) Batch 0.122 (0.145) Remain 02:59:51 loss: 1.4352 Lr: 5.99499e-03 +[2025-02-22 11:02:35,648 INFO hook.py line 109 2775932] Train: [7/100][650/800] Data 0.003 (0.004) Batch 0.149 (0.145) Remain 02:59:53 loss: -0.2860 Lr: 5.99463e-03 +[2025-02-22 11:02:43,009 INFO hook.py line 109 2775932] Train: [7/100][700/800] Data 0.002 (0.004) Batch 0.133 (0.145) Remain 02:59:59 loss: -0.3259 Lr: 5.99425e-03 +[2025-02-22 11:02:50,365 INFO hook.py line 109 2775932] Train: [7/100][750/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 03:00:02 loss: 0.2124 Lr: 5.99386e-03 +[2025-02-22 11:02:57,398 INFO hook.py line 109 2775932] Train: [7/100][800/800] Data 0.001 (0.004) Batch 0.111 (0.145) Remain 02:59:34 loss: -0.2884 Lr: 5.99346e-03 +[2025-02-22 11:02:57,398 INFO misc.py line 135 2775932] Train result: loss: -0.1265 seg_loss: 0.4142 bias_l1_loss: 0.3453 bias_cosine_loss: -0.8860 +[2025-02-22 11:02:57,399 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:03:04,397 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.5332 +[2025-02-22 11:03:04,900 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2062 +[2025-02-22 11:03:04,960 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.0427 +[2025-02-22 11:03:05,027 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4024 +[2025-02-22 11:03:05,111 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3830 +[2025-02-22 11:03:05,171 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.4608 +[2025-02-22 11:03:05,454 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3149 +[2025-02-22 11:03:05,484 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4807 +[2025-02-22 11:03:05,614 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0464 +[2025-02-22 11:03:05,666 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.5206 +[2025-02-22 11:03:05,904 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1208 +[2025-02-22 11:03:05,998 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1128 +[2025-02-22 11:03:06,075 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5848 +[2025-02-22 11:03:06,169 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7898 +[2025-02-22 11:03:06,267 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6713 +[2025-02-22 11:03:06,345 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4797 +[2025-02-22 11:03:06,495 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2889 +[2025-02-22 11:03:06,591 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0294 +[2025-02-22 11:03:06,736 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0031 +[2025-02-22 11:03:06,803 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1378 +[2025-02-22 11:03:06,944 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4676 +[2025-02-22 11:03:07,115 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2361 +[2025-02-22 11:03:07,182 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0160 +[2025-02-22 11:03:07,237 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1652 +[2025-02-22 11:03:07,289 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1790 +[2025-02-22 11:03:07,345 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.2390 +[2025-02-22 11:03:07,489 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0359 +[2025-02-22 11:03:07,572 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.9158 +[2025-02-22 11:03:07,641 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4305 +[2025-02-22 11:03:07,710 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.2699 +[2025-02-22 11:03:08,361 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3255 +[2025-02-22 11:03:08,505 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7669 +[2025-02-22 11:03:08,550 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6574 +[2025-02-22 11:03:08,646 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1678 +[2025-02-22 11:03:08,683 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5351 +[2025-02-22 11:03:08,795 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1372 +[2025-02-22 11:03:08,854 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.2195 +[2025-02-22 11:03:08,954 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4811 +[2025-02-22 11:03:09,095 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3199 +[2025-02-22 11:03:09,262 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1270 +[2025-02-22 11:03:09,410 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5440 +[2025-02-22 11:03:09,459 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0001 +[2025-02-22 11:03:09,492 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5833 +[2025-02-22 11:03:09,728 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5754 +[2025-02-22 11:03:09,762 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2655 +[2025-02-22 11:03:09,797 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.1537 +[2025-02-22 11:03:09,887 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.1775 +[2025-02-22 11:03:10,000 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0133 +[2025-02-22 11:03:10,126 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2428 +[2025-02-22 11:03:10,215 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3702 +[2025-02-22 11:03:10,274 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0892 +[2025-02-22 11:03:10,379 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1594 +[2025-02-22 11:03:10,422 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6818 +[2025-02-22 11:03:10,529 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.7597 +[2025-02-22 11:03:10,599 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6572 +[2025-02-22 11:03:10,632 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7281 +[2025-02-22 11:03:10,741 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1352 +[2025-02-22 11:03:10,787 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1861 +[2025-02-22 11:03:10,971 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1506 +[2025-02-22 11:03:11,076 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1929 +[2025-02-22 11:03:11,147 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8115 +[2025-02-22 11:03:11,205 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3513 +[2025-02-22 11:03:11,353 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0431 +[2025-02-22 11:03:11,463 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5089 +[2025-02-22 11:03:11,536 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2136 +[2025-02-22 11:03:11,657 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1370 +[2025-02-22 11:03:11,815 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3328 +[2025-02-22 11:03:11,903 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5198 +[2025-02-22 11:03:11,953 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6565 +[2025-02-22 11:03:12,004 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1375 +[2025-02-22 11:03:12,156 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0007 +[2025-02-22 11:03:12,194 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4312 +[2025-02-22 11:03:12,258 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5356 +[2025-02-22 11:03:12,351 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.6836 +[2025-02-22 11:03:12,553 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3932 +[2025-02-22 11:03:12,629 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.4205 +[2025-02-22 11:03:12,796 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3697 +[2025-02-22 11:03:12,891 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5405 +[2025-02-22 11:03:26,668 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:03:26,668 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:03:26,668 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] cabinet : 0.1241 0.3047 0.5788 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] bed : 0.3434 0.6772 0.8345 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] chair : 0.6945 0.8615 0.9181 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] sofa : 0.3226 0.5820 0.8014 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] table : 0.2494 0.4302 0.5837 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] door : 0.1453 0.3218 0.4959 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] window : 0.1113 0.2353 0.4441 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] bookshelf : 0.0332 0.1659 0.5782 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] picture : 0.1994 0.3200 0.4610 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] counter : 0.0103 0.0610 0.3011 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] desk : 0.0371 0.1479 0.5870 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] curtain : 0.2233 0.3843 0.6650 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] refridgerator : 0.2766 0.4082 0.4474 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] shower curtain : 0.3467 0.5704 0.7752 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] toilet : 0.8536 0.9988 0.9988 +[2025-02-22 11:03:26,668 INFO evaluator.py line 547 2775932] sink : 0.2411 0.5725 0.8043 +[2025-02-22 11:03:26,669 INFO evaluator.py line 547 2775932] bathtub : 0.4569 0.6667 0.8192 +[2025-02-22 11:03:26,669 INFO evaluator.py line 547 2775932] otherfurniture : 0.2118 0.3828 0.5992 +[2025-02-22 11:03:26,669 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:03:26,669 INFO evaluator.py line 554 2775932] average : 0.2712 0.4495 0.6496 +[2025-02-22 11:03:26,669 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:03:26,669 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:03:26,704 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4495 +[2025-02-22 11:03:26,706 INFO misc.py line 164 2775932] Currently Best AP50: 0.4495 +[2025-02-22 11:03:26,706 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:03:35,334 INFO hook.py line 109 2775932] Train: [8/100][50/800] Data 0.004 (0.003) Batch 0.146 (0.141) Remain 02:54:52 loss: 0.1058 Lr: 5.99304e-03 +[2025-02-22 11:03:42,822 INFO hook.py line 109 2775932] Train: [8/100][100/800] Data 0.003 (0.006) Batch 0.149 (0.146) Remain 03:00:15 loss: -0.3310 Lr: 5.99261e-03 +[2025-02-22 11:03:49,783 INFO hook.py line 109 2775932] Train: [8/100][150/800] Data 0.003 (0.005) Batch 0.159 (0.143) Remain 02:57:27 loss: -0.4787 Lr: 5.99217e-03 +[2025-02-22 11:03:56,896 INFO hook.py line 109 2775932] Train: [8/100][200/800] Data 0.002 (0.004) Batch 0.166 (0.143) Remain 02:56:59 loss: 0.3690 Lr: 5.99172e-03 +[2025-02-22 11:04:04,218 INFO hook.py line 109 2775932] Train: [8/100][250/800] Data 0.002 (0.004) Batch 0.158 (0.144) Remain 02:57:41 loss: -0.1784 Lr: 5.99125e-03 +[2025-02-22 11:04:11,906 INFO hook.py line 109 2775932] Train: [8/100][300/800] Data 0.003 (0.004) Batch 0.130 (0.145) Remain 02:59:39 loss: -0.0899 Lr: 5.99077e-03 +[2025-02-22 11:04:19,009 INFO hook.py line 109 2775932] Train: [8/100][350/800] Data 0.003 (0.004) Batch 0.146 (0.145) Remain 02:58:55 loss: -0.1023 Lr: 5.99028e-03 +[2025-02-22 11:04:26,395 INFO hook.py line 109 2775932] Train: [8/100][400/800] Data 0.005 (0.004) Batch 0.146 (0.145) Remain 02:59:13 loss: -0.2149 Lr: 5.98977e-03 +[2025-02-22 11:04:33,713 INFO hook.py line 109 2775932] Train: [8/100][450/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 02:59:15 loss: -0.1630 Lr: 5.98926e-03 +[2025-02-22 11:04:41,134 INFO hook.py line 109 2775932] Train: [8/100][500/800] Data 0.003 (0.004) Batch 0.142 (0.146) Remain 02:59:29 loss: -0.2423 Lr: 5.98873e-03 +[2025-02-22 11:04:48,406 INFO hook.py line 109 2775932] Train: [8/100][550/800] Data 0.003 (0.004) Batch 0.136 (0.146) Remain 02:59:20 loss: -0.3424 Lr: 5.98818e-03 +[2025-02-22 11:04:55,867 INFO hook.py line 109 2775932] Train: [8/100][600/800] Data 0.002 (0.004) Batch 0.144 (0.146) Remain 02:59:35 loss: 0.1276 Lr: 5.98763e-03 +[2025-02-22 11:05:03,150 INFO hook.py line 109 2775932] Train: [8/100][650/800] Data 0.003 (0.004) Batch 0.169 (0.146) Remain 02:59:25 loss: -0.2554 Lr: 5.98706e-03 +[2025-02-22 11:05:10,396 INFO hook.py line 109 2775932] Train: [8/100][700/800] Data 0.002 (0.003) Batch 0.137 (0.146) Remain 02:59:12 loss: -0.0164 Lr: 5.98648e-03 +[2025-02-22 11:05:17,694 INFO hook.py line 109 2775932] Train: [8/100][750/800] Data 0.003 (0.003) Batch 0.145 (0.146) Remain 02:59:05 loss: -0.2457 Lr: 5.98588e-03 +[2025-02-22 11:05:24,696 INFO hook.py line 109 2775932] Train: [8/100][800/800] Data 0.002 (0.003) Batch 0.118 (0.146) Remain 02:58:31 loss: -0.2883 Lr: 5.98527e-03 +[2025-02-22 11:05:24,697 INFO misc.py line 135 2775932] Train result: loss: -0.1678 seg_loss: 0.3901 bias_l1_loss: 0.3336 bias_cosine_loss: -0.8915 +[2025-02-22 11:05:24,698 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:05:32,368 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6234 +[2025-02-22 11:05:32,565 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.1764 +[2025-02-22 11:05:32,626 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.1649 +[2025-02-22 11:05:32,701 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4733 +[2025-02-22 11:05:32,766 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.2940 +[2025-02-22 11:05:32,821 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9698 +[2025-02-22 11:05:33,100 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3774 +[2025-02-22 11:05:33,131 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3721 +[2025-02-22 11:05:33,265 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0229 +[2025-02-22 11:05:33,322 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.4628 +[2025-02-22 11:05:33,562 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0206 +[2025-02-22 11:05:33,668 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0770 +[2025-02-22 11:05:33,753 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.6293 +[2025-02-22 11:05:33,840 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.6102 +[2025-02-22 11:05:33,928 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5995 +[2025-02-22 11:05:33,995 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4987 +[2025-02-22 11:05:34,141 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.1497 +[2025-02-22 11:05:34,231 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1506 +[2025-02-22 11:05:34,409 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2740 +[2025-02-22 11:05:34,492 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0636 +[2025-02-22 11:05:34,659 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4809 +[2025-02-22 11:05:34,864 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1961 +[2025-02-22 11:05:34,946 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0994 +[2025-02-22 11:05:35,019 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0253 +[2025-02-22 11:05:35,102 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2177 +[2025-02-22 11:05:35,164 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3215 +[2025-02-22 11:05:35,329 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2427 +[2025-02-22 11:05:35,424 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7375 +[2025-02-22 11:05:35,497 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5270 +[2025-02-22 11:05:35,589 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.2398 +[2025-02-22 11:05:36,402 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3127 +[2025-02-22 11:05:36,549 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2938 +[2025-02-22 11:05:36,589 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6615 +[2025-02-22 11:05:36,701 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2100 +[2025-02-22 11:05:36,743 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5467 +[2025-02-22 11:05:36,869 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1805 +[2025-02-22 11:05:36,939 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.1886 +[2025-02-22 11:05:37,079 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4829 +[2025-02-22 11:05:37,240 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6145 +[2025-02-22 11:05:37,457 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8912 +[2025-02-22 11:05:37,616 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3710 +[2025-02-22 11:05:37,667 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1087 +[2025-02-22 11:05:37,707 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5701 +[2025-02-22 11:05:38,010 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.2620 +[2025-02-22 11:05:38,056 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.0764 +[2025-02-22 11:05:38,100 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4336 +[2025-02-22 11:05:38,193 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.2332 +[2025-02-22 11:05:38,304 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2161 +[2025-02-22 11:05:38,414 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0233 +[2025-02-22 11:05:38,553 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3825 +[2025-02-22 11:05:38,622 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0495 +[2025-02-22 11:05:38,780 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.0332 +[2025-02-22 11:05:38,831 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6367 +[2025-02-22 11:05:38,932 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.3829 +[2025-02-22 11:05:39,047 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7306 +[2025-02-22 11:05:39,112 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7095 +[2025-02-22 11:05:39,236 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.2811 +[2025-02-22 11:05:39,273 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1997 +[2025-02-22 11:05:39,522 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2559 +[2025-02-22 11:05:39,629 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0405 +[2025-02-22 11:05:39,703 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6793 +[2025-02-22 11:05:39,766 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4357 +[2025-02-22 11:05:39,938 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0105 +[2025-02-22 11:05:40,048 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5811 +[2025-02-22 11:05:40,125 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.8765 +[2025-02-22 11:05:40,243 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1470 +[2025-02-22 11:05:40,402 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.1138 +[2025-02-22 11:05:40,494 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.6886 +[2025-02-22 11:05:40,552 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6522 +[2025-02-22 11:05:40,603 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0858 +[2025-02-22 11:05:40,755 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0157 +[2025-02-22 11:05:40,794 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3401 +[2025-02-22 11:05:40,844 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5362 +[2025-02-22 11:05:40,941 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.6200 +[2025-02-22 11:05:41,132 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4910 +[2025-02-22 11:05:41,205 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1751 +[2025-02-22 11:05:41,365 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.2003 +[2025-02-22 11:05:41,443 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6706 +[2025-02-22 11:05:53,740 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:05:53,740 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:05:53,740 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] cabinet : 0.1818 0.4040 0.6593 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] bed : 0.3028 0.6197 0.7557 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] chair : 0.6784 0.8446 0.8901 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] sofa : 0.2940 0.5605 0.8259 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] table : 0.3640 0.5693 0.6676 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] door : 0.1466 0.3279 0.5030 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] window : 0.0977 0.2482 0.5392 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] bookshelf : 0.1333 0.3984 0.7308 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] picture : 0.2255 0.3933 0.5187 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] counter : 0.0330 0.1291 0.4904 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] desk : 0.0553 0.1771 0.5417 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] curtain : 0.1886 0.2999 0.4528 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] refridgerator : 0.2598 0.3939 0.5803 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] shower curtain : 0.3430 0.5757 0.7961 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] toilet : 0.7833 0.9655 0.9828 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] sink : 0.1601 0.4502 0.7365 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] bathtub : 0.5867 0.7742 0.8710 +[2025-02-22 11:05:53,740 INFO evaluator.py line 547 2775932] otherfurniture : 0.1894 0.3507 0.4976 +[2025-02-22 11:05:53,740 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:05:53,740 INFO evaluator.py line 554 2775932] average : 0.2791 0.4712 0.6689 +[2025-02-22 11:05:53,740 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:05:53,740 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:05:53,796 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4712 +[2025-02-22 11:05:53,796 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:05:53,798 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:06:02,813 INFO hook.py line 109 2775932] Train: [9/100][50/800] Data 0.003 (0.007) Batch 0.137 (0.151) Remain 03:04:43 loss: -0.3840 Lr: 5.98465e-03 +[2025-02-22 11:06:10,119 INFO hook.py line 109 2775932] Train: [9/100][100/800] Data 0.003 (0.005) Batch 0.151 (0.148) Remain 03:01:42 loss: -0.0498 Lr: 5.98402e-03 +[2025-02-22 11:06:17,387 INFO hook.py line 109 2775932] Train: [9/100][150/800] Data 0.002 (0.004) Batch 0.159 (0.147) Remain 03:00:20 loss: -0.2104 Lr: 5.98338e-03 +[2025-02-22 11:06:24,523 INFO hook.py line 109 2775932] Train: [9/100][200/800] Data 0.003 (0.004) Batch 0.155 (0.146) Remain 02:58:47 loss: -0.2418 Lr: 5.98272e-03 +[2025-02-22 11:06:31,652 INFO hook.py line 109 2775932] Train: [9/100][250/800] Data 0.002 (0.004) Batch 0.139 (0.145) Remain 02:57:47 loss: -0.0387 Lr: 5.98205e-03 +[2025-02-22 11:06:39,092 INFO hook.py line 109 2775932] Train: [9/100][300/800] Data 0.004 (0.004) Batch 0.131 (0.146) Remain 02:58:21 loss: -0.2047 Lr: 5.98136e-03 +[2025-02-22 11:06:46,215 INFO hook.py line 109 2775932] Train: [9/100][350/800] Data 0.003 (0.004) Batch 0.152 (0.145) Remain 02:57:37 loss: -0.3423 Lr: 5.98067e-03 +[2025-02-22 11:06:53,421 INFO hook.py line 109 2775932] Train: [9/100][400/800] Data 0.004 (0.004) Batch 0.148 (0.145) Remain 02:57:17 loss: -0.2929 Lr: 5.97996e-03 +[2025-02-22 11:07:00,815 INFO hook.py line 109 2775932] Train: [9/100][450/800] Data 0.002 (0.004) Batch 0.138 (0.146) Remain 02:57:30 loss: -0.3310 Lr: 5.97924e-03 +[2025-02-22 11:07:07,958 INFO hook.py line 109 2775932] Train: [9/100][500/800] Data 0.002 (0.004) Batch 0.123 (0.145) Remain 02:57:03 loss: -0.2823 Lr: 5.97852e-03 +[2025-02-22 11:07:15,354 INFO hook.py line 109 2775932] Train: [9/100][550/800] Data 0.003 (0.004) Batch 0.158 (0.146) Remain 02:57:13 loss: -0.3559 Lr: 5.97777e-03 +[2025-02-22 11:07:22,859 INFO hook.py line 109 2775932] Train: [9/100][600/800] Data 0.002 (0.004) Batch 0.154 (0.146) Remain 02:57:33 loss: -0.2510 Lr: 5.97701e-03 +[2025-02-22 11:07:30,294 INFO hook.py line 109 2775932] Train: [9/100][650/800] Data 0.002 (0.004) Batch 0.149 (0.146) Remain 02:57:41 loss: 0.0423 Lr: 5.97624e-03 +[2025-02-22 11:07:37,364 INFO hook.py line 109 2775932] Train: [9/100][700/800] Data 0.002 (0.004) Batch 0.136 (0.146) Remain 02:57:09 loss: -0.2858 Lr: 5.97545e-03 +[2025-02-22 11:07:44,615 INFO hook.py line 109 2775932] Train: [9/100][750/800] Data 0.002 (0.004) Batch 0.125 (0.146) Remain 02:56:58 loss: 0.2347 Lr: 5.97465e-03 +[2025-02-22 11:07:51,518 INFO hook.py line 109 2775932] Train: [9/100][800/800] Data 0.001 (0.004) Batch 0.106 (0.145) Remain 02:56:16 loss: -0.0330 Lr: 5.97384e-03 +[2025-02-22 11:07:51,519 INFO misc.py line 135 2775932] Train result: loss: -0.1785 seg_loss: 0.3875 bias_l1_loss: 0.3286 bias_cosine_loss: -0.8946 +[2025-02-22 11:07:51,519 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:07:58,629 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6300 +[2025-02-22 11:07:58,949 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.1352 +[2025-02-22 11:07:59,014 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2899 +[2025-02-22 11:07:59,087 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4303 +[2025-02-22 11:07:59,149 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4102 +[2025-02-22 11:07:59,526 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8245 +[2025-02-22 11:07:59,809 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2213 +[2025-02-22 11:07:59,840 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4882 +[2025-02-22 11:07:59,999 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1370 +[2025-02-22 11:08:00,057 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2793 +[2025-02-22 11:08:00,287 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3536 +[2025-02-22 11:08:00,392 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0467 +[2025-02-22 11:08:00,464 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.9879 +[2025-02-22 11:08:00,552 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9300 +[2025-02-22 11:08:00,628 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7296 +[2025-02-22 11:08:00,693 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3396 +[2025-02-22 11:08:00,833 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2792 +[2025-02-22 11:08:00,928 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1009 +[2025-02-22 11:08:01,067 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.3236 +[2025-02-22 11:08:01,136 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0293 +[2025-02-22 11:08:01,287 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6282 +[2025-02-22 11:08:01,458 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.6511 +[2025-02-22 11:08:01,544 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0697 +[2025-02-22 11:08:01,617 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1115 +[2025-02-22 11:08:01,701 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.2483 +[2025-02-22 11:08:01,756 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3323 +[2025-02-22 11:08:01,913 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3374 +[2025-02-22 11:08:02,026 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0641 +[2025-02-22 11:08:02,105 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5218 +[2025-02-22 11:08:02,175 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4469 +[2025-02-22 11:08:02,816 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3495 +[2025-02-22 11:08:02,931 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4716 +[2025-02-22 11:08:02,977 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6403 +[2025-02-22 11:08:03,075 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2162 +[2025-02-22 11:08:03,115 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6802 +[2025-02-22 11:08:03,247 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8868 +[2025-02-22 11:08:03,339 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5817 +[2025-02-22 11:08:03,555 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5353 +[2025-02-22 11:08:03,690 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5693 +[2025-02-22 11:08:03,879 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7983 +[2025-02-22 11:08:04,042 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3254 +[2025-02-22 11:08:04,096 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1833 +[2025-02-22 11:08:04,137 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5381 +[2025-02-22 11:08:04,389 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5578 +[2025-02-22 11:08:04,443 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2900 +[2025-02-22 11:08:04,488 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2910 +[2025-02-22 11:08:04,586 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5359 +[2025-02-22 11:08:04,697 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0524 +[2025-02-22 11:08:04,808 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0876 +[2025-02-22 11:08:04,889 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.6100 +[2025-02-22 11:08:04,957 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0135 +[2025-02-22 11:08:05,100 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1787 +[2025-02-22 11:08:05,155 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6773 +[2025-02-22 11:08:05,279 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.4635 +[2025-02-22 11:08:05,366 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7247 +[2025-02-22 11:08:05,412 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7577 +[2025-02-22 11:08:05,539 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0774 +[2025-02-22 11:08:05,582 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0964 +[2025-02-22 11:08:05,808 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0055 +[2025-02-22 11:08:05,898 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1702 +[2025-02-22 11:08:05,975 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.0603 +[2025-02-22 11:08:06,024 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4317 +[2025-02-22 11:08:06,164 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1289 +[2025-02-22 11:08:06,256 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5151 +[2025-02-22 11:08:06,336 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3001 +[2025-02-22 11:08:06,470 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1867 +[2025-02-22 11:08:06,612 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5060 +[2025-02-22 11:08:06,700 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.4404 +[2025-02-22 11:08:06,750 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6809 +[2025-02-22 11:08:06,798 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.3507 +[2025-02-22 11:08:06,928 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1962 +[2025-02-22 11:08:06,963 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5497 +[2025-02-22 11:08:07,012 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5281 +[2025-02-22 11:08:07,097 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6062 +[2025-02-22 11:08:07,290 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5491 +[2025-02-22 11:08:07,365 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1408 +[2025-02-22 11:08:07,531 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4231 +[2025-02-22 11:08:07,607 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6010 +[2025-02-22 11:08:18,978 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:08:18,978 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:08:18,978 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] cabinet : 0.1067 0.2603 0.5199 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] bed : 0.2860 0.6154 0.7330 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] chair : 0.6753 0.8469 0.8986 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] sofa : 0.3262 0.6025 0.7989 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] table : 0.2967 0.5357 0.6735 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] door : 0.2148 0.3988 0.5396 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] window : 0.0632 0.1605 0.3190 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] bookshelf : 0.1100 0.3737 0.7170 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] picture : 0.1008 0.1818 0.2710 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] counter : 0.0005 0.0033 0.2092 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] desk : 0.0507 0.1833 0.6042 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] curtain : 0.2281 0.4436 0.6279 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] refridgerator : 0.2232 0.3810 0.4698 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] shower curtain : 0.3481 0.5398 0.6947 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] toilet : 0.8040 0.9655 0.9828 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] sink : 0.2133 0.4083 0.7829 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] bathtub : 0.5743 0.7172 0.8528 +[2025-02-22 11:08:18,978 INFO evaluator.py line 547 2775932] otherfurniture : 0.2385 0.4200 0.5568 +[2025-02-22 11:08:18,978 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:08:18,978 INFO evaluator.py line 554 2775932] average : 0.2700 0.4465 0.6251 +[2025-02-22 11:08:18,978 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:08:18,978 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:08:19,016 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:08:19,017 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:08:27,631 INFO hook.py line 109 2775932] Train: [10/100][50/800] Data 0.002 (0.006) Batch 0.131 (0.144) Remain 02:55:06 loss: -0.0069 Lr: 5.97302e-03 +[2025-02-22 11:08:34,853 INFO hook.py line 109 2775932] Train: [10/100][100/800] Data 0.002 (0.005) Batch 0.141 (0.144) Remain 02:55:00 loss: 0.0770 Lr: 5.97218e-03 +[2025-02-22 11:08:42,259 INFO hook.py line 109 2775932] Train: [10/100][150/800] Data 0.003 (0.006) Batch 0.137 (0.146) Remain 02:56:23 loss: -0.4736 Lr: 5.97134e-03 +[2025-02-22 11:08:49,462 INFO hook.py line 109 2775932] Train: [10/100][200/800] Data 0.003 (0.005) Batch 0.140 (0.145) Remain 02:55:46 loss: 0.0542 Lr: 5.97047e-03 +[2025-02-22 11:08:56,630 INFO hook.py line 109 2775932] Train: [10/100][250/800] Data 0.004 (0.004) Batch 0.225 (0.145) Remain 02:55:11 loss: -0.3073 Lr: 5.96960e-03 +[2025-02-22 11:09:04,079 INFO hook.py line 109 2775932] Train: [10/100][300/800] Data 0.003 (0.004) Batch 0.134 (0.146) Remain 02:55:54 loss: -0.1952 Lr: 5.96871e-03 +[2025-02-22 11:09:11,059 INFO hook.py line 109 2775932] Train: [10/100][350/800] Data 0.003 (0.004) Batch 0.145 (0.145) Remain 02:54:44 loss: -0.2143 Lr: 5.96781e-03 +[2025-02-22 11:09:18,272 INFO hook.py line 109 2775932] Train: [10/100][400/800] Data 0.004 (0.004) Batch 0.138 (0.145) Remain 02:54:33 loss: -0.1059 Lr: 5.96690e-03 +[2025-02-22 11:09:25,645 INFO hook.py line 109 2775932] Train: [10/100][450/800] Data 0.003 (0.004) Batch 0.136 (0.145) Remain 02:54:48 loss: -0.0160 Lr: 5.96598e-03 +[2025-02-22 11:09:32,865 INFO hook.py line 109 2775932] Train: [10/100][500/800] Data 0.003 (0.004) Batch 0.147 (0.145) Remain 02:54:37 loss: -0.2533 Lr: 5.96504e-03 +[2025-02-22 11:09:40,280 INFO hook.py line 109 2775932] Train: [10/100][550/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 02:54:52 loss: 0.0109 Lr: 5.96409e-03 +[2025-02-22 11:09:47,770 INFO hook.py line 109 2775932] Train: [10/100][600/800] Data 0.003 (0.004) Batch 0.148 (0.146) Remain 02:55:12 loss: -0.1533 Lr: 5.96313e-03 +[2025-02-22 11:09:55,001 INFO hook.py line 109 2775932] Train: [10/100][650/800] Data 0.003 (0.004) Batch 0.141 (0.146) Remain 02:54:59 loss: -0.1356 Lr: 5.96215e-03 +[2025-02-22 11:10:02,465 INFO hook.py line 109 2775932] Train: [10/100][700/800] Data 0.003 (0.004) Batch 0.143 (0.146) Remain 02:55:11 loss: -0.4837 Lr: 5.96116e-03 +[2025-02-22 11:10:09,669 INFO hook.py line 109 2775932] Train: [10/100][750/800] Data 0.003 (0.004) Batch 0.132 (0.146) Remain 02:54:56 loss: -0.2204 Lr: 5.96016e-03 +[2025-02-22 11:10:16,518 INFO hook.py line 109 2775932] Train: [10/100][800/800] Data 0.002 (0.004) Batch 0.120 (0.145) Remain 02:54:09 loss: -0.2245 Lr: 5.95915e-03 +[2025-02-22 11:10:16,519 INFO misc.py line 135 2775932] Train result: loss: -0.1860 seg_loss: 0.3789 bias_l1_loss: 0.3288 bias_cosine_loss: -0.8936 +[2025-02-22 11:10:16,519 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:10:23,689 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6723 +[2025-02-22 11:10:23,923 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1077 +[2025-02-22 11:10:24,171 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3079 +[2025-02-22 11:10:24,272 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5216 +[2025-02-22 11:10:24,337 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4542 +[2025-02-22 11:10:24,447 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7755 +[2025-02-22 11:10:24,737 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2916 +[2025-02-22 11:10:24,768 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4333 +[2025-02-22 11:10:24,914 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.4769 +[2025-02-22 11:10:24,967 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.4945 +[2025-02-22 11:10:25,216 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1395 +[2025-02-22 11:10:25,317 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1138 +[2025-02-22 11:10:25,391 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.0610 +[2025-02-22 11:10:25,481 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.5777 +[2025-02-22 11:10:25,562 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3349 +[2025-02-22 11:10:25,615 INFO evaluator.py line 595 2775932] Test: [16/78] Loss 1.5345 +[2025-02-22 11:10:25,761 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.1613 +[2025-02-22 11:10:25,856 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1554 +[2025-02-22 11:10:26,005 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2055 +[2025-02-22 11:10:26,077 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.4729 +[2025-02-22 11:10:26,226 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5825 +[2025-02-22 11:10:26,383 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.7766 +[2025-02-22 11:10:26,452 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2568 +[2025-02-22 11:10:26,513 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2092 +[2025-02-22 11:10:26,571 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0140 +[2025-02-22 11:10:26,640 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4683 +[2025-02-22 11:10:26,788 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.8817 +[2025-02-22 11:10:26,897 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0292 +[2025-02-22 11:10:26,963 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5076 +[2025-02-22 11:10:27,031 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4998 +[2025-02-22 11:10:27,741 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3916 +[2025-02-22 11:10:27,870 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.6491 +[2025-02-22 11:10:27,910 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6171 +[2025-02-22 11:10:27,996 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1947 +[2025-02-22 11:10:28,035 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5477 +[2025-02-22 11:10:28,171 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2060 +[2025-02-22 11:10:28,251 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3664 +[2025-02-22 11:10:28,398 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4591 +[2025-02-22 11:10:28,550 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7126 +[2025-02-22 11:10:28,783 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.3319 +[2025-02-22 11:10:28,961 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3954 +[2025-02-22 11:10:29,011 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1318 +[2025-02-22 11:10:29,056 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6582 +[2025-02-22 11:10:29,321 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5216 +[2025-02-22 11:10:29,366 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.1510 +[2025-02-22 11:10:29,410 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4227 +[2025-02-22 11:10:29,535 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4715 +[2025-02-22 11:10:29,664 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1437 +[2025-02-22 11:10:29,763 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0440 +[2025-02-22 11:10:29,860 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2787 +[2025-02-22 11:10:29,939 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.2710 +[2025-02-22 11:10:30,080 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0834 +[2025-02-22 11:10:30,123 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5700 +[2025-02-22 11:10:30,218 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.5378 +[2025-02-22 11:10:30,307 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7145 +[2025-02-22 11:10:30,351 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6623 +[2025-02-22 11:10:30,477 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1179 +[2025-02-22 11:10:30,527 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3848 +[2025-02-22 11:10:30,743 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1740 +[2025-02-22 11:10:30,846 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0961 +[2025-02-22 11:10:30,921 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.3100 +[2025-02-22 11:10:30,979 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3814 +[2025-02-22 11:10:31,141 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2303 +[2025-02-22 11:10:31,258 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5369 +[2025-02-22 11:10:31,333 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4134 +[2025-02-22 11:10:31,466 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1159 +[2025-02-22 11:10:31,641 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2825 +[2025-02-22 11:10:31,722 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.4526 +[2025-02-22 11:10:31,771 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6963 +[2025-02-22 11:10:31,821 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.3950 +[2025-02-22 11:10:31,950 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0939 +[2025-02-22 11:10:31,986 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3871 +[2025-02-22 11:10:32,031 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6715 +[2025-02-22 11:10:32,124 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.5052 +[2025-02-22 11:10:32,323 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4446 +[2025-02-22 11:10:32,398 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2301 +[2025-02-22 11:10:32,534 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3908 +[2025-02-22 11:10:32,608 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3339 +[2025-02-22 11:10:45,143 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:10:45,143 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:10:45,143 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] cabinet : 0.1271 0.3148 0.5688 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] bed : 0.2810 0.6015 0.8712 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] chair : 0.6185 0.7731 0.8423 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] sofa : 0.2784 0.4823 0.7198 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] table : 0.3380 0.5699 0.7045 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] door : 0.1717 0.3423 0.4838 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] window : 0.1287 0.2876 0.5133 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] bookshelf : 0.1987 0.4825 0.7498 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] picture : 0.1185 0.2231 0.3437 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] counter : 0.0264 0.0940 0.4606 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] desk : 0.0580 0.1785 0.5100 +[2025-02-22 11:10:45,143 INFO evaluator.py line 547 2775932] curtain : 0.1242 0.2735 0.5325 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] refridgerator : 0.0000 0.0000 0.0000 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] shower curtain : 0.4206 0.6665 0.7228 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] toilet : 0.7729 0.9960 0.9972 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] sink : 0.2058 0.4493 0.7538 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] bathtub : 0.6489 0.7742 0.8710 +[2025-02-22 11:10:45,144 INFO evaluator.py line 547 2775932] otherfurniture : 0.2494 0.4067 0.5535 +[2025-02-22 11:10:45,144 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:10:45,144 INFO evaluator.py line 554 2775932] average : 0.2648 0.4398 0.6221 +[2025-02-22 11:10:45,144 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:10:45,144 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:10:45,182 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:10:45,183 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:10:54,393 INFO hook.py line 109 2775932] Train: [11/100][50/800] Data 0.005 (0.003) Batch 0.136 (0.148) Remain 02:57:31 loss: -0.4091 Lr: 5.95812e-03 +[2025-02-22 11:11:01,639 INFO hook.py line 109 2775932] Train: [11/100][100/800] Data 0.004 (0.003) Batch 0.147 (0.146) Remain 02:55:28 loss: -0.2352 Lr: 5.95708e-03 +[2025-02-22 11:11:08,937 INFO hook.py line 109 2775932] Train: [11/100][150/800] Data 0.002 (0.003) Batch 0.147 (0.146) Remain 02:55:09 loss: -0.3875 Lr: 5.95603e-03 +[2025-02-22 11:11:16,198 INFO hook.py line 109 2775932] Train: [11/100][200/800] Data 0.003 (0.003) Batch 0.134 (0.146) Remain 02:54:43 loss: -0.3338 Lr: 5.95497e-03 +[2025-02-22 11:11:23,280 INFO hook.py line 109 2775932] Train: [11/100][250/800] Data 0.003 (0.003) Batch 0.167 (0.145) Remain 02:53:32 loss: -0.2043 Lr: 5.95389e-03 +[2025-02-22 11:11:30,422 INFO hook.py line 109 2775932] Train: [11/100][300/800] Data 0.002 (0.003) Batch 0.166 (0.145) Remain 02:52:57 loss: -0.3426 Lr: 5.95280e-03 +[2025-02-22 11:11:37,571 INFO hook.py line 109 2775932] Train: [11/100][350/800] Data 0.004 (0.004) Batch 0.138 (0.144) Remain 02:52:32 loss: -0.0686 Lr: 5.95170e-03 +[2025-02-22 11:11:44,776 INFO hook.py line 109 2775932] Train: [11/100][400/800] Data 0.002 (0.003) Batch 0.157 (0.144) Remain 02:52:21 loss: -0.2264 Lr: 5.95059e-03 +[2025-02-22 11:11:51,653 INFO hook.py line 109 2775932] Train: [11/100][450/800] Data 0.003 (0.003) Batch 0.161 (0.144) Remain 02:51:18 loss: -0.4205 Lr: 5.94946e-03 +[2025-02-22 11:11:58,737 INFO hook.py line 109 2775932] Train: [11/100][500/800] Data 0.004 (0.003) Batch 0.136 (0.143) Remain 02:50:57 loss: -0.3928 Lr: 5.94832e-03 +[2025-02-22 11:12:06,064 INFO hook.py line 109 2775932] Train: [11/100][550/800] Data 0.002 (0.003) Batch 0.141 (0.144) Remain 02:51:10 loss: -0.0115 Lr: 5.94717e-03 +[2025-02-22 11:12:13,116 INFO hook.py line 109 2775932] Train: [11/100][600/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 02:50:47 loss: -0.0048 Lr: 5.94600e-03 +[2025-02-22 11:12:20,609 INFO hook.py line 109 2775932] Train: [11/100][650/800] Data 0.003 (0.003) Batch 0.141 (0.144) Remain 02:51:14 loss: -0.4995 Lr: 5.94483e-03 +[2025-02-22 11:12:27,957 INFO hook.py line 109 2775932] Train: [11/100][700/800] Data 0.004 (0.003) Batch 0.133 (0.144) Remain 02:51:22 loss: -0.2753 Lr: 5.94364e-03 +[2025-02-22 11:12:35,247 INFO hook.py line 109 2775932] Train: [11/100][750/800] Data 0.003 (0.003) Batch 0.136 (0.144) Remain 02:51:23 loss: -0.4924 Lr: 5.94243e-03 +[2025-02-22 11:12:42,250 INFO hook.py line 109 2775932] Train: [11/100][800/800] Data 0.002 (0.003) Batch 0.121 (0.144) Remain 02:50:56 loss: -0.5410 Lr: 5.94122e-03 +[2025-02-22 11:12:42,250 INFO misc.py line 135 2775932] Train result: loss: -0.2231 seg_loss: 0.3579 bias_l1_loss: 0.3172 bias_cosine_loss: -0.8982 +[2025-02-22 11:12:42,251 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:12:49,879 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.4517 +[2025-02-22 11:12:50,077 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.2178 +[2025-02-22 11:12:50,141 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2011 +[2025-02-22 11:12:50,211 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5092 +[2025-02-22 11:12:50,279 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.2580 +[2025-02-22 11:12:50,340 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5778 +[2025-02-22 11:12:50,630 INFO evaluator.py line 595 2775932] Test: [7/78] Loss 0.0499 +[2025-02-22 11:12:50,659 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3680 +[2025-02-22 11:12:50,807 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0924 +[2025-02-22 11:12:50,868 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.5307 +[2025-02-22 11:12:51,114 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0540 +[2025-02-22 11:12:51,225 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.2197 +[2025-02-22 11:12:51,290 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.4220 +[2025-02-22 11:12:51,388 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7709 +[2025-02-22 11:12:51,469 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3898 +[2025-02-22 11:12:51,545 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4210 +[2025-02-22 11:12:51,693 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.2908 +[2025-02-22 11:12:51,792 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1384 +[2025-02-22 11:12:51,951 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4984 +[2025-02-22 11:12:52,040 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2685 +[2025-02-22 11:12:52,192 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5083 +[2025-02-22 11:12:52,358 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.9319 +[2025-02-22 11:12:52,437 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0026 +[2025-02-22 11:12:52,499 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1856 +[2025-02-22 11:12:52,564 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0874 +[2025-02-22 11:12:52,619 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3377 +[2025-02-22 11:12:52,758 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.6882 +[2025-02-22 11:12:52,844 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7707 +[2025-02-22 11:12:52,910 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5529 +[2025-02-22 11:12:52,987 INFO evaluator.py line 595 2775932] Test: [30/78] Loss 0.5659 +[2025-02-22 11:12:53,663 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.1570 +[2025-02-22 11:12:53,765 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3803 +[2025-02-22 11:12:53,799 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5842 +[2025-02-22 11:12:53,896 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2394 +[2025-02-22 11:12:53,931 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5349 +[2025-02-22 11:12:54,037 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9809 +[2025-02-22 11:12:54,118 INFO evaluator.py line 595 2775932] Test: [37/78] Loss 0.8874 +[2025-02-22 11:12:54,230 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5211 +[2025-02-22 11:12:54,372 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 1.6368 +[2025-02-22 11:12:54,604 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9672 +[2025-02-22 11:12:54,769 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4116 +[2025-02-22 11:12:54,820 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.2980 +[2025-02-22 11:12:54,868 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4029 +[2025-02-22 11:12:55,086 INFO evaluator.py line 595 2775932] Test: [44/78] Loss 0.3158 +[2025-02-22 11:12:55,129 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.4178 +[2025-02-22 11:12:55,172 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.0183 +[2025-02-22 11:12:55,276 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.6190 +[2025-02-22 11:12:55,396 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.1262 +[2025-02-22 11:12:55,492 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0045 +[2025-02-22 11:12:55,563 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.6883 +[2025-02-22 11:12:55,622 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.5326 +[2025-02-22 11:12:55,732 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1504 +[2025-02-22 11:12:55,765 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5259 +[2025-02-22 11:12:55,858 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3551 +[2025-02-22 11:12:55,940 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6555 +[2025-02-22 11:12:55,991 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.4381 +[2025-02-22 11:12:56,105 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0820 +[2025-02-22 11:12:56,136 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2427 +[2025-02-22 11:12:56,332 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0717 +[2025-02-22 11:12:56,448 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1479 +[2025-02-22 11:12:56,505 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6551 +[2025-02-22 11:12:56,552 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3128 +[2025-02-22 11:12:56,705 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1255 +[2025-02-22 11:12:56,796 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 1.1579 +[2025-02-22 11:12:56,863 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3281 +[2025-02-22 11:12:56,976 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.2440 +[2025-02-22 11:12:57,148 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3509 +[2025-02-22 11:12:57,228 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.7556 +[2025-02-22 11:12:57,277 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6634 +[2025-02-22 11:12:57,330 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.5830 +[2025-02-22 11:12:57,478 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.9910 +[2025-02-22 11:12:57,542 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.1789 +[2025-02-22 11:12:57,602 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5113 +[2025-02-22 11:12:57,688 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3252 +[2025-02-22 11:12:57,889 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4533 +[2025-02-22 11:12:57,965 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.3950 +[2025-02-22 11:12:58,131 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.0922 +[2025-02-22 11:12:58,216 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.1411 +[2025-02-22 11:13:11,946 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:13:11,947 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:13:11,947 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] cabinet : 0.1903 0.4029 0.6343 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] bed : 0.3065 0.6673 0.8363 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] chair : 0.6700 0.8530 0.9146 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] sofa : 0.3134 0.4860 0.8027 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] table : 0.3212 0.5333 0.6642 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] door : 0.1319 0.2599 0.3968 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] window : 0.0625 0.1450 0.3771 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] bookshelf : 0.1408 0.4134 0.7199 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] picture : 0.1232 0.2281 0.3116 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] counter : 0.0125 0.0629 0.3510 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] desk : 0.0623 0.2002 0.6379 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] curtain : 0.0896 0.2680 0.5520 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] refridgerator : 0.2791 0.4078 0.4853 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] shower curtain : 0.2340 0.3819 0.5314 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] toilet : 0.7437 0.9473 0.9815 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] sink : 0.1536 0.3480 0.6920 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] bathtub : 0.5849 0.7295 0.8157 +[2025-02-22 11:13:11,947 INFO evaluator.py line 547 2775932] otherfurniture : 0.2054 0.3457 0.5167 +[2025-02-22 11:13:11,947 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:13:11,947 INFO evaluator.py line 554 2775932] average : 0.2569 0.4267 0.6234 +[2025-02-22 11:13:11,947 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:13:11,947 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:13:11,995 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:13:11,998 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:13:20,757 INFO hook.py line 109 2775932] Train: [12/100][50/800] Data 0.002 (0.003) Batch 0.140 (0.143) Remain 02:49:12 loss: -0.2570 Lr: 5.93999e-03 +[2025-02-22 11:13:27,921 INFO hook.py line 109 2775932] Train: [12/100][100/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 02:49:26 loss: 0.2672 Lr: 5.93875e-03 +[2025-02-22 11:13:35,071 INFO hook.py line 109 2775932] Train: [12/100][150/800] Data 0.002 (0.003) Batch 0.133 (0.143) Remain 02:49:18 loss: -0.2226 Lr: 5.93750e-03 +[2025-02-22 11:13:42,331 INFO hook.py line 109 2775932] Train: [12/100][200/800] Data 0.003 (0.004) Batch 0.129 (0.144) Remain 02:49:52 loss: -0.3456 Lr: 5.93626e-03 +[2025-02-22 11:13:49,607 INFO hook.py line 109 2775932] Train: [12/100][250/800] Data 0.004 (0.004) Batch 0.125 (0.144) Remain 02:50:12 loss: -0.1417 Lr: 5.93498e-03 +[2025-02-22 11:13:56,843 INFO hook.py line 109 2775932] Train: [12/100][300/800] Data 0.003 (0.004) Batch 0.139 (0.144) Remain 02:50:15 loss: -0.2174 Lr: 5.93369e-03 +[2025-02-22 11:14:03,815 INFO hook.py line 109 2775932] Train: [12/100][350/800] Data 0.002 (0.003) Batch 0.135 (0.143) Remain 02:49:20 loss: -0.3586 Lr: 5.93239e-03 +[2025-02-22 11:14:10,923 INFO hook.py line 109 2775932] Train: [12/100][400/800] Data 0.002 (0.003) Batch 0.150 (0.143) Remain 02:49:02 loss: -0.2960 Lr: 5.93107e-03 +[2025-02-22 11:14:18,351 INFO hook.py line 109 2775932] Train: [12/100][450/800] Data 0.003 (0.003) Batch 0.154 (0.144) Remain 02:49:36 loss: -0.1165 Lr: 5.92975e-03 +[2025-02-22 11:14:25,607 INFO hook.py line 109 2775932] Train: [12/100][500/800] Data 0.003 (0.003) Batch 0.128 (0.144) Remain 02:49:39 loss: -0.6227 Lr: 5.92841e-03 +[2025-02-22 11:14:32,733 INFO hook.py line 109 2775932] Train: [12/100][550/800] Data 0.002 (0.003) Batch 0.132 (0.144) Remain 02:49:22 loss: 0.2307 Lr: 5.92705e-03 +[2025-02-22 11:14:40,151 INFO hook.py line 109 2775932] Train: [12/100][600/800] Data 0.003 (0.003) Batch 0.153 (0.144) Remain 02:49:41 loss: -0.3765 Lr: 5.92569e-03 +[2025-02-22 11:14:47,411 INFO hook.py line 109 2775932] Train: [12/100][650/800] Data 0.003 (0.003) Batch 0.145 (0.144) Remain 02:49:39 loss: -0.1603 Lr: 5.92431e-03 +[2025-02-22 11:14:54,569 INFO hook.py line 109 2775932] Train: [12/100][700/800] Data 0.003 (0.003) Batch 0.134 (0.144) Remain 02:49:27 loss: 0.0937 Lr: 5.92292e-03 +[2025-02-22 11:15:01,792 INFO hook.py line 109 2775932] Train: [12/100][750/800] Data 0.002 (0.003) Batch 0.148 (0.144) Remain 02:49:20 loss: -0.2668 Lr: 5.92152e-03 +[2025-02-22 11:15:08,895 INFO hook.py line 109 2775932] Train: [12/100][800/800] Data 0.003 (0.003) Batch 0.127 (0.144) Remain 02:49:04 loss: -0.3460 Lr: 5.92010e-03 +[2025-02-22 11:15:08,896 INFO misc.py line 135 2775932] Train result: loss: -0.2256 seg_loss: 0.3573 bias_l1_loss: 0.3175 bias_cosine_loss: -0.9003 +[2025-02-22 11:15:08,896 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:15:15,907 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6021 +[2025-02-22 11:15:16,178 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1854 +[2025-02-22 11:15:16,253 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2287 +[2025-02-22 11:15:16,363 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4855 +[2025-02-22 11:15:16,697 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4555 +[2025-02-22 11:15:16,757 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.3794 +[2025-02-22 11:15:17,051 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3477 +[2025-02-22 11:15:17,086 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.2869 +[2025-02-22 11:15:17,216 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.2274 +[2025-02-22 11:15:17,298 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.7322 +[2025-02-22 11:15:17,564 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0310 +[2025-02-22 11:15:17,667 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0804 +[2025-02-22 11:15:17,751 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4323 +[2025-02-22 11:15:17,863 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8591 +[2025-02-22 11:15:17,965 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1523 +[2025-02-22 11:15:18,045 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4157 +[2025-02-22 11:15:18,192 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2204 +[2025-02-22 11:15:18,300 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2756 +[2025-02-22 11:15:18,499 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0420 +[2025-02-22 11:15:18,566 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1507 +[2025-02-22 11:15:18,725 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4275 +[2025-02-22 11:15:18,929 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4156 +[2025-02-22 11:15:19,010 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2133 +[2025-02-22 11:15:19,070 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2255 +[2025-02-22 11:15:19,144 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3537 +[2025-02-22 11:15:19,209 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.1797 +[2025-02-22 11:15:19,372 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.5545 +[2025-02-22 11:15:19,503 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4466 +[2025-02-22 11:15:19,604 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4919 +[2025-02-22 11:15:19,672 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4346 +[2025-02-22 11:15:20,430 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.1150 +[2025-02-22 11:15:20,562 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5776 +[2025-02-22 11:15:20,601 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5807 +[2025-02-22 11:15:20,698 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2683 +[2025-02-22 11:15:20,740 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.0507 +[2025-02-22 11:15:20,855 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2401 +[2025-02-22 11:15:20,919 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3042 +[2025-02-22 11:15:21,056 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4576 +[2025-02-22 11:15:21,238 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6758 +[2025-02-22 11:15:21,453 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9203 +[2025-02-22 11:15:21,639 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6684 +[2025-02-22 11:15:21,690 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0080 +[2025-02-22 11:15:21,744 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4356 +[2025-02-22 11:15:22,017 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4342 +[2025-02-22 11:15:22,062 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.1490 +[2025-02-22 11:15:22,104 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3685 +[2025-02-22 11:15:22,203 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.6228 +[2025-02-22 11:15:22,322 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0517 +[2025-02-22 11:15:22,436 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0996 +[2025-02-22 11:15:22,546 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4312 +[2025-02-22 11:15:22,647 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.3267 +[2025-02-22 11:15:22,781 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1243 +[2025-02-22 11:15:22,829 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4606 +[2025-02-22 11:15:22,938 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0118 +[2025-02-22 11:15:23,028 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6779 +[2025-02-22 11:15:23,079 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5583 +[2025-02-22 11:15:23,206 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0550 +[2025-02-22 11:15:23,245 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2419 +[2025-02-22 11:15:23,468 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0261 +[2025-02-22 11:15:23,588 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0958 +[2025-02-22 11:15:23,654 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5210 +[2025-02-22 11:15:23,711 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4318 +[2025-02-22 11:15:23,881 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0948 +[2025-02-22 11:15:24,000 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6371 +[2025-02-22 11:15:24,077 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.6119 +[2025-02-22 11:15:24,201 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0055 +[2025-02-22 11:15:24,400 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3335 +[2025-02-22 11:15:24,501 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5407 +[2025-02-22 11:15:24,556 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7371 +[2025-02-22 11:15:24,612 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1213 +[2025-02-22 11:15:24,777 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0242 +[2025-02-22 11:15:24,818 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4144 +[2025-02-22 11:15:24,879 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3820 +[2025-02-22 11:15:24,975 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.7923 +[2025-02-22 11:15:25,195 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3380 +[2025-02-22 11:15:25,274 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0508 +[2025-02-22 11:15:25,443 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.0944 +[2025-02-22 11:15:25,533 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5263 +[2025-02-22 11:15:39,459 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:15:39,459 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:15:39,459 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] cabinet : 0.1460 0.3235 0.5772 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] bed : 0.3191 0.6819 0.8260 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] chair : 0.6439 0.8168 0.8791 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] sofa : 0.3318 0.5946 0.8286 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] table : 0.3342 0.5294 0.6574 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] door : 0.1316 0.2626 0.4088 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] window : 0.0968 0.2146 0.4138 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] bookshelf : 0.1809 0.4304 0.6341 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] picture : 0.2470 0.4103 0.4935 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] counter : 0.0276 0.0788 0.4459 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] desk : 0.0383 0.1525 0.5619 +[2025-02-22 11:15:39,459 INFO evaluator.py line 547 2775932] curtain : 0.1496 0.2537 0.4445 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] refridgerator : 0.2432 0.3849 0.4317 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] shower curtain : 0.4166 0.6221 0.6755 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] toilet : 0.8206 0.9828 0.9828 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] sink : 0.2767 0.5518 0.8416 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] bathtub : 0.4279 0.5589 0.8324 +[2025-02-22 11:15:39,460 INFO evaluator.py line 547 2775932] otherfurniture : 0.1820 0.3098 0.4708 +[2025-02-22 11:15:39,460 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:15:39,460 INFO evaluator.py line 554 2775932] average : 0.2786 0.4533 0.6336 +[2025-02-22 11:15:39,460 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:15:39,460 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:15:39,517 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:15:39,519 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:15:48,602 INFO hook.py line 109 2775932] Train: [13/100][50/800] Data 0.003 (0.011) Batch 0.138 (0.155) Remain 03:02:10 loss: 0.0235 Lr: 5.91867e-03 +[2025-02-22 11:15:55,686 INFO hook.py line 109 2775932] Train: [13/100][100/800] Data 0.003 (0.007) Batch 0.132 (0.148) Remain 02:53:46 loss: -0.1613 Lr: 5.91723e-03 +[2025-02-22 11:16:03,329 INFO hook.py line 109 2775932] Train: [13/100][150/800] Data 0.002 (0.005) Batch 0.118 (0.150) Remain 02:55:27 loss: -0.2643 Lr: 5.91578e-03 +[2025-02-22 11:16:10,473 INFO hook.py line 109 2775932] Train: [13/100][200/800] Data 0.002 (0.005) Batch 0.150 (0.148) Remain 02:53:15 loss: -0.3250 Lr: 5.91432e-03 +[2025-02-22 11:16:17,708 INFO hook.py line 109 2775932] Train: [13/100][250/800] Data 0.003 (0.004) Batch 0.160 (0.147) Remain 02:52:20 loss: -0.0400 Lr: 5.91284e-03 +[2025-02-22 11:16:25,308 INFO hook.py line 109 2775932] Train: [13/100][300/800] Data 0.003 (0.004) Batch 0.143 (0.148) Remain 02:53:06 loss: -0.2849 Lr: 5.91135e-03 +[2025-02-22 11:16:32,479 INFO hook.py line 109 2775932] Train: [13/100][350/800] Data 0.003 (0.004) Batch 0.118 (0.147) Remain 02:52:11 loss: -0.0138 Lr: 5.90985e-03 +[2025-02-22 11:16:39,802 INFO hook.py line 109 2775932] Train: [13/100][400/800] Data 0.003 (0.004) Batch 0.138 (0.147) Remain 02:51:55 loss: -0.3722 Lr: 5.90833e-03 +[2025-02-22 11:16:46,908 INFO hook.py line 109 2775932] Train: [13/100][450/800] Data 0.005 (0.004) Batch 0.128 (0.147) Remain 02:51:06 loss: -0.3206 Lr: 5.90680e-03 +[2025-02-22 11:16:54,201 INFO hook.py line 109 2775932] Train: [13/100][500/800] Data 0.002 (0.004) Batch 0.151 (0.147) Remain 02:50:53 loss: -0.0336 Lr: 5.90526e-03 +[2025-02-22 11:17:01,352 INFO hook.py line 109 2775932] Train: [13/100][550/800] Data 0.004 (0.004) Batch 0.156 (0.146) Remain 02:50:22 loss: -0.2246 Lr: 5.90371e-03 +[2025-02-22 11:17:08,635 INFO hook.py line 109 2775932] Train: [13/100][600/800] Data 0.002 (0.003) Batch 0.138 (0.146) Remain 02:50:10 loss: -0.0175 Lr: 5.90215e-03 +[2025-02-22 11:17:15,685 INFO hook.py line 109 2775932] Train: [13/100][650/800] Data 0.002 (0.003) Batch 0.149 (0.146) Remain 02:49:35 loss: 0.0375 Lr: 5.90057e-03 +[2025-02-22 11:17:23,110 INFO hook.py line 109 2775932] Train: [13/100][700/800] Data 0.003 (0.003) Batch 0.141 (0.146) Remain 02:49:40 loss: -0.0527 Lr: 5.89898e-03 +[2025-02-22 11:17:30,183 INFO hook.py line 109 2775932] Train: [13/100][750/800] Data 0.003 (0.003) Batch 0.139 (0.146) Remain 02:49:12 loss: -0.1112 Lr: 5.89738e-03 +[2025-02-22 11:17:37,161 INFO hook.py line 109 2775932] Train: [13/100][800/800] Data 0.002 (0.003) Batch 0.116 (0.145) Remain 02:48:37 loss: -0.1458 Lr: 5.89577e-03 +[2025-02-22 11:17:37,163 INFO misc.py line 135 2775932] Train result: loss: -0.2297 seg_loss: 0.3535 bias_l1_loss: 0.3177 bias_cosine_loss: -0.9009 +[2025-02-22 11:17:37,163 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:17:44,124 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6571 +[2025-02-22 11:17:44,840 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0370 +[2025-02-22 11:17:44,908 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2980 +[2025-02-22 11:17:44,984 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4032 +[2025-02-22 11:17:45,045 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.1302 +[2025-02-22 11:17:45,101 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8726 +[2025-02-22 11:17:45,381 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2562 +[2025-02-22 11:17:45,409 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3535 +[2025-02-22 11:17:45,559 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0650 +[2025-02-22 11:17:45,643 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2811 +[2025-02-22 11:17:45,894 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3690 +[2025-02-22 11:17:46,005 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1073 +[2025-02-22 11:17:46,072 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.9809 +[2025-02-22 11:17:46,174 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9507 +[2025-02-22 11:17:46,381 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4655 +[2025-02-22 11:17:46,467 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4980 +[2025-02-22 11:17:46,603 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.0948 +[2025-02-22 11:17:46,694 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0327 +[2025-02-22 11:17:46,864 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.6297 +[2025-02-22 11:17:46,928 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3514 +[2025-02-22 11:17:47,084 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6378 +[2025-02-22 11:17:47,266 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.8431 +[2025-02-22 11:17:47,337 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0667 +[2025-02-22 11:17:47,399 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0514 +[2025-02-22 11:17:47,467 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0077 +[2025-02-22 11:17:47,534 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4488 +[2025-02-22 11:17:47,672 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.9155 +[2025-02-22 11:17:47,762 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7993 +[2025-02-22 11:17:47,836 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4800 +[2025-02-22 11:17:47,911 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3438 +[2025-02-22 11:17:48,581 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.2450 +[2025-02-22 11:17:48,690 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5046 +[2025-02-22 11:17:48,727 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6276 +[2025-02-22 11:17:48,828 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0657 +[2025-02-22 11:17:48,871 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6948 +[2025-02-22 11:17:49,013 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1818 +[2025-02-22 11:17:49,095 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3901 +[2025-02-22 11:17:49,227 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5677 +[2025-02-22 11:17:49,393 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0876 +[2025-02-22 11:17:49,605 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9492 +[2025-02-22 11:17:49,764 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4168 +[2025-02-22 11:17:49,823 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1311 +[2025-02-22 11:17:49,871 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6299 +[2025-02-22 11:17:50,212 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5271 +[2025-02-22 11:17:50,270 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2477 +[2025-02-22 11:17:50,330 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3918 +[2025-02-22 11:17:50,437 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7019 +[2025-02-22 11:17:50,565 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.4813 +[2025-02-22 11:17:50,679 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3673 +[2025-02-22 11:17:50,777 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3811 +[2025-02-22 11:17:50,852 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1287 +[2025-02-22 11:17:50,997 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0014 +[2025-02-22 11:17:51,037 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7421 +[2025-02-22 11:17:51,134 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2353 +[2025-02-22 11:17:51,230 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7562 +[2025-02-22 11:17:51,278 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6909 +[2025-02-22 11:17:51,400 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0601 +[2025-02-22 11:17:51,441 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3117 +[2025-02-22 11:17:51,688 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1890 +[2025-02-22 11:17:51,787 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0741 +[2025-02-22 11:17:51,863 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8877 +[2025-02-22 11:17:51,925 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2093 +[2025-02-22 11:17:52,094 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2047 +[2025-02-22 11:17:52,210 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7692 +[2025-02-22 11:17:52,282 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.7737 +[2025-02-22 11:17:52,399 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0162 +[2025-02-22 11:17:52,557 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2643 +[2025-02-22 11:17:52,655 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.4293 +[2025-02-22 11:17:52,708 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7015 +[2025-02-22 11:17:52,764 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1458 +[2025-02-22 11:17:52,928 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.3217 +[2025-02-22 11:17:52,965 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4521 +[2025-02-22 11:17:53,017 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5174 +[2025-02-22 11:17:53,115 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5388 +[2025-02-22 11:17:53,323 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3546 +[2025-02-22 11:17:53,396 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2349 +[2025-02-22 11:17:53,575 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3462 +[2025-02-22 11:17:53,691 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4188 +[2025-02-22 11:18:07,063 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:18:07,064 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:18:07,064 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] cabinet : 0.1028 0.2404 0.4653 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] bed : 0.3338 0.7014 0.8070 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] chair : 0.6687 0.8314 0.8915 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] sofa : 0.3768 0.6728 0.8329 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] table : 0.2675 0.4546 0.5928 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] door : 0.2232 0.4280 0.5775 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] window : 0.1046 0.2063 0.3695 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] bookshelf : 0.0546 0.2058 0.5676 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] picture : 0.2095 0.3254 0.4167 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] counter : 0.0014 0.0074 0.2680 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] desk : 0.0327 0.1136 0.5830 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] curtain : 0.0993 0.2032 0.3764 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] refridgerator : 0.0724 0.1445 0.2045 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] shower curtain : 0.4179 0.6274 0.6818 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] toilet : 0.6986 0.8938 0.9396 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] sink : 0.0983 0.3013 0.5356 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] bathtub : 0.4833 0.7054 0.8295 +[2025-02-22 11:18:07,064 INFO evaluator.py line 547 2775932] otherfurniture : 0.3053 0.4634 0.6338 +[2025-02-22 11:18:07,064 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:18:07,064 INFO evaluator.py line 554 2775932] average : 0.2528 0.4181 0.5874 +[2025-02-22 11:18:07,064 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:18:07,064 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:18:07,106 INFO misc.py line 164 2775932] Currently Best AP50: 0.4712 +[2025-02-22 11:18:07,108 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:18:15,988 INFO hook.py line 109 2775932] Train: [14/100][50/800] Data 0.003 (0.003) Batch 0.152 (0.147) Remain 02:50:16 loss: -0.4080 Lr: 5.89414e-03 +[2025-02-22 11:18:23,126 INFO hook.py line 109 2775932] Train: [14/100][100/800] Data 0.002 (0.003) Batch 0.140 (0.145) Remain 02:47:40 loss: -0.2023 Lr: 5.89250e-03 +[2025-02-22 11:18:30,114 INFO hook.py line 109 2775932] Train: [14/100][150/800] Data 0.002 (0.003) Batch 0.162 (0.143) Remain 02:45:35 loss: 0.1798 Lr: 5.89085e-03 +[2025-02-22 11:18:37,181 INFO hook.py line 109 2775932] Train: [14/100][200/800] Data 0.003 (0.003) Batch 0.159 (0.143) Remain 02:44:57 loss: -0.4043 Lr: 5.88919e-03 +[2025-02-22 11:18:44,543 INFO hook.py line 109 2775932] Train: [14/100][250/800] Data 0.002 (0.004) Batch 0.132 (0.144) Remain 02:45:55 loss: -0.1045 Lr: 5.88751e-03 +[2025-02-22 11:18:51,681 INFO hook.py line 109 2775932] Train: [14/100][300/800] Data 0.004 (0.004) Batch 0.157 (0.143) Remain 02:45:39 loss: 0.1278 Lr: 5.88582e-03 +[2025-02-22 11:18:58,509 INFO hook.py line 109 2775932] Train: [14/100][350/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 02:44:23 loss: -0.3985 Lr: 5.88412e-03 +[2025-02-22 11:19:05,874 INFO hook.py line 109 2775932] Train: [14/100][400/800] Data 0.003 (0.003) Batch 0.148 (0.143) Remain 02:44:58 loss: -0.1754 Lr: 5.88241e-03 +[2025-02-22 11:19:13,045 INFO hook.py line 109 2775932] Train: [14/100][450/800] Data 0.003 (0.003) Batch 0.156 (0.143) Remain 02:44:54 loss: -0.3679 Lr: 5.88069e-03 +[2025-02-22 11:19:20,224 INFO hook.py line 109 2775932] Train: [14/100][500/800] Data 0.003 (0.003) Batch 0.167 (0.143) Remain 02:44:50 loss: -0.0425 Lr: 5.87895e-03 +[2025-02-22 11:19:27,632 INFO hook.py line 109 2775932] Train: [14/100][550/800] Data 0.002 (0.003) Batch 0.153 (0.144) Remain 02:45:15 loss: -0.2433 Lr: 5.87720e-03 +[2025-02-22 11:19:34,994 INFO hook.py line 109 2775932] Train: [14/100][600/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 02:45:29 loss: -0.2700 Lr: 5.87544e-03 +[2025-02-22 11:19:42,336 INFO hook.py line 109 2775932] Train: [14/100][650/800] Data 0.003 (0.003) Batch 0.173 (0.144) Remain 02:45:37 loss: -0.0177 Lr: 5.87366e-03 +[2025-02-22 11:19:49,626 INFO hook.py line 109 2775932] Train: [14/100][700/800] Data 0.003 (0.003) Batch 0.138 (0.144) Remain 02:45:38 loss: -0.0973 Lr: 5.87188e-03 +[2025-02-22 11:19:56,705 INFO hook.py line 109 2775932] Train: [14/100][750/800] Data 0.003 (0.003) Batch 0.147 (0.144) Remain 02:45:19 loss: -0.2204 Lr: 5.87011e-03 +[2025-02-22 11:20:03,500 INFO hook.py line 109 2775932] Train: [14/100][800/800] Data 0.002 (0.003) Batch 0.105 (0.144) Remain 02:44:36 loss: -0.0323 Lr: 5.86830e-03 +[2025-02-22 11:20:03,500 INFO misc.py line 135 2775932] Train result: loss: -0.2460 seg_loss: 0.3462 bias_l1_loss: 0.3113 bias_cosine_loss: -0.9036 +[2025-02-22 11:20:03,501 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:20:10,782 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.5433 +[2025-02-22 11:20:11,004 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0056 +[2025-02-22 11:20:11,133 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3230 +[2025-02-22 11:20:11,199 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5026 +[2025-02-22 11:20:11,275 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4744 +[2025-02-22 11:20:11,331 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7487 +[2025-02-22 11:20:11,658 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3342 +[2025-02-22 11:20:11,695 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5122 +[2025-02-22 11:20:11,838 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2021 +[2025-02-22 11:20:11,887 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2201 +[2025-02-22 11:20:12,143 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1884 +[2025-02-22 11:20:12,260 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0767 +[2025-02-22 11:20:12,348 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4118 +[2025-02-22 11:20:12,439 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.5336 +[2025-02-22 11:20:12,538 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6664 +[2025-02-22 11:20:12,622 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5268 +[2025-02-22 11:20:12,755 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.1902 +[2025-02-22 11:20:12,850 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.0692 +[2025-02-22 11:20:13,026 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0811 +[2025-02-22 11:20:13,098 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0225 +[2025-02-22 11:20:13,238 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5393 +[2025-02-22 11:20:13,414 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3495 +[2025-02-22 11:20:13,484 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.5094 +[2025-02-22 11:20:13,533 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0101 +[2025-02-22 11:20:13,597 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.1385 +[2025-02-22 11:20:13,656 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5195 +[2025-02-22 11:20:13,793 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0930 +[2025-02-22 11:20:13,881 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6797 +[2025-02-22 11:20:13,946 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5349 +[2025-02-22 11:20:14,020 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5417 +[2025-02-22 11:20:14,684 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3965 +[2025-02-22 11:20:14,783 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4369 +[2025-02-22 11:20:14,815 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5122 +[2025-02-22 11:20:14,914 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0276 +[2025-02-22 11:20:14,959 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5241 +[2025-02-22 11:20:15,077 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1675 +[2025-02-22 11:20:15,145 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4721 +[2025-02-22 11:20:15,264 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5215 +[2025-02-22 11:20:15,419 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3172 +[2025-02-22 11:20:15,627 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8213 +[2025-02-22 11:20:15,794 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6002 +[2025-02-22 11:20:15,860 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0601 +[2025-02-22 11:20:15,902 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5155 +[2025-02-22 11:20:16,167 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5696 +[2025-02-22 11:20:16,219 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.0238 +[2025-02-22 11:20:16,268 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4107 +[2025-02-22 11:20:16,363 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2702 +[2025-02-22 11:20:16,481 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0220 +[2025-02-22 11:20:16,584 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0686 +[2025-02-22 11:20:16,685 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3100 +[2025-02-22 11:20:16,752 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.4431 +[2025-02-22 11:20:16,924 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1493 +[2025-02-22 11:20:16,965 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5511 +[2025-02-22 11:20:17,084 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0683 +[2025-02-22 11:20:17,171 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7742 +[2025-02-22 11:20:17,220 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6142 +[2025-02-22 11:20:17,351 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1424 +[2025-02-22 11:20:17,404 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1349 +[2025-02-22 11:20:17,643 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0162 +[2025-02-22 11:20:17,752 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0986 +[2025-02-22 11:20:17,833 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7471 +[2025-02-22 11:20:17,891 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4638 +[2025-02-22 11:20:18,053 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0782 +[2025-02-22 11:20:18,181 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6195 +[2025-02-22 11:20:18,265 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4668 +[2025-02-22 11:20:18,393 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1653 +[2025-02-22 11:20:18,590 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3726 +[2025-02-22 11:20:18,681 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2326 +[2025-02-22 11:20:18,726 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6419 +[2025-02-22 11:20:18,784 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2923 +[2025-02-22 11:20:18,941 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0772 +[2025-02-22 11:20:18,978 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5295 +[2025-02-22 11:20:19,032 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.3934 +[2025-02-22 11:20:19,127 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8698 +[2025-02-22 11:20:19,357 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4231 +[2025-02-22 11:20:19,432 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1679 +[2025-02-22 11:20:19,628 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.0525 +[2025-02-22 11:20:19,708 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6785 +[2025-02-22 11:20:34,418 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:20:34,419 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:20:34,419 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] cabinet : 0.1820 0.3892 0.6212 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] bed : 0.2840 0.5894 0.7122 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] chair : 0.6922 0.8556 0.9080 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] sofa : 0.3164 0.5552 0.7639 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] table : 0.4087 0.6453 0.7639 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] door : 0.2032 0.4379 0.5881 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] window : 0.1163 0.2663 0.5561 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] bookshelf : 0.1988 0.5440 0.7285 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] picture : 0.1982 0.3301 0.4344 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] counter : 0.0324 0.1298 0.4319 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] desk : 0.0238 0.1091 0.5278 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] curtain : 0.1062 0.2506 0.5088 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] refridgerator : 0.3318 0.4568 0.5860 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] shower curtain : 0.3396 0.6365 0.7613 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] toilet : 0.8126 0.9828 1.0000 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] sink : 0.2499 0.6080 0.8621 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] bathtub : 0.2435 0.3509 0.7603 +[2025-02-22 11:20:34,419 INFO evaluator.py line 547 2775932] otherfurniture : 0.3001 0.4790 0.6337 +[2025-02-22 11:20:34,419 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:20:34,419 INFO evaluator.py line 554 2775932] average : 0.2800 0.4787 0.6749 +[2025-02-22 11:20:34,419 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:20:34,419 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:20:34,490 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4787 +[2025-02-22 11:20:34,492 INFO misc.py line 164 2775932] Currently Best AP50: 0.4787 +[2025-02-22 11:20:34,493 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:20:43,873 INFO hook.py line 109 2775932] Train: [15/100][50/800] Data 0.006 (0.003) Batch 0.143 (0.144) Remain 02:44:35 loss: -0.1977 Lr: 5.86648e-03 +[2025-02-22 11:20:51,051 INFO hook.py line 109 2775932] Train: [15/100][100/800] Data 0.003 (0.003) Batch 0.144 (0.144) Remain 02:44:25 loss: -0.0411 Lr: 5.86464e-03 +[2025-02-22 11:20:58,316 INFO hook.py line 109 2775932] Train: [15/100][150/800] Data 0.003 (0.004) Batch 0.146 (0.144) Remain 02:44:57 loss: -0.0695 Lr: 5.86280e-03 +[2025-02-22 11:21:05,485 INFO hook.py line 109 2775932] Train: [15/100][200/800] Data 0.003 (0.004) Batch 0.156 (0.144) Remain 02:44:36 loss: -0.1210 Lr: 5.86094e-03 +[2025-02-22 11:21:12,680 INFO hook.py line 109 2775932] Train: [15/100][250/800] Data 0.003 (0.004) Batch 0.161 (0.144) Remain 02:44:28 loss: -0.0124 Lr: 5.85906e-03 +[2025-02-22 11:21:19,779 INFO hook.py line 109 2775932] Train: [15/100][300/800] Data 0.003 (0.004) Batch 0.152 (0.144) Remain 02:43:58 loss: -0.4296 Lr: 5.85718e-03 +[2025-02-22 11:21:26,808 INFO hook.py line 109 2775932] Train: [15/100][350/800] Data 0.003 (0.003) Batch 0.134 (0.143) Remain 02:43:21 loss: -0.4075 Lr: 5.85528e-03 +[2025-02-22 11:21:34,390 INFO hook.py line 109 2775932] Train: [15/100][400/800] Data 0.004 (0.003) Batch 0.149 (0.144) Remain 02:44:26 loss: -0.0784 Lr: 5.85338e-03 +[2025-02-22 11:21:41,710 INFO hook.py line 109 2775932] Train: [15/100][450/800] Data 0.003 (0.003) Batch 0.159 (0.144) Remain 02:44:35 loss: -0.3319 Lr: 5.85146e-03 +[2025-02-22 11:21:49,253 INFO hook.py line 109 2775932] Train: [15/100][500/800] Data 0.002 (0.004) Batch 0.130 (0.145) Remain 02:45:12 loss: -0.1590 Lr: 5.84952e-03 +[2025-02-22 11:21:56,404 INFO hook.py line 109 2775932] Train: [15/100][550/800] Data 0.003 (0.004) Batch 0.161 (0.145) Remain 02:44:51 loss: -0.1855 Lr: 5.84758e-03 +[2025-02-22 11:22:03,680 INFO hook.py line 109 2775932] Train: [15/100][600/800] Data 0.004 (0.004) Batch 0.144 (0.145) Remain 02:44:47 loss: -0.3400 Lr: 5.84562e-03 +[2025-02-22 11:22:10,824 INFO hook.py line 109 2775932] Train: [15/100][650/800] Data 0.003 (0.004) Batch 0.122 (0.145) Remain 02:44:29 loss: -0.4294 Lr: 5.84365e-03 +[2025-02-22 11:22:18,130 INFO hook.py line 109 2775932] Train: [15/100][700/800] Data 0.003 (0.004) Batch 0.122 (0.145) Remain 02:44:28 loss: -0.1395 Lr: 5.84167e-03 +[2025-02-22 11:22:25,090 INFO hook.py line 109 2775932] Train: [15/100][750/800] Data 0.002 (0.004) Batch 0.126 (0.145) Remain 02:43:55 loss: -0.2949 Lr: 5.83968e-03 +[2025-02-22 11:22:31,901 INFO hook.py line 109 2775932] Train: [15/100][800/800] Data 0.002 (0.003) Batch 0.101 (0.144) Remain 02:43:12 loss: -0.0423 Lr: 5.83767e-03 +[2025-02-22 11:22:31,902 INFO misc.py line 135 2775932] Train result: loss: -0.2494 seg_loss: 0.3433 bias_l1_loss: 0.3106 bias_cosine_loss: -0.9033 +[2025-02-22 11:22:31,902 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:22:39,152 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.5362 +[2025-02-22 11:22:39,594 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1647 +[2025-02-22 11:22:39,649 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2858 +[2025-02-22 11:22:39,722 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4264 +[2025-02-22 11:22:39,789 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4409 +[2025-02-22 11:22:39,844 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7078 +[2025-02-22 11:22:40,133 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2444 +[2025-02-22 11:22:40,161 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3406 +[2025-02-22 11:22:40,293 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1885 +[2025-02-22 11:22:40,348 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2011 +[2025-02-22 11:22:40,629 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3347 +[2025-02-22 11:22:40,727 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2759 +[2025-02-22 11:22:40,809 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.3912 +[2025-02-22 11:22:40,905 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3114 +[2025-02-22 11:22:40,992 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7686 +[2025-02-22 11:22:41,075 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5112 +[2025-02-22 11:22:41,216 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2724 +[2025-02-22 11:22:41,303 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1559 +[2025-02-22 11:22:41,473 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0135 +[2025-02-22 11:22:41,547 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1232 +[2025-02-22 11:22:41,687 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5400 +[2025-02-22 11:22:41,873 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.1718 +[2025-02-22 11:22:41,945 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0963 +[2025-02-22 11:22:42,006 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0626 +[2025-02-22 11:22:42,071 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2274 +[2025-02-22 11:22:42,133 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4054 +[2025-02-22 11:22:42,274 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1460 +[2025-02-22 11:22:42,368 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6450 +[2025-02-22 11:22:42,436 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4949 +[2025-02-22 11:22:42,508 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3865 +[2025-02-22 11:22:43,264 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.2810 +[2025-02-22 11:22:43,387 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.6086 +[2025-02-22 11:22:43,422 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6645 +[2025-02-22 11:22:43,517 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1963 +[2025-02-22 11:22:43,547 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.7031 +[2025-02-22 11:22:43,678 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0969 +[2025-02-22 11:22:43,757 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4207 +[2025-02-22 11:22:43,932 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5707 +[2025-02-22 11:22:44,068 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5096 +[2025-02-22 11:22:44,300 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6549 +[2025-02-22 11:22:44,476 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4531 +[2025-02-22 11:22:44,524 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0580 +[2025-02-22 11:22:44,570 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4923 +[2025-02-22 11:22:44,880 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5250 +[2025-02-22 11:22:44,934 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2337 +[2025-02-22 11:22:44,982 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4975 +[2025-02-22 11:22:45,075 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8323 +[2025-02-22 11:22:45,199 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.2249 +[2025-02-22 11:22:45,308 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1857 +[2025-02-22 11:22:45,394 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1814 +[2025-02-22 11:22:45,469 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1671 +[2025-02-22 11:22:45,615 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0348 +[2025-02-22 11:22:45,814 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6934 +[2025-02-22 11:22:45,929 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8290 +[2025-02-22 11:22:46,018 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6270 +[2025-02-22 11:22:46,065 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7344 +[2025-02-22 11:22:46,189 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0548 +[2025-02-22 11:22:46,231 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1553 +[2025-02-22 11:22:46,464 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2949 +[2025-02-22 11:22:46,578 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1833 +[2025-02-22 11:22:46,650 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5931 +[2025-02-22 11:22:46,717 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2181 +[2025-02-22 11:22:47,006 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1083 +[2025-02-22 11:22:47,135 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.8651 +[2025-02-22 11:22:47,201 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.6403 +[2025-02-22 11:22:47,310 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0830 +[2025-02-22 11:22:47,465 INFO evaluator.py line 595 2775932] Test: [67/78] Loss 0.1247 +[2025-02-22 11:22:47,541 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2410 +[2025-02-22 11:22:47,588 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6857 +[2025-02-22 11:22:47,630 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0540 +[2025-02-22 11:22:47,753 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0189 +[2025-02-22 11:22:47,783 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2937 +[2025-02-22 11:22:47,829 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5902 +[2025-02-22 11:22:47,933 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.6806 +[2025-02-22 11:22:48,122 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4567 +[2025-02-22 11:22:48,186 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2493 +[2025-02-22 11:22:48,353 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3902 +[2025-02-22 11:22:48,419 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5776 +[2025-02-22 11:23:02,323 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:23:02,323 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:23:02,323 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] cabinet : 0.1495 0.3412 0.5568 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] bed : 0.3295 0.6262 0.7867 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] chair : 0.6785 0.8523 0.9115 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] sofa : 0.2620 0.4647 0.7846 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] table : 0.3031 0.5624 0.7071 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] door : 0.1828 0.3985 0.5672 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] window : 0.1071 0.2283 0.4326 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] bookshelf : 0.2177 0.5162 0.6732 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] picture : 0.2730 0.4548 0.5498 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] counter : 0.0194 0.0750 0.3942 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] desk : 0.0454 0.1898 0.6599 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] curtain : 0.1203 0.2109 0.3292 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] refridgerator : 0.2191 0.3324 0.3651 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] shower curtain : 0.0246 0.1370 0.5467 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] toilet : 0.7833 0.9618 0.9788 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] sink : 0.1946 0.4295 0.7938 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] bathtub : 0.5358 0.6781 0.7726 +[2025-02-22 11:23:02,323 INFO evaluator.py line 547 2775932] otherfurniture : 0.3167 0.4649 0.6290 +[2025-02-22 11:23:02,323 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:23:02,323 INFO evaluator.py line 554 2775932] average : 0.2646 0.4402 0.6355 +[2025-02-22 11:23:02,323 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:23:02,324 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:23:02,381 INFO misc.py line 164 2775932] Currently Best AP50: 0.4787 +[2025-02-22 11:23:02,383 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:23:11,527 INFO hook.py line 109 2775932] Train: [16/100][50/800] Data 0.003 (0.017) Batch 0.134 (0.159) Remain 03:00:25 loss: -0.2748 Lr: 5.83565e-03 +[2025-02-22 11:23:18,844 INFO hook.py line 109 2775932] Train: [16/100][100/800] Data 0.004 (0.010) Batch 0.130 (0.153) Remain 02:52:44 loss: 0.1297 Lr: 5.83362e-03 +[2025-02-22 11:23:25,814 INFO hook.py line 109 2775932] Train: [16/100][150/800] Data 0.002 (0.008) Batch 0.150 (0.148) Remain 02:47:30 loss: 0.3715 Lr: 5.83158e-03 +[2025-02-22 11:23:32,868 INFO hook.py line 109 2775932] Train: [16/100][200/800] Data 0.002 (0.006) Batch 0.143 (0.146) Remain 02:45:22 loss: -0.2376 Lr: 5.82952e-03 +[2025-02-22 11:23:39,864 INFO hook.py line 109 2775932] Train: [16/100][250/800] Data 0.002 (0.006) Batch 0.153 (0.145) Remain 02:43:46 loss: -0.3018 Lr: 5.82746e-03 +[2025-02-22 11:23:46,904 INFO hook.py line 109 2775932] Train: [16/100][300/800] Data 0.003 (0.005) Batch 0.129 (0.144) Remain 02:42:51 loss: -0.0214 Lr: 5.82538e-03 +[2025-02-22 11:23:54,017 INFO hook.py line 109 2775932] Train: [16/100][350/800] Data 0.003 (0.005) Batch 0.137 (0.144) Remain 02:42:23 loss: -0.1035 Lr: 5.82329e-03 +[2025-02-22 11:24:01,218 INFO hook.py line 109 2775932] Train: [16/100][400/800] Data 0.002 (0.005) Batch 0.140 (0.144) Remain 02:42:16 loss: -0.2719 Lr: 5.82119e-03 +[2025-02-22 11:24:09,054 INFO hook.py line 109 2775932] Train: [16/100][450/800] Data 0.002 (0.006) Batch 0.137 (0.145) Remain 02:43:44 loss: -0.0553 Lr: 5.81907e-03 +[2025-02-22 11:24:16,051 INFO hook.py line 109 2775932] Train: [16/100][500/800] Data 0.003 (0.005) Batch 0.130 (0.145) Remain 02:43:00 loss: -0.4630 Lr: 5.81695e-03 +[2025-02-22 11:24:23,295 INFO hook.py line 109 2775932] Train: [16/100][550/800] Data 0.002 (0.005) Batch 0.136 (0.145) Remain 02:42:52 loss: -0.2569 Lr: 5.81481e-03 +[2025-02-22 11:24:30,713 INFO hook.py line 109 2775932] Train: [16/100][600/800] Data 0.002 (0.005) Batch 0.176 (0.145) Remain 02:43:05 loss: -0.2221 Lr: 5.81266e-03 +[2025-02-22 11:24:38,215 INFO hook.py line 109 2775932] Train: [16/100][650/800] Data 0.002 (0.005) Batch 0.137 (0.146) Remain 02:43:23 loss: -0.1726 Lr: 5.81049e-03 +[2025-02-22 11:24:45,553 INFO hook.py line 109 2775932] Train: [16/100][700/800] Data 0.003 (0.005) Batch 0.133 (0.146) Remain 02:43:21 loss: -0.0648 Lr: 5.80832e-03 +[2025-02-22 11:24:52,946 INFO hook.py line 109 2775932] Train: [16/100][750/800] Data 0.003 (0.005) Batch 0.132 (0.146) Remain 02:43:24 loss: -0.4580 Lr: 5.80613e-03 +[2025-02-22 11:24:59,769 INFO hook.py line 109 2775932] Train: [16/100][800/800] Data 0.002 (0.004) Batch 0.098 (0.145) Remain 02:42:37 loss: -0.0679 Lr: 5.80393e-03 +[2025-02-22 11:24:59,769 INFO misc.py line 135 2775932] Train result: loss: -0.2739 seg_loss: 0.3304 bias_l1_loss: 0.3022 bias_cosine_loss: -0.9065 +[2025-02-22 11:24:59,771 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:25:06,825 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6339 +[2025-02-22 11:25:07,180 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0200 +[2025-02-22 11:25:07,627 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3396 +[2025-02-22 11:25:07,697 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5224 +[2025-02-22 11:25:07,766 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5061 +[2025-02-22 11:25:07,825 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.6287 +[2025-02-22 11:25:08,074 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2778 +[2025-02-22 11:25:08,111 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3671 +[2025-02-22 11:25:08,267 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0064 +[2025-02-22 11:25:08,323 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2548 +[2025-02-22 11:25:08,555 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0296 +[2025-02-22 11:25:08,674 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1388 +[2025-02-22 11:25:08,748 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5448 +[2025-02-22 11:25:08,846 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.6780 +[2025-02-22 11:25:08,921 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7462 +[2025-02-22 11:25:08,979 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5533 +[2025-02-22 11:25:09,103 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3633 +[2025-02-22 11:25:09,218 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0347 +[2025-02-22 11:25:09,404 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0990 +[2025-02-22 11:25:09,465 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0850 +[2025-02-22 11:25:09,620 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5033 +[2025-02-22 11:25:09,782 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.7585 +[2025-02-22 11:25:09,850 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1974 +[2025-02-22 11:25:09,922 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2920 +[2025-02-22 11:25:09,978 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3777 +[2025-02-22 11:25:10,031 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5041 +[2025-02-22 11:25:10,155 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3721 +[2025-02-22 11:25:10,234 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0632 +[2025-02-22 11:25:10,306 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4571 +[2025-02-22 11:25:10,373 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3944 +[2025-02-22 11:25:11,175 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3689 +[2025-02-22 11:25:11,290 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3606 +[2025-02-22 11:25:11,332 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5669 +[2025-02-22 11:25:11,423 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1014 +[2025-02-22 11:25:11,462 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6177 +[2025-02-22 11:25:11,566 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8833 +[2025-02-22 11:25:11,646 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4100 +[2025-02-22 11:25:11,772 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4951 +[2025-02-22 11:25:11,921 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 1.0563 +[2025-02-22 11:25:12,152 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6903 +[2025-02-22 11:25:12,303 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4135 +[2025-02-22 11:25:12,350 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0573 +[2025-02-22 11:25:12,389 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6080 +[2025-02-22 11:25:12,646 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4406 +[2025-02-22 11:25:12,693 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.0355 +[2025-02-22 11:25:12,740 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5269 +[2025-02-22 11:25:12,840 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5292 +[2025-02-22 11:25:12,961 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1392 +[2025-02-22 11:25:13,063 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0746 +[2025-02-22 11:25:13,153 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4512 +[2025-02-22 11:25:13,224 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0639 +[2025-02-22 11:25:13,364 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.1165 +[2025-02-22 11:25:13,424 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6758 +[2025-02-22 11:25:13,521 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.7832 +[2025-02-22 11:25:13,620 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.6871 +[2025-02-22 11:25:13,664 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6314 +[2025-02-22 11:25:13,777 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0219 +[2025-02-22 11:25:13,821 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0346 +[2025-02-22 11:25:14,031 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3178 +[2025-02-22 11:25:14,145 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.4170 +[2025-02-22 11:25:14,213 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8439 +[2025-02-22 11:25:14,281 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2667 +[2025-02-22 11:25:14,438 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2880 +[2025-02-22 11:25:14,577 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7808 +[2025-02-22 11:25:14,655 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1282 +[2025-02-22 11:25:14,759 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1726 +[2025-02-22 11:25:14,916 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3713 +[2025-02-22 11:25:14,996 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1956 +[2025-02-22 11:25:15,046 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7274 +[2025-02-22 11:25:15,092 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2903 +[2025-02-22 11:25:15,231 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1726 +[2025-02-22 11:25:15,280 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3829 +[2025-02-22 11:25:15,334 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6554 +[2025-02-22 11:25:15,441 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.6696 +[2025-02-22 11:25:15,620 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4225 +[2025-02-22 11:25:15,700 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1494 +[2025-02-22 11:25:15,858 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3497 +[2025-02-22 11:25:15,939 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4531 +[2025-02-22 11:25:27,756 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:25:27,756 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:25:27,756 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] cabinet : 0.1561 0.3333 0.5790 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] bed : 0.3096 0.6431 0.8069 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] chair : 0.7137 0.8824 0.9296 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] sofa : 0.3515 0.5850 0.8078 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] table : 0.2625 0.4567 0.5980 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] door : 0.1894 0.3616 0.5244 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] window : 0.1653 0.3362 0.5638 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] bookshelf : 0.2050 0.5065 0.7885 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] picture : 0.1947 0.3456 0.4543 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] counter : 0.0269 0.1252 0.3870 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] desk : 0.0708 0.2257 0.5774 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] curtain : 0.2416 0.4187 0.6139 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] refridgerator : 0.2268 0.3254 0.3563 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] shower curtain : 0.4152 0.6174 0.7813 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] toilet : 0.7632 0.9310 0.9810 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] sink : 0.2480 0.5390 0.7892 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] bathtub : 0.6188 0.8065 0.8710 +[2025-02-22 11:25:27,756 INFO evaluator.py line 547 2775932] otherfurniture : 0.3097 0.4919 0.6252 +[2025-02-22 11:25:27,756 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:25:27,756 INFO evaluator.py line 554 2775932] average : 0.3038 0.4962 0.6686 +[2025-02-22 11:25:27,756 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:25:27,756 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:25:27,798 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.4962 +[2025-02-22 11:25:27,800 INFO misc.py line 164 2775932] Currently Best AP50: 0.4962 +[2025-02-22 11:25:27,800 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:25:37,233 INFO hook.py line 109 2775932] Train: [17/100][50/800] Data 0.003 (0.008) Batch 0.137 (0.151) Remain 02:48:42 loss: -0.5185 Lr: 5.80172e-03 +[2025-02-22 11:25:44,466 INFO hook.py line 109 2775932] Train: [17/100][100/800] Data 0.003 (0.005) Batch 0.162 (0.148) Remain 02:45:03 loss: -0.4163 Lr: 5.79950e-03 +[2025-02-22 11:25:51,722 INFO hook.py line 109 2775932] Train: [17/100][150/800] Data 0.003 (0.005) Batch 0.153 (0.147) Remain 02:44:00 loss: -0.2770 Lr: 5.79727e-03 +[2025-02-22 11:25:59,147 INFO hook.py line 109 2775932] Train: [17/100][200/800] Data 0.003 (0.005) Batch 0.150 (0.147) Remain 02:44:22 loss: -0.2247 Lr: 5.79502e-03 +[2025-02-22 11:26:06,534 INFO hook.py line 109 2775932] Train: [17/100][250/800] Data 0.004 (0.005) Batch 0.140 (0.147) Remain 02:44:22 loss: 0.1541 Lr: 5.79276e-03 +[2025-02-22 11:26:13,725 INFO hook.py line 109 2775932] Train: [17/100][300/800] Data 0.003 (0.004) Batch 0.143 (0.147) Remain 02:43:35 loss: -0.2991 Lr: 5.79049e-03 +[2025-02-22 11:26:20,863 INFO hook.py line 109 2775932] Train: [17/100][350/800] Data 0.002 (0.004) Batch 0.141 (0.146) Remain 02:42:50 loss: -0.4645 Lr: 5.78821e-03 +[2025-02-22 11:26:28,257 INFO hook.py line 109 2775932] Train: [17/100][400/800] Data 0.002 (0.004) Batch 0.123 (0.146) Remain 02:42:57 loss: -0.2199 Lr: 5.78591e-03 +[2025-02-22 11:26:35,548 INFO hook.py line 109 2775932] Train: [17/100][450/800] Data 0.002 (0.004) Batch 0.128 (0.146) Remain 02:42:46 loss: 0.0411 Lr: 5.78361e-03 +[2025-02-22 11:26:42,629 INFO hook.py line 109 2775932] Train: [17/100][500/800] Data 0.003 (0.004) Batch 0.215 (0.146) Remain 02:42:07 loss: -0.1834 Lr: 5.78129e-03 +[2025-02-22 11:26:50,116 INFO hook.py line 109 2775932] Train: [17/100][550/800] Data 0.003 (0.004) Batch 0.138 (0.146) Remain 02:42:23 loss: -0.4067 Lr: 5.77896e-03 +[2025-02-22 11:26:57,163 INFO hook.py line 109 2775932] Train: [17/100][600/800] Data 0.003 (0.004) Batch 0.129 (0.146) Remain 02:41:47 loss: -0.1377 Lr: 5.77662e-03 +[2025-02-22 11:27:04,328 INFO hook.py line 109 2775932] Train: [17/100][650/800] Data 0.003 (0.004) Batch 0.147 (0.146) Remain 02:41:27 loss: -0.1634 Lr: 5.77426e-03 +[2025-02-22 11:27:12,032 INFO hook.py line 109 2775932] Train: [17/100][700/800] Data 0.003 (0.004) Batch 0.173 (0.146) Remain 02:42:00 loss: -0.3297 Lr: 5.77190e-03 +[2025-02-22 11:27:19,114 INFO hook.py line 109 2775932] Train: [17/100][750/800] Data 0.003 (0.004) Batch 0.138 (0.146) Remain 02:41:33 loss: -0.1848 Lr: 5.76952e-03 +[2025-02-22 11:27:26,194 INFO hook.py line 109 2775932] Train: [17/100][800/800] Data 0.002 (0.004) Batch 0.118 (0.146) Remain 02:41:08 loss: -0.5099 Lr: 5.76713e-03 +[2025-02-22 11:27:26,195 INFO misc.py line 135 2775932] Train result: loss: -0.2738 seg_loss: 0.3279 bias_l1_loss: 0.3055 bias_cosine_loss: -0.9072 +[2025-02-22 11:27:26,195 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:27:33,636 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7188 +[2025-02-22 11:27:33,885 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0887 +[2025-02-22 11:27:33,955 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3446 +[2025-02-22 11:27:34,022 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3380 +[2025-02-22 11:27:34,086 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4836 +[2025-02-22 11:27:34,145 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5952 +[2025-02-22 11:27:34,429 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3542 +[2025-02-22 11:27:34,459 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3591 +[2025-02-22 11:27:34,593 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0090 +[2025-02-22 11:27:34,648 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0441 +[2025-02-22 11:27:34,915 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2384 +[2025-02-22 11:27:35,028 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0219 +[2025-02-22 11:27:35,097 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.0517 +[2025-02-22 11:27:35,209 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8968 +[2025-02-22 11:27:35,298 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8446 +[2025-02-22 11:27:35,374 INFO evaluator.py line 595 2775932] Test: [16/78] Loss 0.4086 +[2025-02-22 11:27:35,519 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.1633 +[2025-02-22 11:27:35,616 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.0798 +[2025-02-22 11:27:35,784 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1092 +[2025-02-22 11:27:35,844 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0510 +[2025-02-22 11:27:35,992 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5627 +[2025-02-22 11:27:36,199 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.5667 +[2025-02-22 11:27:36,285 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1411 +[2025-02-22 11:27:36,353 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0224 +[2025-02-22 11:27:36,432 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1568 +[2025-02-22 11:27:36,532 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5010 +[2025-02-22 11:27:36,712 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2855 +[2025-02-22 11:27:36,817 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7726 +[2025-02-22 11:27:36,902 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4959 +[2025-02-22 11:27:36,995 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6001 +[2025-02-22 11:27:37,801 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3990 +[2025-02-22 11:27:37,923 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4478 +[2025-02-22 11:27:37,960 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7071 +[2025-02-22 11:27:38,065 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0398 +[2025-02-22 11:27:38,101 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6758 +[2025-02-22 11:27:38,223 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8817 +[2025-02-22 11:27:38,309 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6094 +[2025-02-22 11:27:38,437 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5495 +[2025-02-22 11:27:38,581 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5806 +[2025-02-22 11:27:38,760 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1806 +[2025-02-22 11:27:38,909 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.2953 +[2025-02-22 11:27:38,952 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1449 +[2025-02-22 11:27:38,987 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6359 +[2025-02-22 11:27:39,244 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.3916 +[2025-02-22 11:27:39,295 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4179 +[2025-02-22 11:27:39,341 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3650 +[2025-02-22 11:27:39,459 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1894 +[2025-02-22 11:27:39,573 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2301 +[2025-02-22 11:27:39,677 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0372 +[2025-02-22 11:27:39,762 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1546 +[2025-02-22 11:27:39,828 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0051 +[2025-02-22 11:27:39,974 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.0844 +[2025-02-22 11:27:40,026 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7675 +[2025-02-22 11:27:40,130 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0729 +[2025-02-22 11:27:40,222 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7971 +[2025-02-22 11:27:40,399 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7598 +[2025-02-22 11:27:40,526 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0314 +[2025-02-22 11:27:40,571 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2063 +[2025-02-22 11:27:40,815 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3511 +[2025-02-22 11:27:40,914 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1161 +[2025-02-22 11:27:40,980 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7059 +[2025-02-22 11:27:41,034 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6192 +[2025-02-22 11:27:41,193 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0013 +[2025-02-22 11:27:41,311 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4948 +[2025-02-22 11:27:41,388 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2942 +[2025-02-22 11:27:41,509 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1895 +[2025-02-22 11:27:41,676 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5093 +[2025-02-22 11:27:41,754 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0972 +[2025-02-22 11:27:41,804 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7234 +[2025-02-22 11:27:41,858 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0012 +[2025-02-22 11:27:41,999 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0987 +[2025-02-22 11:27:42,055 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3068 +[2025-02-22 11:27:42,110 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5744 +[2025-02-22 11:27:42,204 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.8363 +[2025-02-22 11:27:42,395 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4410 +[2025-02-22 11:27:42,477 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0727 +[2025-02-22 11:27:42,633 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3402 +[2025-02-22 11:27:42,723 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4131 +[2025-02-22 11:27:54,635 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:27:54,636 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:27:54,636 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] cabinet : 0.2117 0.4591 0.6935 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] bed : 0.2978 0.5816 0.7576 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] chair : 0.6705 0.8285 0.8839 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] sofa : 0.3405 0.5932 0.7473 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] table : 0.3043 0.4893 0.6121 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] door : 0.2317 0.4329 0.5667 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] window : 0.1366 0.2878 0.4871 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] bookshelf : 0.1902 0.4851 0.7596 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] picture : 0.1903 0.2875 0.3843 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] counter : 0.0393 0.1276 0.5139 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] desk : 0.1415 0.4114 0.7737 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] curtain : 0.2442 0.4198 0.6130 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] refridgerator : 0.2880 0.3860 0.4497 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] shower curtain : 0.4369 0.6863 0.8357 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] toilet : 0.8673 1.0000 1.0000 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] sink : 0.2704 0.5302 0.8340 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] bathtub : 0.5115 0.7254 0.8481 +[2025-02-22 11:27:54,636 INFO evaluator.py line 547 2775932] otherfurniture : 0.3633 0.5363 0.6337 +[2025-02-22 11:27:54,636 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:27:54,636 INFO evaluator.py line 554 2775932] average : 0.3187 0.5149 0.6886 +[2025-02-22 11:27:54,636 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:27:54,636 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:27:54,672 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5149 +[2025-02-22 11:27:54,674 INFO misc.py line 164 2775932] Currently Best AP50: 0.5149 +[2025-02-22 11:27:54,674 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:28:04,429 INFO hook.py line 109 2775932] Train: [18/100][50/800] Data 0.002 (0.007) Batch 0.142 (0.151) Remain 02:46:58 loss: -0.2912 Lr: 5.76473e-03 +[2025-02-22 11:28:11,556 INFO hook.py line 109 2775932] Train: [18/100][100/800] Data 0.003 (0.005) Batch 0.149 (0.147) Remain 02:42:02 loss: -0.3231 Lr: 5.76232e-03 +[2025-02-22 11:28:18,521 INFO hook.py line 109 2775932] Train: [18/100][150/800] Data 0.003 (0.004) Batch 0.132 (0.144) Remain 02:39:09 loss: -0.3284 Lr: 5.75994e-03 +[2025-02-22 11:28:25,732 INFO hook.py line 109 2775932] Train: [18/100][200/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 02:39:03 loss: 0.0259 Lr: 5.75751e-03 +[2025-02-22 11:28:32,883 INFO hook.py line 109 2775932] Train: [18/100][250/800] Data 0.002 (0.004) Batch 0.143 (0.144) Remain 02:38:41 loss: -0.3523 Lr: 5.75506e-03 +[2025-02-22 11:28:40,280 INFO hook.py line 109 2775932] Train: [18/100][300/800] Data 0.002 (0.004) Batch 0.138 (0.145) Remain 02:39:18 loss: -0.3459 Lr: 5.75260e-03 +[2025-02-22 11:28:47,300 INFO hook.py line 109 2775932] Train: [18/100][350/800] Data 0.004 (0.003) Batch 0.148 (0.144) Remain 02:38:31 loss: -0.3532 Lr: 5.75013e-03 +[2025-02-22 11:28:54,773 INFO hook.py line 109 2775932] Train: [18/100][400/800] Data 0.003 (0.004) Batch 0.165 (0.145) Remain 02:39:09 loss: -0.5740 Lr: 5.74764e-03 +[2025-02-22 11:29:01,911 INFO hook.py line 109 2775932] Train: [18/100][450/800] Data 0.002 (0.004) Batch 0.160 (0.144) Remain 02:38:47 loss: -0.1305 Lr: 5.74515e-03 +[2025-02-22 11:29:08,955 INFO hook.py line 109 2775932] Train: [18/100][500/800] Data 0.006 (0.004) Batch 0.143 (0.144) Remain 02:38:16 loss: -0.0516 Lr: 5.74264e-03 +[2025-02-22 11:29:16,362 INFO hook.py line 109 2775932] Train: [18/100][550/800] Data 0.002 (0.004) Batch 0.151 (0.144) Remain 02:38:33 loss: -0.3147 Lr: 5.74012e-03 +[2025-02-22 11:29:23,578 INFO hook.py line 109 2775932] Train: [18/100][600/800] Data 0.002 (0.004) Batch 0.159 (0.144) Remain 02:38:25 loss: -0.2311 Lr: 5.73759e-03 +[2025-02-22 11:29:30,643 INFO hook.py line 109 2775932] Train: [18/100][650/800] Data 0.003 (0.004) Batch 0.130 (0.144) Remain 02:38:02 loss: -0.2637 Lr: 5.73505e-03 +[2025-02-22 11:29:37,945 INFO hook.py line 109 2775932] Train: [18/100][700/800] Data 0.003 (0.004) Batch 0.160 (0.144) Remain 02:38:03 loss: -0.1314 Lr: 5.73250e-03 +[2025-02-22 11:29:45,046 INFO hook.py line 109 2775932] Train: [18/100][750/800] Data 0.002 (0.004) Batch 0.131 (0.144) Remain 02:37:46 loss: 0.0215 Lr: 5.72993e-03 +[2025-02-22 11:29:51,944 INFO hook.py line 109 2775932] Train: [18/100][800/800] Data 0.003 (0.004) Batch 0.111 (0.144) Remain 02:37:13 loss: -0.5790 Lr: 5.72736e-03 +[2025-02-22 11:29:51,944 INFO misc.py line 135 2775932] Train result: loss: -0.2927 seg_loss: 0.3217 bias_l1_loss: 0.2956 bias_cosine_loss: -0.9100 +[2025-02-22 11:29:51,945 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:29:59,034 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6765 +[2025-02-22 11:29:59,233 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2005 +[2025-02-22 11:29:59,312 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4336 +[2025-02-22 11:29:59,442 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5076 +[2025-02-22 11:29:59,519 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5403 +[2025-02-22 11:29:59,830 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9079 +[2025-02-22 11:30:00,121 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3282 +[2025-02-22 11:30:00,155 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5237 +[2025-02-22 11:30:00,309 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0750 +[2025-02-22 11:30:00,364 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.4064 +[2025-02-22 11:30:00,589 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0640 +[2025-02-22 11:30:00,697 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2499 +[2025-02-22 11:30:00,776 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5412 +[2025-02-22 11:30:00,871 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8183 +[2025-02-22 11:30:00,952 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6463 +[2025-02-22 11:30:01,032 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5594 +[2025-02-22 11:30:01,160 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4437 +[2025-02-22 11:30:01,258 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1566 +[2025-02-22 11:30:01,411 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2222 +[2025-02-22 11:30:01,468 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.3249 +[2025-02-22 11:30:01,616 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6042 +[2025-02-22 11:30:01,793 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2010 +[2025-02-22 11:30:01,864 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0103 +[2025-02-22 11:30:01,915 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0024 +[2025-02-22 11:30:01,984 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2964 +[2025-02-22 11:30:02,045 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4206 +[2025-02-22 11:30:02,179 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3015 +[2025-02-22 11:30:02,284 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8860 +[2025-02-22 11:30:02,380 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5377 +[2025-02-22 11:30:02,459 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5899 +[2025-02-22 11:30:03,355 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4397 +[2025-02-22 11:30:03,480 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4839 +[2025-02-22 11:30:03,526 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6427 +[2025-02-22 11:30:03,626 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2831 +[2025-02-22 11:30:03,665 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4444 +[2025-02-22 11:30:03,793 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1145 +[2025-02-22 11:30:03,859 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5295 +[2025-02-22 11:30:03,991 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5726 +[2025-02-22 11:30:04,158 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8239 +[2025-02-22 11:30:04,347 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8539 +[2025-02-22 11:30:04,500 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4303 +[2025-02-22 11:30:04,556 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0707 +[2025-02-22 11:30:04,598 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6281 +[2025-02-22 11:30:04,871 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5402 +[2025-02-22 11:30:04,917 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2679 +[2025-02-22 11:30:04,971 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5063 +[2025-02-22 11:30:05,072 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2983 +[2025-02-22 11:30:05,222 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0104 +[2025-02-22 11:30:05,351 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0509 +[2025-02-22 11:30:05,432 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4301 +[2025-02-22 11:30:05,509 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.4925 +[2025-02-22 11:30:05,629 INFO evaluator.py line 595 2775932] Test: [52/78] Loss 0.0664 +[2025-02-22 11:30:05,679 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5988 +[2025-02-22 11:30:05,774 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2729 +[2025-02-22 11:30:05,865 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7643 +[2025-02-22 11:30:05,914 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7705 +[2025-02-22 11:30:06,037 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1567 +[2025-02-22 11:30:06,078 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0996 +[2025-02-22 11:30:06,291 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2143 +[2025-02-22 11:30:06,399 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0840 +[2025-02-22 11:30:06,465 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7930 +[2025-02-22 11:30:06,523 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3937 +[2025-02-22 11:30:06,661 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3476 +[2025-02-22 11:30:06,781 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6214 +[2025-02-22 11:30:06,846 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4539 +[2025-02-22 11:30:06,958 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1776 +[2025-02-22 11:30:07,113 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3284 +[2025-02-22 11:30:07,193 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2885 +[2025-02-22 11:30:07,243 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6833 +[2025-02-22 11:30:07,291 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2380 +[2025-02-22 11:30:07,430 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1230 +[2025-02-22 11:30:07,466 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5310 +[2025-02-22 11:30:07,520 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5509 +[2025-02-22 11:30:07,611 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.1914 +[2025-02-22 11:30:07,819 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4898 +[2025-02-22 11:30:07,892 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0960 +[2025-02-22 11:30:08,053 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4541 +[2025-02-22 11:30:08,135 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3566 +[2025-02-22 11:30:19,690 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:30:19,690 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:30:19,690 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:30:19,690 INFO evaluator.py line 547 2775932] cabinet : 0.2005 0.4156 0.6647 +[2025-02-22 11:30:19,690 INFO evaluator.py line 547 2775932] bed : 0.3405 0.7031 0.8594 +[2025-02-22 11:30:19,690 INFO evaluator.py line 547 2775932] chair : 0.7235 0.8840 0.9323 +[2025-02-22 11:30:19,690 INFO evaluator.py line 547 2775932] sofa : 0.3232 0.5688 0.8104 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] table : 0.3287 0.5760 0.7309 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] door : 0.2016 0.4054 0.5303 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] window : 0.1324 0.2984 0.5180 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] bookshelf : 0.1461 0.4048 0.5625 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] picture : 0.2377 0.3661 0.4488 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] counter : 0.0635 0.1980 0.5237 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] desk : 0.0771 0.2580 0.7060 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] curtain : 0.2282 0.3999 0.5515 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] refridgerator : 0.3051 0.4881 0.5088 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] shower curtain : 0.3848 0.6303 0.7576 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] toilet : 0.7849 0.9474 0.9997 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] sink : 0.2308 0.4459 0.8179 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] bathtub : 0.6071 0.7742 0.8710 +[2025-02-22 11:30:19,691 INFO evaluator.py line 547 2775932] otherfurniture : 0.3505 0.5281 0.6584 +[2025-02-22 11:30:19,691 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:30:19,691 INFO evaluator.py line 554 2775932] average : 0.3148 0.5162 0.6918 +[2025-02-22 11:30:19,691 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:30:19,691 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:30:19,732 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5162 +[2025-02-22 11:30:19,734 INFO misc.py line 164 2775932] Currently Best AP50: 0.5162 +[2025-02-22 11:30:19,734 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:30:28,610 INFO hook.py line 109 2775932] Train: [19/100][50/800] Data 0.002 (0.003) Batch 0.133 (0.144) Remain 02:37:45 loss: -0.3648 Lr: 5.72477e-03 +[2025-02-22 11:30:35,930 INFO hook.py line 109 2775932] Train: [19/100][100/800] Data 0.003 (0.003) Batch 0.139 (0.145) Remain 02:38:45 loss: -0.0658 Lr: 5.72217e-03 +[2025-02-22 11:30:43,320 INFO hook.py line 109 2775932] Train: [19/100][150/800] Data 0.003 (0.005) Batch 0.138 (0.146) Remain 02:39:30 loss: -0.3185 Lr: 5.71956e-03 +[2025-02-22 11:30:50,325 INFO hook.py line 109 2775932] Train: [19/100][200/800] Data 0.003 (0.004) Batch 0.155 (0.145) Remain 02:37:41 loss: -0.2320 Lr: 5.71693e-03 +[2025-02-22 11:30:57,665 INFO hook.py line 109 2775932] Train: [19/100][250/800] Data 0.003 (0.005) Batch 0.137 (0.145) Remain 02:38:02 loss: -0.3844 Lr: 5.71430e-03 +[2025-02-22 11:31:04,922 INFO hook.py line 109 2775932] Train: [19/100][300/800] Data 0.002 (0.005) Batch 0.134 (0.145) Remain 02:37:55 loss: -0.2764 Lr: 5.71165e-03 +[2025-02-22 11:31:12,535 INFO hook.py line 109 2775932] Train: [19/100][350/800] Data 0.003 (0.004) Batch 0.116 (0.146) Remain 02:38:55 loss: -0.2435 Lr: 5.70899e-03 +[2025-02-22 11:31:19,866 INFO hook.py line 109 2775932] Train: [19/100][400/800] Data 0.003 (0.004) Batch 0.161 (0.146) Remain 02:38:52 loss: -0.3551 Lr: 5.70632e-03 +[2025-02-22 11:31:27,083 INFO hook.py line 109 2775932] Train: [19/100][450/800] Data 0.003 (0.004) Batch 0.139 (0.146) Remain 02:38:31 loss: -0.0199 Lr: 5.70364e-03 +[2025-02-22 11:31:34,154 INFO hook.py line 109 2775932] Train: [19/100][500/800] Data 0.002 (0.004) Batch 0.150 (0.146) Remain 02:37:54 loss: -0.3315 Lr: 5.70095e-03 +[2025-02-22 11:31:41,370 INFO hook.py line 109 2775932] Train: [19/100][550/800] Data 0.002 (0.004) Batch 0.133 (0.145) Remain 02:37:39 loss: 0.0551 Lr: 5.69825e-03 +[2025-02-22 11:31:48,452 INFO hook.py line 109 2775932] Train: [19/100][600/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 02:37:11 loss: -0.0883 Lr: 5.69553e-03 +[2025-02-22 11:31:55,870 INFO hook.py line 109 2775932] Train: [19/100][650/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 02:37:20 loss: -0.1786 Lr: 5.69280e-03 +[2025-02-22 11:32:03,097 INFO hook.py line 109 2775932] Train: [19/100][700/800] Data 0.003 (0.004) Batch 0.153 (0.145) Remain 02:37:09 loss: -0.4933 Lr: 5.69006e-03 +[2025-02-22 11:32:10,323 INFO hook.py line 109 2775932] Train: [19/100][750/800] Data 0.002 (0.004) Batch 0.140 (0.145) Remain 02:36:59 loss: -0.1576 Lr: 5.68731e-03 +[2025-02-22 11:32:17,016 INFO hook.py line 109 2775932] Train: [19/100][800/800] Data 0.002 (0.003) Batch 0.113 (0.145) Remain 02:36:05 loss: -0.2686 Lr: 5.68455e-03 +[2025-02-22 11:32:17,017 INFO misc.py line 135 2775932] Train result: loss: -0.2853 seg_loss: 0.3239 bias_l1_loss: 0.2992 bias_cosine_loss: -0.9084 +[2025-02-22 11:32:17,017 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:32:24,139 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6898 +[2025-02-22 11:32:24,407 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3433 +[2025-02-22 11:32:24,787 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3897 +[2025-02-22 11:32:24,872 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4308 +[2025-02-22 11:32:24,950 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5036 +[2025-02-22 11:32:25,007 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5968 +[2025-02-22 11:32:25,272 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3932 +[2025-02-22 11:32:25,307 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4465 +[2025-02-22 11:32:25,444 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1804 +[2025-02-22 11:32:25,499 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3849 +[2025-02-22 11:32:25,771 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3665 +[2025-02-22 11:32:25,877 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0813 +[2025-02-22 11:32:25,959 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0050 +[2025-02-22 11:32:26,054 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1361 +[2025-02-22 11:32:26,135 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.9094 +[2025-02-22 11:32:26,218 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4926 +[2025-02-22 11:32:26,367 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4375 +[2025-02-22 11:32:26,467 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1705 +[2025-02-22 11:32:26,630 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1882 +[2025-02-22 11:32:26,699 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0856 +[2025-02-22 11:32:26,862 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6035 +[2025-02-22 11:32:27,081 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1147 +[2025-02-22 11:32:27,152 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1227 +[2025-02-22 11:32:27,210 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1045 +[2025-02-22 11:32:27,264 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0206 +[2025-02-22 11:32:27,321 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4336 +[2025-02-22 11:32:27,475 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1347 +[2025-02-22 11:32:27,562 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8602 +[2025-02-22 11:32:27,636 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5786 +[2025-02-22 11:32:27,705 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4415 +[2025-02-22 11:32:28,585 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3067 +[2025-02-22 11:32:28,700 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3094 +[2025-02-22 11:32:28,735 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6569 +[2025-02-22 11:32:28,821 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1567 +[2025-02-22 11:32:28,860 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5566 +[2025-02-22 11:32:28,971 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1347 +[2025-02-22 11:32:29,041 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4723 +[2025-02-22 11:32:29,167 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6017 +[2025-02-22 11:32:29,323 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5027 +[2025-02-22 11:32:29,518 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6390 +[2025-02-22 11:32:29,675 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1881 +[2025-02-22 11:32:29,724 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1395 +[2025-02-22 11:32:29,761 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6205 +[2025-02-22 11:32:30,005 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4259 +[2025-02-22 11:32:30,053 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3447 +[2025-02-22 11:32:30,101 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4059 +[2025-02-22 11:32:30,214 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4302 +[2025-02-22 11:32:30,336 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2169 +[2025-02-22 11:32:30,448 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3751 +[2025-02-22 11:32:30,545 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0954 +[2025-02-22 11:32:30,614 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.3888 +[2025-02-22 11:32:30,738 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2160 +[2025-02-22 11:32:30,778 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6930 +[2025-02-22 11:32:30,886 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.6762 +[2025-02-22 11:32:30,971 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7115 +[2025-02-22 11:32:31,018 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7492 +[2025-02-22 11:32:31,152 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1120 +[2025-02-22 11:32:31,193 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1917 +[2025-02-22 11:32:31,411 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4171 +[2025-02-22 11:32:31,522 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1491 +[2025-02-22 11:32:31,602 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.1375 +[2025-02-22 11:32:31,652 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4378 +[2025-02-22 11:32:31,823 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1765 +[2025-02-22 11:32:31,937 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5303 +[2025-02-22 11:32:32,011 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1518 +[2025-02-22 11:32:32,132 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2591 +[2025-02-22 11:32:32,322 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.1664 +[2025-02-22 11:32:32,411 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1565 +[2025-02-22 11:32:32,465 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6390 +[2025-02-22 11:32:32,515 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1438 +[2025-02-22 11:32:32,656 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0009 +[2025-02-22 11:32:32,696 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4942 +[2025-02-22 11:32:32,745 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6784 +[2025-02-22 11:32:32,849 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8129 +[2025-02-22 11:32:33,067 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5160 +[2025-02-22 11:32:33,146 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.3140 +[2025-02-22 11:32:33,308 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4729 +[2025-02-22 11:32:33,415 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5263 +[2025-02-22 11:32:45,894 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:32:45,895 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:32:45,895 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] cabinet : 0.1755 0.3766 0.6312 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] bed : 0.3275 0.6625 0.8189 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] chair : 0.7099 0.8691 0.9150 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] sofa : 0.2599 0.4910 0.7641 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] table : 0.3250 0.5680 0.7020 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] door : 0.1724 0.3617 0.5094 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] window : 0.0806 0.1778 0.3370 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] bookshelf : 0.2267 0.5547 0.6709 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] picture : 0.2416 0.4032 0.4593 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] counter : 0.0232 0.0956 0.6358 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] desk : 0.0948 0.2605 0.6673 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] curtain : 0.2108 0.4474 0.6075 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] refridgerator : 0.3644 0.5164 0.5922 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] shower curtain : 0.3807 0.5426 0.7820 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] toilet : 0.7973 0.9741 0.9741 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] sink : 0.2491 0.4477 0.8034 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] bathtub : 0.6338 0.8065 0.8065 +[2025-02-22 11:32:45,895 INFO evaluator.py line 547 2775932] otherfurniture : 0.3523 0.5441 0.6884 +[2025-02-22 11:32:45,895 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:32:45,895 INFO evaluator.py line 554 2775932] average : 0.3125 0.5055 0.6869 +[2025-02-22 11:32:45,895 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:32:45,895 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:32:45,944 INFO misc.py line 164 2775932] Currently Best AP50: 0.5162 +[2025-02-22 11:32:45,946 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:32:54,775 INFO hook.py line 109 2775932] Train: [20/100][50/800] Data 0.003 (0.003) Batch 0.163 (0.147) Remain 02:38:07 loss: -0.4899 Lr: 5.68178e-03 +[2025-02-22 11:33:01,942 INFO hook.py line 109 2775932] Train: [20/100][100/800] Data 0.003 (0.003) Batch 0.141 (0.145) Remain 02:36:14 loss: -0.0356 Lr: 5.67899e-03 +[2025-02-22 11:33:09,334 INFO hook.py line 109 2775932] Train: [20/100][150/800] Data 0.002 (0.004) Batch 0.136 (0.146) Remain 02:37:11 loss: -0.3035 Lr: 5.67620e-03 +[2025-02-22 11:33:16,470 INFO hook.py line 109 2775932] Train: [20/100][200/800] Data 0.003 (0.004) Batch 0.147 (0.145) Remain 02:36:12 loss: -0.3362 Lr: 5.67339e-03 +[2025-02-22 11:33:23,573 INFO hook.py line 109 2775932] Train: [20/100][250/800] Data 0.002 (0.004) Batch 0.129 (0.144) Remain 02:35:25 loss: -0.2351 Lr: 5.67057e-03 +[2025-02-22 11:33:30,801 INFO hook.py line 109 2775932] Train: [20/100][300/800] Data 0.002 (0.004) Batch 0.138 (0.144) Remain 02:35:19 loss: -0.0438 Lr: 5.66774e-03 +[2025-02-22 11:33:37,831 INFO hook.py line 109 2775932] Train: [20/100][350/800] Data 0.002 (0.004) Batch 0.114 (0.144) Remain 02:34:36 loss: -0.2447 Lr: 5.66490e-03 +[2025-02-22 11:33:44,929 INFO hook.py line 109 2775932] Train: [20/100][400/800] Data 0.004 (0.004) Batch 0.162 (0.144) Remain 02:34:12 loss: -0.1748 Lr: 5.66205e-03 +[2025-02-22 11:33:51,865 INFO hook.py line 109 2775932] Train: [20/100][450/800] Data 0.002 (0.004) Batch 0.119 (0.143) Remain 02:33:29 loss: 0.0418 Lr: 5.65918e-03 +[2025-02-22 11:33:58,968 INFO hook.py line 109 2775932] Train: [20/100][500/800] Data 0.003 (0.003) Batch 0.143 (0.143) Remain 02:33:15 loss: -0.4398 Lr: 5.65630e-03 +[2025-02-22 11:34:06,153 INFO hook.py line 109 2775932] Train: [20/100][550/800] Data 0.002 (0.003) Batch 0.154 (0.143) Remain 02:33:12 loss: 0.0562 Lr: 5.65342e-03 +[2025-02-22 11:34:13,816 INFO hook.py line 109 2775932] Train: [20/100][600/800] Data 0.003 (0.003) Batch 0.125 (0.144) Remain 02:34:00 loss: -0.3837 Lr: 5.65052e-03 +[2025-02-22 11:34:21,070 INFO hook.py line 109 2775932] Train: [20/100][650/800] Data 0.002 (0.003) Batch 0.141 (0.144) Remain 02:33:58 loss: 0.0007 Lr: 5.64761e-03 +[2025-02-22 11:34:28,097 INFO hook.py line 109 2775932] Train: [20/100][700/800] Data 0.004 (0.003) Batch 0.138 (0.144) Remain 02:33:35 loss: -0.3543 Lr: 5.64469e-03 +[2025-02-22 11:34:35,203 INFO hook.py line 109 2775932] Train: [20/100][750/800] Data 0.003 (0.003) Batch 0.145 (0.144) Remain 02:33:21 loss: -0.4174 Lr: 5.64176e-03 +[2025-02-22 11:34:42,169 INFO hook.py line 109 2775932] Train: [20/100][800/800] Data 0.002 (0.003) Batch 0.113 (0.143) Remain 02:32:56 loss: -0.3477 Lr: 5.63881e-03 +[2025-02-22 11:34:42,169 INFO misc.py line 135 2775932] Train result: loss: -0.2966 seg_loss: 0.3161 bias_l1_loss: 0.2972 bias_cosine_loss: -0.9099 +[2025-02-22 11:34:42,171 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:34:49,810 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6955 +[2025-02-22 11:34:49,996 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2900 +[2025-02-22 11:34:50,064 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4336 +[2025-02-22 11:34:50,138 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5093 +[2025-02-22 11:34:50,398 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4896 +[2025-02-22 11:34:50,453 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7737 +[2025-02-22 11:34:50,733 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3191 +[2025-02-22 11:34:50,764 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4468 +[2025-02-22 11:34:50,921 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1113 +[2025-02-22 11:34:50,977 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1616 +[2025-02-22 11:34:51,253 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2145 +[2025-02-22 11:34:51,391 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0182 +[2025-02-22 11:34:51,470 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.2652 +[2025-02-22 11:34:51,557 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9332 +[2025-02-22 11:34:51,637 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3262 +[2025-02-22 11:34:51,712 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.2104 +[2025-02-22 11:34:51,865 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.1726 +[2025-02-22 11:34:51,963 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0267 +[2025-02-22 11:34:52,117 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1006 +[2025-02-22 11:34:52,212 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2824 +[2025-02-22 11:34:52,383 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5440 +[2025-02-22 11:34:52,582 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2716 +[2025-02-22 11:34:52,660 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0389 +[2025-02-22 11:34:52,725 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1457 +[2025-02-22 11:34:52,789 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3922 +[2025-02-22 11:34:52,854 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4000 +[2025-02-22 11:34:53,009 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0502 +[2025-02-22 11:34:53,106 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7835 +[2025-02-22 11:34:53,184 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5550 +[2025-02-22 11:34:53,256 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6008 +[2025-02-22 11:34:54,192 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3445 +[2025-02-22 11:34:54,328 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5514 +[2025-02-22 11:34:54,396 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6212 +[2025-02-22 11:34:54,527 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2907 +[2025-02-22 11:34:54,576 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5608 +[2025-02-22 11:34:54,698 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.5023 +[2025-02-22 11:34:54,784 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5683 +[2025-02-22 11:34:54,950 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5249 +[2025-02-22 11:34:55,139 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4928 +[2025-02-22 11:34:55,348 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7862 +[2025-02-22 11:34:55,517 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1453 +[2025-02-22 11:34:55,566 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0446 +[2025-02-22 11:34:55,609 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6438 +[2025-02-22 11:34:55,889 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5188 +[2025-02-22 11:34:55,931 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3587 +[2025-02-22 11:34:55,986 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5541 +[2025-02-22 11:34:56,077 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3176 +[2025-02-22 11:34:56,197 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0305 +[2025-02-22 11:34:56,305 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1343 +[2025-02-22 11:34:56,406 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1186 +[2025-02-22 11:34:56,491 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1819 +[2025-02-22 11:34:56,626 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2091 +[2025-02-22 11:34:56,671 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5050 +[2025-02-22 11:34:56,786 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8746 +[2025-02-22 11:34:56,885 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7401 +[2025-02-22 11:34:56,932 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6236 +[2025-02-22 11:34:57,091 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.2783 +[2025-02-22 11:34:57,161 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2922 +[2025-02-22 11:34:57,395 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3475 +[2025-02-22 11:34:57,511 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0086 +[2025-02-22 11:34:57,580 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6513 +[2025-02-22 11:34:57,653 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3062 +[2025-02-22 11:34:57,804 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2624 +[2025-02-22 11:34:57,923 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6045 +[2025-02-22 11:34:57,998 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0072 +[2025-02-22 11:34:58,119 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1934 +[2025-02-22 11:34:58,305 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4511 +[2025-02-22 11:34:58,390 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1616 +[2025-02-22 11:34:58,439 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6581 +[2025-02-22 11:34:58,490 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2821 +[2025-02-22 11:34:58,643 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1608 +[2025-02-22 11:34:58,681 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5301 +[2025-02-22 11:34:58,730 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6291 +[2025-02-22 11:34:58,820 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8186 +[2025-02-22 11:34:59,037 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4735 +[2025-02-22 11:34:59,112 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1614 +[2025-02-22 11:34:59,255 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4148 +[2025-02-22 11:34:59,343 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6107 +[2025-02-22 11:35:11,493 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:35:11,493 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:35:11,493 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] cabinet : 0.2405 0.4725 0.6744 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] bed : 0.3904 0.7616 0.8733 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] chair : 0.6918 0.8547 0.9173 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] sofa : 0.3220 0.5878 0.8152 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] table : 0.3796 0.6330 0.7682 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] door : 0.1900 0.3816 0.5321 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] window : 0.1488 0.3294 0.5346 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] bookshelf : 0.2046 0.4844 0.7668 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] picture : 0.2644 0.4352 0.5502 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] counter : 0.0410 0.1589 0.5465 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] desk : 0.0902 0.2698 0.5435 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] curtain : 0.2472 0.4235 0.5809 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] refridgerator : 0.2616 0.3500 0.4306 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] shower curtain : 0.4447 0.5927 0.7075 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] toilet : 0.7943 0.9751 0.9913 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] sink : 0.2962 0.6339 0.8797 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] bathtub : 0.6235 0.8010 0.8986 +[2025-02-22 11:35:11,493 INFO evaluator.py line 547 2775932] otherfurniture : 0.3673 0.5512 0.6836 +[2025-02-22 11:35:11,493 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:35:11,493 INFO evaluator.py line 554 2775932] average : 0.3332 0.5387 0.7052 +[2025-02-22 11:35:11,493 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:35:11,494 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:35:11,542 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5387 +[2025-02-22 11:35:11,545 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:35:11,545 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:35:20,645 INFO hook.py line 109 2775932] Train: [21/100][50/800] Data 0.004 (0.004) Batch 0.135 (0.144) Remain 02:33:47 loss: -0.3586 Lr: 5.63592e-03 +[2025-02-22 11:35:27,661 INFO hook.py line 109 2775932] Train: [21/100][100/800] Data 0.003 (0.003) Batch 0.146 (0.142) Remain 02:31:29 loss: 0.2128 Lr: 5.63295e-03 +[2025-02-22 11:35:34,863 INFO hook.py line 109 2775932] Train: [21/100][150/800] Data 0.002 (0.003) Batch 0.137 (0.143) Remain 02:32:01 loss: -0.3169 Lr: 5.62997e-03 +[2025-02-22 11:35:42,068 INFO hook.py line 109 2775932] Train: [21/100][200/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 02:32:14 loss: -0.1147 Lr: 5.62698e-03 +[2025-02-22 11:35:49,215 INFO hook.py line 109 2775932] Train: [21/100][250/800] Data 0.002 (0.003) Batch 0.125 (0.143) Remain 02:32:04 loss: -0.0382 Lr: 5.62398e-03 +[2025-02-22 11:35:56,434 INFO hook.py line 109 2775932] Train: [21/100][300/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 02:32:10 loss: -0.3690 Lr: 5.62097e-03 +[2025-02-22 11:36:03,815 INFO hook.py line 109 2775932] Train: [21/100][350/800] Data 0.003 (0.003) Batch 0.245 (0.144) Remain 02:32:42 loss: 1.2379 Lr: 5.61795e-03 +[2025-02-22 11:36:10,861 INFO hook.py line 109 2775932] Train: [21/100][400/800] Data 0.003 (0.003) Batch 0.137 (0.144) Remain 02:32:10 loss: -0.3899 Lr: 5.61492e-03 +[2025-02-22 11:36:17,982 INFO hook.py line 109 2775932] Train: [21/100][450/800] Data 0.003 (0.003) Batch 0.128 (0.143) Remain 02:31:55 loss: -0.4448 Lr: 5.61187e-03 +[2025-02-22 11:36:25,363 INFO hook.py line 109 2775932] Train: [21/100][500/800] Data 0.002 (0.003) Batch 0.123 (0.144) Remain 02:32:15 loss: -0.1958 Lr: 5.60882e-03 +[2025-02-22 11:36:32,778 INFO hook.py line 109 2775932] Train: [21/100][550/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 02:32:33 loss: 0.0367 Lr: 5.60575e-03 +[2025-02-22 11:36:40,209 INFO hook.py line 109 2775932] Train: [21/100][600/800] Data 0.003 (0.003) Batch 0.153 (0.145) Remain 02:32:49 loss: -0.2440 Lr: 5.60267e-03 +[2025-02-22 11:36:47,268 INFO hook.py line 109 2775932] Train: [21/100][650/800] Data 0.002 (0.003) Batch 0.157 (0.144) Remain 02:32:25 loss: -0.3127 Lr: 5.59958e-03 +[2025-02-22 11:36:54,500 INFO hook.py line 109 2775932] Train: [21/100][700/800] Data 0.003 (0.003) Batch 0.147 (0.144) Remain 02:32:19 loss: -0.2573 Lr: 5.59648e-03 +[2025-02-22 11:37:01,748 INFO hook.py line 109 2775932] Train: [21/100][750/800] Data 0.002 (0.003) Batch 0.126 (0.144) Remain 02:32:14 loss: -0.4870 Lr: 5.59337e-03 +[2025-02-22 11:37:08,661 INFO hook.py line 109 2775932] Train: [21/100][800/800] Data 0.002 (0.003) Batch 0.110 (0.144) Remain 02:31:43 loss: -0.3683 Lr: 5.59025e-03 +[2025-02-22 11:37:08,662 INFO misc.py line 135 2775932] Train result: loss: -0.2938 seg_loss: 0.3126 bias_l1_loss: 0.3011 bias_cosine_loss: -0.9075 +[2025-02-22 11:37:08,662 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:37:15,941 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6538 +[2025-02-22 11:37:16,174 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2281 +[2025-02-22 11:37:16,243 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2427 +[2025-02-22 11:37:16,337 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5437 +[2025-02-22 11:37:16,408 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5284 +[2025-02-22 11:37:16,477 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9711 +[2025-02-22 11:37:16,776 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3370 +[2025-02-22 11:37:16,836 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5023 +[2025-02-22 11:37:16,999 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0430 +[2025-02-22 11:37:17,056 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3305 +[2025-02-22 11:37:17,295 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3748 +[2025-02-22 11:37:17,405 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2759 +[2025-02-22 11:37:17,487 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4846 +[2025-02-22 11:37:17,602 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9913 +[2025-02-22 11:37:17,685 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5251 +[2025-02-22 11:37:17,791 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5566 +[2025-02-22 11:37:17,946 INFO evaluator.py line 595 2775932] Test: [17/78] Loss 0.0640 +[2025-02-22 11:37:18,053 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2512 +[2025-02-22 11:37:18,211 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0014 +[2025-02-22 11:37:18,272 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0854 +[2025-02-22 11:37:18,428 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5979 +[2025-02-22 11:37:18,612 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3706 +[2025-02-22 11:37:18,685 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0630 +[2025-02-22 11:37:18,746 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1420 +[2025-02-22 11:37:18,817 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1963 +[2025-02-22 11:37:18,881 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3636 +[2025-02-22 11:37:19,028 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1592 +[2025-02-22 11:37:19,128 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7597 +[2025-02-22 11:37:19,216 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5366 +[2025-02-22 11:37:19,322 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3235 +[2025-02-22 11:37:20,188 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3890 +[2025-02-22 11:37:20,336 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3101 +[2025-02-22 11:37:20,398 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6415 +[2025-02-22 11:37:20,516 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1302 +[2025-02-22 11:37:20,561 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6248 +[2025-02-22 11:37:20,707 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1762 +[2025-02-22 11:37:20,788 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.3233 +[2025-02-22 11:37:20,929 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6273 +[2025-02-22 11:37:21,124 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2001 +[2025-02-22 11:37:21,331 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7758 +[2025-02-22 11:37:21,501 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1432 +[2025-02-22 11:37:21,550 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1271 +[2025-02-22 11:37:21,608 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6195 +[2025-02-22 11:37:21,851 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5945 +[2025-02-22 11:37:21,892 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2349 +[2025-02-22 11:37:21,933 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3345 +[2025-02-22 11:37:22,042 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2101 +[2025-02-22 11:37:22,159 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1435 +[2025-02-22 11:37:22,257 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3714 +[2025-02-22 11:37:22,343 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2000 +[2025-02-22 11:37:22,420 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2083 +[2025-02-22 11:37:22,550 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1676 +[2025-02-22 11:37:22,589 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6983 +[2025-02-22 11:37:22,692 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8372 +[2025-02-22 11:37:22,791 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7814 +[2025-02-22 11:37:22,836 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7328 +[2025-02-22 11:37:23,091 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0938 +[2025-02-22 11:37:23,133 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2336 +[2025-02-22 11:37:23,360 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2659 +[2025-02-22 11:37:23,456 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2112 +[2025-02-22 11:37:23,527 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7670 +[2025-02-22 11:37:23,581 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4448 +[2025-02-22 11:37:23,721 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1765 +[2025-02-22 11:37:23,821 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3778 +[2025-02-22 11:37:23,885 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0488 +[2025-02-22 11:37:24,011 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0359 +[2025-02-22 11:37:24,175 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6300 +[2025-02-22 11:37:24,256 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2524 +[2025-02-22 11:37:24,307 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7060 +[2025-02-22 11:37:24,357 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1680 +[2025-02-22 11:37:24,502 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0285 +[2025-02-22 11:37:24,538 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4914 +[2025-02-22 11:37:24,588 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6906 +[2025-02-22 11:37:24,687 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.9274 +[2025-02-22 11:37:24,874 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4921 +[2025-02-22 11:37:24,952 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1263 +[2025-02-22 11:37:25,123 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3256 +[2025-02-22 11:37:25,213 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6149 +[2025-02-22 11:37:37,345 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:37:37,345 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:37:37,345 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] cabinet : 0.1770 0.3727 0.6008 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] bed : 0.3399 0.7109 0.8395 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] chair : 0.7111 0.8701 0.9227 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] sofa : 0.3314 0.6030 0.8092 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] table : 0.3542 0.5625 0.7167 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] door : 0.2083 0.3975 0.5483 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] window : 0.1652 0.3182 0.5180 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] bookshelf : 0.1679 0.4866 0.6602 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] picture : 0.2356 0.3725 0.4251 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] counter : 0.0346 0.1507 0.5326 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] desk : 0.0210 0.0959 0.5549 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] curtain : 0.2148 0.3795 0.5512 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] refridgerator : 0.3228 0.4516 0.5230 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] shower curtain : 0.3933 0.5521 0.5521 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] toilet : 0.7990 0.9652 0.9828 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] sink : 0.2796 0.5319 0.8650 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] bathtub : 0.6016 0.7701 0.8710 +[2025-02-22 11:37:37,345 INFO evaluator.py line 547 2775932] otherfurniture : 0.3094 0.4980 0.6325 +[2025-02-22 11:37:37,345 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:37:37,345 INFO evaluator.py line 554 2775932] average : 0.3148 0.5049 0.6725 +[2025-02-22 11:37:37,345 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:37:37,345 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:37:37,387 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:37:37,390 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:37:46,198 INFO hook.py line 109 2775932] Train: [22/100][50/800] Data 0.003 (0.003) Batch 0.144 (0.146) Remain 02:33:59 loss: -0.1883 Lr: 5.58712e-03 +[2025-02-22 11:37:53,314 INFO hook.py line 109 2775932] Train: [22/100][100/800] Data 0.002 (0.003) Batch 0.140 (0.144) Remain 02:31:42 loss: -0.3647 Lr: 5.58397e-03 +[2025-02-22 11:38:00,609 INFO hook.py line 109 2775932] Train: [22/100][150/800] Data 0.003 (0.003) Batch 0.131 (0.145) Remain 02:32:10 loss: -0.3245 Lr: 5.58081e-03 +[2025-02-22 11:38:08,160 INFO hook.py line 109 2775932] Train: [22/100][200/800] Data 0.003 (0.005) Batch 0.132 (0.146) Remain 02:33:42 loss: -0.4347 Lr: 5.57765e-03 +[2025-02-22 11:38:15,366 INFO hook.py line 109 2775932] Train: [22/100][250/800] Data 0.004 (0.005) Batch 0.134 (0.146) Remain 02:33:06 loss: -0.1774 Lr: 5.57447e-03 +[2025-02-22 11:38:22,599 INFO hook.py line 109 2775932] Train: [22/100][300/800] Data 0.003 (0.004) Batch 0.145 (0.146) Remain 02:32:45 loss: -0.1873 Lr: 5.57128e-03 +[2025-02-22 11:38:29,554 INFO hook.py line 109 2775932] Train: [22/100][350/800] Data 0.004 (0.004) Batch 0.138 (0.145) Remain 02:31:38 loss: -0.2326 Lr: 5.56808e-03 +[2025-02-22 11:38:36,699 INFO hook.py line 109 2775932] Train: [22/100][400/800] Data 0.003 (0.004) Batch 0.171 (0.145) Remain 02:31:16 loss: -0.3336 Lr: 5.56487e-03 +[2025-02-22 11:38:43,684 INFO hook.py line 109 2775932] Train: [22/100][450/800] Data 0.003 (0.004) Batch 0.133 (0.144) Remain 02:30:35 loss: -0.1938 Lr: 5.56165e-03 +[2025-02-22 11:38:50,999 INFO hook.py line 109 2775932] Train: [22/100][500/800] Data 0.002 (0.004) Batch 0.138 (0.144) Remain 02:30:42 loss: -0.2896 Lr: 5.55842e-03 +[2025-02-22 11:38:58,414 INFO hook.py line 109 2775932] Train: [22/100][550/800] Data 0.003 (0.004) Batch 0.140 (0.145) Remain 02:30:58 loss: -0.1735 Lr: 5.55517e-03 +[2025-02-22 11:39:05,502 INFO hook.py line 109 2775932] Train: [22/100][600/800] Data 0.003 (0.004) Batch 0.150 (0.144) Remain 02:30:36 loss: -0.2415 Lr: 5.55192e-03 +[2025-02-22 11:39:12,525 INFO hook.py line 109 2775932] Train: [22/100][650/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 02:30:10 loss: -0.3732 Lr: 5.54866e-03 +[2025-02-22 11:39:20,017 INFO hook.py line 109 2775932] Train: [22/100][700/800] Data 0.002 (0.003) Batch 0.137 (0.144) Remain 02:30:29 loss: -0.3905 Lr: 5.54538e-03 +[2025-02-22 11:39:27,308 INFO hook.py line 109 2775932] Train: [22/100][750/800] Data 0.003 (0.003) Batch 0.153 (0.145) Remain 02:30:27 loss: -0.2646 Lr: 5.54209e-03 +[2025-02-22 11:39:34,224 INFO hook.py line 109 2775932] Train: [22/100][800/800] Data 0.003 (0.003) Batch 0.116 (0.144) Remain 02:29:56 loss: -0.3880 Lr: 5.53879e-03 +[2025-02-22 11:39:34,225 INFO misc.py line 135 2775932] Train result: loss: -0.3060 seg_loss: 0.3122 bias_l1_loss: 0.2927 bias_cosine_loss: -0.9108 +[2025-02-22 11:39:34,226 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:39:42,509 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6845 +[2025-02-22 11:39:42,715 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3387 +[2025-02-22 11:39:42,774 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2821 +[2025-02-22 11:39:42,844 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5663 +[2025-02-22 11:39:42,925 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4378 +[2025-02-22 11:39:42,976 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8178 +[2025-02-22 11:39:43,236 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4136 +[2025-02-22 11:39:43,267 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.2605 +[2025-02-22 11:39:43,389 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0246 +[2025-02-22 11:39:43,443 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0338 +[2025-02-22 11:39:43,673 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2284 +[2025-02-22 11:39:43,773 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.3048 +[2025-02-22 11:39:43,847 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.3895 +[2025-02-22 11:39:43,930 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2197 +[2025-02-22 11:39:44,003 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2756 +[2025-02-22 11:39:44,071 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4924 +[2025-02-22 11:39:44,207 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3023 +[2025-02-22 11:39:44,306 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2085 +[2025-02-22 11:39:44,444 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0863 +[2025-02-22 11:39:44,508 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0163 +[2025-02-22 11:39:44,650 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5957 +[2025-02-22 11:39:44,805 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2939 +[2025-02-22 11:39:44,871 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2829 +[2025-02-22 11:39:44,921 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1974 +[2025-02-22 11:39:44,980 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2329 +[2025-02-22 11:39:45,043 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5396 +[2025-02-22 11:39:45,150 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.7116 +[2025-02-22 11:39:45,239 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5984 +[2025-02-22 11:39:45,301 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5100 +[2025-02-22 11:39:45,369 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4253 +[2025-02-22 11:39:46,066 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3459 +[2025-02-22 11:39:46,173 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3782 +[2025-02-22 11:39:46,205 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6874 +[2025-02-22 11:39:46,292 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2489 +[2025-02-22 11:39:46,322 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6365 +[2025-02-22 11:39:46,430 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8993 +[2025-02-22 11:39:46,491 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4150 +[2025-02-22 11:39:46,592 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5140 +[2025-02-22 11:39:46,733 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.0482 +[2025-02-22 11:39:46,892 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6093 +[2025-02-22 11:39:47,036 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3518 +[2025-02-22 11:39:47,077 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1260 +[2025-02-22 11:39:47,109 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6164 +[2025-02-22 11:39:47,323 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5059 +[2025-02-22 11:39:47,357 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3811 +[2025-02-22 11:39:47,392 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4757 +[2025-02-22 11:39:47,467 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8873 +[2025-02-22 11:39:47,572 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0701 +[2025-02-22 11:39:47,665 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0625 +[2025-02-22 11:39:47,737 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3401 +[2025-02-22 11:39:47,799 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.8454 +[2025-02-22 11:39:47,909 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1029 +[2025-02-22 11:39:47,942 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7199 +[2025-02-22 11:39:48,032 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8711 +[2025-02-22 11:39:48,115 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7845 +[2025-02-22 11:39:48,151 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7399 +[2025-02-22 11:39:48,255 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0159 +[2025-02-22 11:39:48,288 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1656 +[2025-02-22 11:39:48,469 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1023 +[2025-02-22 11:39:48,557 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.3218 +[2025-02-22 11:39:48,613 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6982 +[2025-02-22 11:39:48,661 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5066 +[2025-02-22 11:39:48,799 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1314 +[2025-02-22 11:39:48,894 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6919 +[2025-02-22 11:39:48,948 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1221 +[2025-02-22 11:39:49,065 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0248 +[2025-02-22 11:39:49,206 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5295 +[2025-02-22 11:39:49,289 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.3987 +[2025-02-22 11:39:49,364 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7195 +[2025-02-22 11:39:49,416 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0994 +[2025-02-22 11:39:49,548 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2475 +[2025-02-22 11:39:49,585 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.2225 +[2025-02-22 11:39:49,647 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6750 +[2025-02-22 11:39:49,747 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.9447 +[2025-02-22 11:39:49,932 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5298 +[2025-02-22 11:39:49,996 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.4124 +[2025-02-22 11:39:50,163 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5161 +[2025-02-22 11:39:50,247 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6044 +[2025-02-22 11:40:00,373 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:40:00,374 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:40:00,374 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] cabinet : 0.2012 0.4069 0.6533 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] bed : 0.3409 0.6711 0.8255 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] chair : 0.6911 0.8531 0.9043 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] sofa : 0.3331 0.5725 0.8030 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] table : 0.3055 0.5078 0.6184 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] door : 0.1532 0.3390 0.4747 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] window : 0.0856 0.1954 0.3728 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] bookshelf : 0.1581 0.4155 0.6723 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] picture : 0.2051 0.3081 0.4085 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] counter : 0.0247 0.0873 0.4427 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] desk : 0.0904 0.3147 0.7623 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] curtain : 0.1543 0.2619 0.4117 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] refridgerator : 0.3208 0.4519 0.5501 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] shower curtain : 0.3866 0.5744 0.7118 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] toilet : 0.7839 0.9467 0.9978 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] sink : 0.2536 0.5392 0.8395 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] bathtub : 0.6274 0.7742 0.8984 +[2025-02-22 11:40:00,374 INFO evaluator.py line 547 2775932] otherfurniture : 0.3281 0.5240 0.6466 +[2025-02-22 11:40:00,374 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:40:00,374 INFO evaluator.py line 554 2775932] average : 0.3024 0.4858 0.6663 +[2025-02-22 11:40:00,374 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:40:00,374 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:40:00,410 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:40:00,413 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:40:09,354 INFO hook.py line 109 2775932] Train: [23/100][50/800] Data 0.007 (0.016) Batch 0.130 (0.156) Remain 02:42:04 loss: -0.1556 Lr: 5.53549e-03 +[2025-02-22 11:40:16,740 INFO hook.py line 109 2775932] Train: [23/100][100/800] Data 0.002 (0.011) Batch 0.127 (0.152) Remain 02:37:31 loss: -0.1759 Lr: 5.53217e-03 +[2025-02-22 11:40:23,844 INFO hook.py line 109 2775932] Train: [23/100][150/800] Data 0.002 (0.008) Batch 0.141 (0.148) Remain 02:34:00 loss: -0.4010 Lr: 5.52884e-03 +[2025-02-22 11:40:31,004 INFO hook.py line 109 2775932] Train: [23/100][200/800] Data 0.003 (0.007) Batch 0.171 (0.147) Remain 02:32:29 loss: -0.4169 Lr: 5.52550e-03 +[2025-02-22 11:40:38,223 INFO hook.py line 109 2775932] Train: [23/100][250/800] Data 0.003 (0.006) Batch 0.146 (0.147) Remain 02:31:48 loss: -0.3967 Lr: 5.52214e-03 +[2025-02-22 11:40:45,376 INFO hook.py line 109 2775932] Train: [23/100][300/800] Data 0.004 (0.005) Batch 0.137 (0.146) Remain 02:31:04 loss: -0.1077 Lr: 5.51878e-03 +[2025-02-22 11:40:52,408 INFO hook.py line 109 2775932] Train: [23/100][350/800] Data 0.003 (0.005) Batch 0.144 (0.145) Remain 02:30:09 loss: -0.4658 Lr: 5.51541e-03 +[2025-02-22 11:40:59,698 INFO hook.py line 109 2775932] Train: [23/100][400/800] Data 0.003 (0.005) Batch 0.132 (0.145) Remain 02:30:06 loss: -0.4549 Lr: 5.51202e-03 +[2025-02-22 11:41:07,107 INFO hook.py line 109 2775932] Train: [23/100][450/800] Data 0.005 (0.005) Batch 0.140 (0.146) Remain 02:30:19 loss: -0.0640 Lr: 5.50863e-03 +[2025-02-22 11:41:14,517 INFO hook.py line 109 2775932] Train: [23/100][500/800] Data 0.003 (0.004) Batch 0.148 (0.146) Remain 02:30:28 loss: -0.3808 Lr: 5.50522e-03 +[2025-02-22 11:41:21,569 INFO hook.py line 109 2775932] Train: [23/100][550/800] Data 0.003 (0.004) Batch 0.130 (0.145) Remain 02:29:54 loss: -0.3492 Lr: 5.50181e-03 +[2025-02-22 11:41:28,895 INFO hook.py line 109 2775932] Train: [23/100][600/800] Data 0.002 (0.004) Batch 0.132 (0.146) Remain 02:29:52 loss: -0.4653 Lr: 5.49838e-03 +[2025-02-22 11:41:35,804 INFO hook.py line 109 2775932] Train: [23/100][650/800] Data 0.002 (0.004) Batch 0.155 (0.145) Remain 02:29:10 loss: -0.2090 Lr: 5.49494e-03 +[2025-02-22 11:41:43,294 INFO hook.py line 109 2775932] Train: [23/100][700/800] Data 0.005 (0.004) Batch 0.127 (0.145) Remain 02:29:24 loss: -0.3990 Lr: 5.49149e-03 +[2025-02-22 11:41:50,465 INFO hook.py line 109 2775932] Train: [23/100][750/800] Data 0.002 (0.004) Batch 0.149 (0.145) Remain 02:29:09 loss: -0.2612 Lr: 5.48803e-03 +[2025-02-22 11:41:57,435 INFO hook.py line 109 2775932] Train: [23/100][800/800] Data 0.002 (0.004) Batch 0.111 (0.145) Remain 02:28:39 loss: -0.4070 Lr: 5.48463e-03 +[2025-02-22 11:41:57,436 INFO misc.py line 135 2775932] Train result: loss: -0.3137 seg_loss: 0.3079 bias_l1_loss: 0.2910 bias_cosine_loss: -0.9126 +[2025-02-22 11:41:57,436 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:42:04,647 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6837 +[2025-02-22 11:42:04,917 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1526 +[2025-02-22 11:42:05,007 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3999 +[2025-02-22 11:42:05,393 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5264 +[2025-02-22 11:42:05,464 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3639 +[2025-02-22 11:42:05,525 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7972 +[2025-02-22 11:42:05,843 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2986 +[2025-02-22 11:42:05,872 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4766 +[2025-02-22 11:42:06,023 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0380 +[2025-02-22 11:42:06,088 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.6214 +[2025-02-22 11:42:06,348 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0918 +[2025-02-22 11:42:06,453 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2431 +[2025-02-22 11:42:06,528 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.1127 +[2025-02-22 11:42:06,619 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2840 +[2025-02-22 11:42:06,699 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6268 +[2025-02-22 11:42:06,772 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5724 +[2025-02-22 11:42:06,932 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2662 +[2025-02-22 11:42:07,031 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1886 +[2025-02-22 11:42:07,204 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1314 +[2025-02-22 11:42:07,288 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2678 +[2025-02-22 11:42:07,469 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5902 +[2025-02-22 11:42:07,631 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4341 +[2025-02-22 11:42:07,701 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0181 +[2025-02-22 11:42:07,753 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0448 +[2025-02-22 11:42:07,832 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1877 +[2025-02-22 11:42:07,892 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4078 +[2025-02-22 11:42:08,003 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2611 +[2025-02-22 11:42:08,095 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.2654 +[2025-02-22 11:42:08,163 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5559 +[2025-02-22 11:42:08,231 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5026 +[2025-02-22 11:42:09,025 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4017 +[2025-02-22 11:42:09,147 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.5030 +[2025-02-22 11:42:09,191 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6808 +[2025-02-22 11:42:09,297 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0995 +[2025-02-22 11:42:09,339 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5713 +[2025-02-22 11:42:09,462 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1816 +[2025-02-22 11:42:09,534 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5414 +[2025-02-22 11:42:09,674 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5201 +[2025-02-22 11:42:09,834 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0185 +[2025-02-22 11:42:10,036 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5888 +[2025-02-22 11:42:10,214 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3043 +[2025-02-22 11:42:10,263 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1809 +[2025-02-22 11:42:10,307 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5880 +[2025-02-22 11:42:10,563 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4075 +[2025-02-22 11:42:10,607 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2755 +[2025-02-22 11:42:10,656 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3391 +[2025-02-22 11:42:10,759 INFO evaluator.py line 595 2775932] Test: [47/78] Loss -0.1390 +[2025-02-22 11:42:10,888 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0904 +[2025-02-22 11:42:11,006 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2300 +[2025-02-22 11:42:11,091 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0696 +[2025-02-22 11:42:11,202 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0268 +[2025-02-22 11:42:11,336 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0236 +[2025-02-22 11:42:11,376 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4655 +[2025-02-22 11:42:11,494 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8101 +[2025-02-22 11:42:11,585 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7672 +[2025-02-22 11:42:11,632 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.4218 +[2025-02-22 11:42:11,759 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0619 +[2025-02-22 11:42:11,807 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0034 +[2025-02-22 11:42:12,070 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1090 +[2025-02-22 11:42:12,165 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0241 +[2025-02-22 11:42:12,242 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.5622 +[2025-02-22 11:42:12,295 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4926 +[2025-02-22 11:42:12,442 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.3100 +[2025-02-22 11:42:12,554 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6460 +[2025-02-22 11:42:12,612 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2753 +[2025-02-22 11:42:12,738 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.2146 +[2025-02-22 11:42:12,893 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2624 +[2025-02-22 11:42:12,975 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0767 +[2025-02-22 11:42:13,020 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8054 +[2025-02-22 11:42:13,061 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.3172 +[2025-02-22 11:42:13,215 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.4913 +[2025-02-22 11:42:13,254 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5373 +[2025-02-22 11:42:13,311 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5377 +[2025-02-22 11:42:13,422 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8950 +[2025-02-22 11:42:13,608 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3152 +[2025-02-22 11:42:13,694 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2120 +[2025-02-22 11:42:13,878 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3914 +[2025-02-22 11:42:13,970 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3379 +[2025-02-22 11:42:26,880 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:42:26,880 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:42:26,881 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] cabinet : 0.1186 0.3006 0.5596 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] bed : 0.3246 0.6859 0.8415 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] chair : 0.7043 0.8639 0.9184 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] sofa : 0.3687 0.6315 0.8259 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] table : 0.3436 0.5414 0.6519 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] door : 0.1911 0.4253 0.5999 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] window : 0.1649 0.3094 0.5415 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] bookshelf : 0.0472 0.2099 0.4594 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] picture : 0.2612 0.4164 0.5159 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] counter : 0.0196 0.0692 0.3736 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] desk : 0.0897 0.2882 0.7033 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] curtain : 0.1778 0.3615 0.5115 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] refridgerator : 0.1969 0.2785 0.3916 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] shower curtain : 0.3767 0.5450 0.6831 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] toilet : 0.8230 0.9655 0.9655 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] sink : 0.2354 0.4553 0.7608 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] bathtub : 0.5103 0.7382 0.8272 +[2025-02-22 11:42:26,881 INFO evaluator.py line 547 2775932] otherfurniture : 0.2839 0.4374 0.5954 +[2025-02-22 11:42:26,881 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:42:26,881 INFO evaluator.py line 554 2775932] average : 0.2910 0.4735 0.6514 +[2025-02-22 11:42:26,881 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:42:26,881 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:42:26,921 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:42:26,923 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:42:35,551 INFO hook.py line 109 2775932] Train: [24/100][50/800] Data 0.003 (0.003) Batch 0.151 (0.146) Remain 02:29:19 loss: -0.1904 Lr: 5.48115e-03 +[2025-02-22 11:42:42,799 INFO hook.py line 109 2775932] Train: [24/100][100/800] Data 0.005 (0.003) Batch 0.143 (0.145) Remain 02:28:53 loss: -0.3936 Lr: 5.47766e-03 +[2025-02-22 11:42:50,078 INFO hook.py line 109 2775932] Train: [24/100][150/800] Data 0.004 (0.003) Batch 0.155 (0.145) Remain 02:28:52 loss: -0.4387 Lr: 5.47416e-03 +[2025-02-22 11:42:57,183 INFO hook.py line 109 2775932] Train: [24/100][200/800] Data 0.002 (0.003) Batch 0.130 (0.145) Remain 02:27:54 loss: -0.0429 Lr: 5.47065e-03 +[2025-02-22 11:43:04,761 INFO hook.py line 109 2775932] Train: [24/100][250/800] Data 0.003 (0.005) Batch 0.152 (0.146) Remain 02:29:14 loss: -0.4724 Lr: 5.46713e-03 +[2025-02-22 11:43:11,941 INFO hook.py line 109 2775932] Train: [24/100][300/800] Data 0.003 (0.004) Batch 0.140 (0.146) Remain 02:28:42 loss: -0.2839 Lr: 5.46360e-03 +[2025-02-22 11:43:18,963 INFO hook.py line 109 2775932] Train: [24/100][350/800] Data 0.002 (0.004) Batch 0.133 (0.145) Remain 02:27:50 loss: 0.1602 Lr: 5.46005e-03 +[2025-02-22 11:43:26,129 INFO hook.py line 109 2775932] Train: [24/100][400/800] Data 0.002 (0.004) Batch 0.147 (0.145) Remain 02:27:31 loss: -0.3606 Lr: 5.45650e-03 +[2025-02-22 11:43:33,682 INFO hook.py line 109 2775932] Train: [24/100][450/800] Data 0.003 (0.004) Batch 0.151 (0.145) Remain 02:28:08 loss: -0.3816 Lr: 5.45293e-03 +[2025-02-22 11:43:40,757 INFO hook.py line 109 2775932] Train: [24/100][500/800] Data 0.002 (0.004) Batch 0.144 (0.145) Remain 02:27:37 loss: -0.3197 Lr: 5.44936e-03 +[2025-02-22 11:43:48,810 INFO hook.py line 109 2775932] Train: [24/100][550/800] Data 0.003 (0.004) Batch 0.135 (0.146) Remain 02:28:59 loss: 0.1804 Lr: 5.44577e-03 +[2025-02-22 11:43:55,971 INFO hook.py line 109 2775932] Train: [24/100][600/800] Data 0.003 (0.004) Batch 0.122 (0.146) Remain 02:28:36 loss: -0.2482 Lr: 5.44218e-03 +[2025-02-22 11:44:03,183 INFO hook.py line 109 2775932] Train: [24/100][650/800] Data 0.002 (0.004) Batch 0.141 (0.146) Remain 02:28:19 loss: -0.1544 Lr: 5.43857e-03 +[2025-02-22 11:44:10,383 INFO hook.py line 109 2775932] Train: [24/100][700/800] Data 0.003 (0.004) Batch 0.161 (0.146) Remain 02:28:03 loss: -0.4560 Lr: 5.43496e-03 +[2025-02-22 11:44:17,608 INFO hook.py line 109 2775932] Train: [24/100][750/800] Data 0.003 (0.004) Batch 0.159 (0.146) Remain 02:27:50 loss: -0.1560 Lr: 5.43133e-03 +[2025-02-22 11:44:24,397 INFO hook.py line 109 2775932] Train: [24/100][800/800] Data 0.001 (0.004) Batch 0.108 (0.145) Remain 02:27:05 loss: -0.1512 Lr: 5.42769e-03 +[2025-02-22 11:44:24,399 INFO misc.py line 135 2775932] Train result: loss: -0.3172 seg_loss: 0.3029 bias_l1_loss: 0.2911 bias_cosine_loss: -0.9113 +[2025-02-22 11:44:24,399 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:44:31,709 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6290 +[2025-02-22 11:44:32,402 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1087 +[2025-02-22 11:44:32,461 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2479 +[2025-02-22 11:44:32,536 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4327 +[2025-02-22 11:44:32,664 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4461 +[2025-02-22 11:44:32,710 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7653 +[2025-02-22 11:44:32,978 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4742 +[2025-02-22 11:44:33,009 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5522 +[2025-02-22 11:44:33,162 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1748 +[2025-02-22 11:44:33,220 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0545 +[2025-02-22 11:44:33,451 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2897 +[2025-02-22 11:44:33,563 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1089 +[2025-02-22 11:44:33,629 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4456 +[2025-02-22 11:44:33,726 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1868 +[2025-02-22 11:44:33,801 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8778 +[2025-02-22 11:44:33,873 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5051 +[2025-02-22 11:44:34,009 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4674 +[2025-02-22 11:44:34,103 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.4052 +[2025-02-22 11:44:34,254 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0783 +[2025-02-22 11:44:34,314 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0923 +[2025-02-22 11:44:34,455 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6283 +[2025-02-22 11:44:34,630 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4806 +[2025-02-22 11:44:34,693 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2244 +[2025-02-22 11:44:34,744 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0934 +[2025-02-22 11:44:34,826 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3814 +[2025-02-22 11:44:34,876 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4956 +[2025-02-22 11:44:34,997 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2835 +[2025-02-22 11:44:35,087 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8127 +[2025-02-22 11:44:35,159 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5963 +[2025-02-22 11:44:35,222 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4152 +[2025-02-22 11:44:35,939 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4033 +[2025-02-22 11:44:36,055 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.8044 +[2025-02-22 11:44:36,102 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6382 +[2025-02-22 11:44:36,205 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2067 +[2025-02-22 11:44:36,240 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6329 +[2025-02-22 11:44:36,353 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8709 +[2025-02-22 11:44:36,413 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5240 +[2025-02-22 11:44:36,523 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6015 +[2025-02-22 11:44:36,654 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8322 +[2025-02-22 11:44:36,817 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8743 +[2025-02-22 11:44:36,946 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4746 +[2025-02-22 11:44:36,984 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0547 +[2025-02-22 11:44:37,015 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5963 +[2025-02-22 11:44:37,237 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4206 +[2025-02-22 11:44:37,277 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3623 +[2025-02-22 11:44:37,323 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4731 +[2025-02-22 11:44:37,440 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0335 +[2025-02-22 11:44:37,570 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1377 +[2025-02-22 11:44:37,688 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2281 +[2025-02-22 11:44:37,776 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2314 +[2025-02-22 11:44:37,850 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0702 +[2025-02-22 11:44:37,975 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2299 +[2025-02-22 11:44:38,016 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7001 +[2025-02-22 11:44:38,128 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.2610 +[2025-02-22 11:44:38,214 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7698 +[2025-02-22 11:44:38,275 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7424 +[2025-02-22 11:44:38,396 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0625 +[2025-02-22 11:44:38,443 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2670 +[2025-02-22 11:44:38,657 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0905 +[2025-02-22 11:44:38,758 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0130 +[2025-02-22 11:44:38,821 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8286 +[2025-02-22 11:44:38,873 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5196 +[2025-02-22 11:44:39,021 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1961 +[2025-02-22 11:44:39,143 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3247 +[2025-02-22 11:44:39,233 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1079 +[2025-02-22 11:44:39,338 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0061 +[2025-02-22 11:44:39,501 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4439 +[2025-02-22 11:44:39,587 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2066 +[2025-02-22 11:44:39,640 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7136 +[2025-02-22 11:44:39,691 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0748 +[2025-02-22 11:44:39,825 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1589 +[2025-02-22 11:44:39,861 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5147 +[2025-02-22 11:44:39,909 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6319 +[2025-02-22 11:44:40,024 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.8274 +[2025-02-22 11:44:40,245 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5073 +[2025-02-22 11:44:40,321 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0545 +[2025-02-22 11:44:40,467 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4982 +[2025-02-22 11:44:40,549 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6334 +[2025-02-22 11:44:51,598 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:44:51,598 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:44:51,598 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] cabinet : 0.2014 0.4164 0.6867 +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] bed : 0.2847 0.6111 0.7894 +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] chair : 0.6937 0.8647 0.9194 +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] sofa : 0.3195 0.5830 0.7970 +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] table : 0.3751 0.5922 0.7291 +[2025-02-22 11:44:51,598 INFO evaluator.py line 547 2775932] door : 0.1872 0.3592 0.4695 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] window : 0.0913 0.1857 0.3664 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] bookshelf : 0.1619 0.4018 0.7067 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] picture : 0.2584 0.3947 0.4589 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] counter : 0.0362 0.1372 0.6396 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] desk : 0.0654 0.2362 0.7171 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] curtain : 0.0848 0.2056 0.4803 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] refridgerator : 0.2922 0.4274 0.5006 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] shower curtain : 0.4133 0.6385 0.7509 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] toilet : 0.8137 0.9477 0.9979 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] sink : 0.2551 0.5439 0.8193 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] bathtub : 0.5909 0.7996 0.8617 +[2025-02-22 11:44:51,599 INFO evaluator.py line 547 2775932] otherfurniture : 0.3230 0.5015 0.6194 +[2025-02-22 11:44:51,599 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:44:51,599 INFO evaluator.py line 554 2775932] average : 0.3026 0.4915 0.6839 +[2025-02-22 11:44:51,599 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:44:51,599 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:44:51,641 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:44:51,644 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:45:00,692 INFO hook.py line 109 2775932] Train: [25/100][50/800] Data 0.003 (0.003) Batch 0.152 (0.146) Remain 02:27:40 loss: -0.3764 Lr: 5.42404e-03 +[2025-02-22 11:45:07,931 INFO hook.py line 109 2775932] Train: [25/100][100/800] Data 0.003 (0.005) Batch 0.136 (0.145) Remain 02:26:59 loss: -0.3824 Lr: 5.42039e-03 +[2025-02-22 11:45:14,857 INFO hook.py line 109 2775932] Train: [25/100][150/800] Data 0.002 (0.004) Batch 0.147 (0.143) Remain 02:24:32 loss: -0.3904 Lr: 5.41672e-03 +[2025-02-22 11:45:21,898 INFO hook.py line 109 2775932] Train: [25/100][200/800] Data 0.003 (0.004) Batch 0.143 (0.142) Remain 02:23:51 loss: -0.2808 Lr: 5.41304e-03 +[2025-02-22 11:45:29,109 INFO hook.py line 109 2775932] Train: [25/100][250/800] Data 0.003 (0.004) Batch 0.137 (0.143) Remain 02:24:06 loss: -0.1167 Lr: 5.40935e-03 +[2025-02-22 11:45:36,443 INFO hook.py line 109 2775932] Train: [25/100][300/800] Data 0.002 (0.003) Batch 0.135 (0.143) Remain 02:24:38 loss: -0.5447 Lr: 5.40565e-03 +[2025-02-22 11:45:43,770 INFO hook.py line 109 2775932] Train: [25/100][350/800] Data 0.002 (0.003) Batch 0.160 (0.144) Remain 02:24:58 loss: -0.3063 Lr: 5.40194e-03 +[2025-02-22 11:45:51,085 INFO hook.py line 109 2775932] Train: [25/100][400/800] Data 0.003 (0.004) Batch 0.137 (0.144) Remain 02:25:09 loss: -0.5264 Lr: 5.39822e-03 +[2025-02-22 11:45:58,086 INFO hook.py line 109 2775932] Train: [25/100][450/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 02:24:34 loss: -0.5154 Lr: 5.39449e-03 +[2025-02-22 11:46:05,515 INFO hook.py line 109 2775932] Train: [25/100][500/800] Data 0.003 (0.004) Batch 0.140 (0.144) Remain 02:24:56 loss: -0.2521 Lr: 5.39075e-03 +[2025-02-22 11:46:12,809 INFO hook.py line 109 2775932] Train: [25/100][550/800] Data 0.004 (0.003) Batch 0.170 (0.144) Remain 02:24:58 loss: -0.1473 Lr: 5.38700e-03 +[2025-02-22 11:46:20,230 INFO hook.py line 109 2775932] Train: [25/100][600/800] Data 0.003 (0.003) Batch 0.135 (0.145) Remain 02:25:11 loss: -0.3972 Lr: 5.38324e-03 +[2025-02-22 11:46:27,552 INFO hook.py line 109 2775932] Train: [25/100][650/800] Data 0.003 (0.003) Batch 0.173 (0.145) Remain 02:25:12 loss: -0.2544 Lr: 5.37947e-03 +[2025-02-22 11:46:34,716 INFO hook.py line 109 2775932] Train: [25/100][700/800] Data 0.002 (0.003) Batch 0.134 (0.145) Remain 02:24:58 loss: -0.3244 Lr: 5.37569e-03 +[2025-02-22 11:46:41,886 INFO hook.py line 109 2775932] Train: [25/100][750/800] Data 0.003 (0.003) Batch 0.136 (0.145) Remain 02:24:45 loss: -0.5932 Lr: 5.37190e-03 +[2025-02-22 11:46:48,884 INFO hook.py line 109 2775932] Train: [25/100][800/800] Data 0.003 (0.003) Batch 0.115 (0.144) Remain 02:24:20 loss: -0.3242 Lr: 5.36809e-03 +[2025-02-22 11:46:48,885 INFO misc.py line 135 2775932] Train result: loss: -0.3180 seg_loss: 0.3015 bias_l1_loss: 0.2922 bias_cosine_loss: -0.9117 +[2025-02-22 11:46:48,885 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:46:56,075 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6477 +[2025-02-22 11:46:56,367 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1131 +[2025-02-22 11:46:56,447 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.0819 +[2025-02-22 11:46:56,526 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3521 +[2025-02-22 11:46:57,049 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3418 +[2025-02-22 11:46:57,112 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9419 +[2025-02-22 11:46:57,376 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3049 +[2025-02-22 11:46:57,407 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4327 +[2025-02-22 11:46:57,553 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0724 +[2025-02-22 11:46:57,622 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0935 +[2025-02-22 11:46:57,864 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2705 +[2025-02-22 11:46:57,972 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2578 +[2025-02-22 11:46:58,038 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0628 +[2025-02-22 11:46:58,139 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3441 +[2025-02-22 11:46:58,224 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4553 +[2025-02-22 11:46:58,299 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4682 +[2025-02-22 11:46:58,435 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2502 +[2025-02-22 11:46:58,525 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1245 +[2025-02-22 11:46:58,684 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1743 +[2025-02-22 11:46:58,749 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0596 +[2025-02-22 11:46:58,898 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4522 +[2025-02-22 11:46:59,076 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3124 +[2025-02-22 11:46:59,148 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0530 +[2025-02-22 11:46:59,214 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1430 +[2025-02-22 11:46:59,277 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0805 +[2025-02-22 11:46:59,330 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3867 +[2025-02-22 11:46:59,462 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4907 +[2025-02-22 11:46:59,549 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0088 +[2025-02-22 11:46:59,618 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5657 +[2025-02-22 11:46:59,689 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5671 +[2025-02-22 11:47:00,405 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.1622 +[2025-02-22 11:47:00,519 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3137 +[2025-02-22 11:47:00,559 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7008 +[2025-02-22 11:47:00,656 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1768 +[2025-02-22 11:47:00,697 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6201 +[2025-02-22 11:47:00,814 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0736 +[2025-02-22 11:47:00,876 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4685 +[2025-02-22 11:47:00,999 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5679 +[2025-02-22 11:47:01,174 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3144 +[2025-02-22 11:47:01,405 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.4928 +[2025-02-22 11:47:01,563 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.2393 +[2025-02-22 11:47:01,617 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0320 +[2025-02-22 11:47:01,657 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5675 +[2025-02-22 11:47:01,883 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4172 +[2025-02-22 11:47:01,918 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3610 +[2025-02-22 11:47:01,951 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2612 +[2025-02-22 11:47:02,042 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3179 +[2025-02-22 11:47:02,162 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0472 +[2025-02-22 11:47:02,254 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.5246 +[2025-02-22 11:47:02,344 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2198 +[2025-02-22 11:47:02,408 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1242 +[2025-02-22 11:47:02,521 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0999 +[2025-02-22 11:47:02,557 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7111 +[2025-02-22 11:47:02,670 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3984 +[2025-02-22 11:47:02,752 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7813 +[2025-02-22 11:47:02,789 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6307 +[2025-02-22 11:47:02,902 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0430 +[2025-02-22 11:47:02,942 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1605 +[2025-02-22 11:47:03,141 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0737 +[2025-02-22 11:47:03,248 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2101 +[2025-02-22 11:47:03,304 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.9894 +[2025-02-22 11:47:03,354 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4442 +[2025-02-22 11:47:03,502 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0691 +[2025-02-22 11:47:03,609 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4169 +[2025-02-22 11:47:03,667 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 1.0443 +[2025-02-22 11:47:03,890 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1162 +[2025-02-22 11:47:04,043 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4707 +[2025-02-22 11:47:04,119 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1358 +[2025-02-22 11:47:04,158 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6448 +[2025-02-22 11:47:04,205 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3117 +[2025-02-22 11:47:04,365 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0630 +[2025-02-22 11:47:04,403 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3979 +[2025-02-22 11:47:04,456 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5848 +[2025-02-22 11:47:04,559 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5993 +[2025-02-22 11:47:04,771 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3278 +[2025-02-22 11:47:04,851 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.5469 +[2025-02-22 11:47:05,009 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.2712 +[2025-02-22 11:47:05,092 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6249 +[2025-02-22 11:47:17,756 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:47:17,756 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:47:17,756 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] cabinet : 0.2835 0.5221 0.7559 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] bed : 0.3238 0.6606 0.7600 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] chair : 0.7043 0.8614 0.9140 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] sofa : 0.3575 0.5988 0.8091 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] table : 0.3245 0.5307 0.6788 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] door : 0.2256 0.3995 0.5228 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] window : 0.1008 0.1914 0.3167 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] bookshelf : 0.1733 0.4407 0.6479 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] picture : 0.2837 0.4343 0.5342 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] counter : 0.0037 0.0226 0.1729 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] desk : 0.0896 0.2666 0.6491 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] curtain : 0.1885 0.3228 0.4732 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] refridgerator : 0.3904 0.5742 0.6733 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] shower curtain : 0.4053 0.6130 0.7031 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] toilet : 0.8332 0.9655 0.9825 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] sink : 0.3030 0.6198 0.8230 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] bathtub : 0.5725 0.6803 0.8626 +[2025-02-22 11:47:17,756 INFO evaluator.py line 547 2775932] otherfurniture : 0.2708 0.4570 0.5884 +[2025-02-22 11:47:17,756 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:47:17,756 INFO evaluator.py line 554 2775932] average : 0.3241 0.5090 0.6593 +[2025-02-22 11:47:17,756 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:47:17,757 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:47:17,793 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:47:17,796 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:47:26,493 INFO hook.py line 109 2775932] Train: [26/100][50/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 02:23:01 loss: -0.4128 Lr: 5.36428e-03 +[2025-02-22 11:47:33,860 INFO hook.py line 109 2775932] Train: [26/100][100/800] Data 0.002 (0.005) Batch 0.159 (0.145) Remain 02:25:03 loss: -0.0468 Lr: 5.36046e-03 +[2025-02-22 11:47:41,012 INFO hook.py line 109 2775932] Train: [26/100][150/800] Data 0.003 (0.004) Batch 0.161 (0.145) Remain 02:24:10 loss: -0.2536 Lr: 5.35663e-03 +[2025-02-22 11:47:48,213 INFO hook.py line 109 2775932] Train: [26/100][200/800] Data 0.004 (0.004) Batch 0.144 (0.144) Remain 02:23:55 loss: -0.5815 Lr: 5.35279e-03 +[2025-02-22 11:47:55,524 INFO hook.py line 109 2775932] Train: [26/100][250/800] Data 0.002 (0.004) Batch 0.140 (0.145) Remain 02:24:10 loss: 0.0288 Lr: 5.34894e-03 +[2025-02-22 11:48:02,822 INFO hook.py line 109 2775932] Train: [26/100][300/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 02:24:14 loss: -0.5425 Lr: 5.34507e-03 +[2025-02-22 11:48:09,998 INFO hook.py line 109 2775932] Train: [26/100][350/800] Data 0.003 (0.004) Batch 0.151 (0.145) Remain 02:23:55 loss: -0.2757 Lr: 5.34120e-03 +[2025-02-22 11:48:17,366 INFO hook.py line 109 2775932] Train: [26/100][400/800] Data 0.003 (0.004) Batch 0.148 (0.145) Remain 02:24:07 loss: -0.4367 Lr: 5.33732e-03 +[2025-02-22 11:48:24,638 INFO hook.py line 109 2775932] Train: [26/100][450/800] Data 0.002 (0.004) Batch 0.138 (0.145) Remain 02:24:02 loss: -0.2142 Lr: 5.33343e-03 +[2025-02-22 11:48:31,928 INFO hook.py line 109 2775932] Train: [26/100][500/800] Data 0.003 (0.004) Batch 0.159 (0.145) Remain 02:23:58 loss: -0.1759 Lr: 5.32953e-03 +[2025-02-22 11:48:39,049 INFO hook.py line 109 2775932] Train: [26/100][550/800] Data 0.002 (0.004) Batch 0.176 (0.145) Remain 02:23:36 loss: -0.2532 Lr: 5.32561e-03 +[2025-02-22 11:48:46,561 INFO hook.py line 109 2775932] Train: [26/100][600/800] Data 0.003 (0.004) Batch 0.171 (0.145) Remain 02:23:55 loss: 0.2772 Lr: 5.32169e-03 +[2025-02-22 11:48:53,720 INFO hook.py line 109 2775932] Train: [26/100][650/800] Data 0.003 (0.004) Batch 0.122 (0.145) Remain 02:23:38 loss: -0.0284 Lr: 5.31784e-03 +[2025-02-22 11:49:00,927 INFO hook.py line 109 2775932] Train: [26/100][700/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 02:23:26 loss: -0.4431 Lr: 5.31390e-03 +[2025-02-22 11:49:08,070 INFO hook.py line 109 2775932] Train: [26/100][750/800] Data 0.003 (0.003) Batch 0.139 (0.145) Remain 02:23:10 loss: -0.4696 Lr: 5.30995e-03 +[2025-02-22 11:49:15,193 INFO hook.py line 109 2775932] Train: [26/100][800/800] Data 0.002 (0.003) Batch 0.121 (0.145) Remain 02:22:53 loss: -0.3882 Lr: 5.30599e-03 +[2025-02-22 11:49:15,194 INFO misc.py line 135 2775932] Train result: loss: -0.3257 seg_loss: 0.2985 bias_l1_loss: 0.2887 bias_cosine_loss: -0.9130 +[2025-02-22 11:49:15,195 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:49:22,695 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6517 +[2025-02-22 11:49:22,910 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4099 +[2025-02-22 11:49:22,982 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3524 +[2025-02-22 11:49:23,813 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5981 +[2025-02-22 11:49:23,886 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5103 +[2025-02-22 11:49:23,932 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9565 +[2025-02-22 11:49:24,191 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4307 +[2025-02-22 11:49:24,235 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5420 +[2025-02-22 11:49:24,353 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0599 +[2025-02-22 11:49:24,418 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1477 +[2025-02-22 11:49:24,655 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0615 +[2025-02-22 11:49:24,759 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1827 +[2025-02-22 11:49:24,827 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.7433 +[2025-02-22 11:49:24,921 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8404 +[2025-02-22 11:49:24,999 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5885 +[2025-02-22 11:49:25,067 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.2468 +[2025-02-22 11:49:25,202 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4312 +[2025-02-22 11:49:25,297 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.0202 +[2025-02-22 11:49:25,460 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.6512 +[2025-02-22 11:49:25,548 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0000 +[2025-02-22 11:49:25,694 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5726 +[2025-02-22 11:49:25,879 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1366 +[2025-02-22 11:49:25,946 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1501 +[2025-02-22 11:49:26,001 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0555 +[2025-02-22 11:49:26,064 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3637 +[2025-02-22 11:49:26,121 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5060 +[2025-02-22 11:49:26,244 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2634 +[2025-02-22 11:49:26,338 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8904 +[2025-02-22 11:49:26,403 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5159 +[2025-02-22 11:49:26,484 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3736 +[2025-02-22 11:49:27,235 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3060 +[2025-02-22 11:49:27,340 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4616 +[2025-02-22 11:49:27,372 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6797 +[2025-02-22 11:49:27,479 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0726 +[2025-02-22 11:49:27,518 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6024 +[2025-02-22 11:49:27,620 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2250 +[2025-02-22 11:49:27,685 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4313 +[2025-02-22 11:49:27,794 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6183 +[2025-02-22 11:49:27,919 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3613 +[2025-02-22 11:49:28,101 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5829 +[2025-02-22 11:49:28,258 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3314 +[2025-02-22 11:49:28,305 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1360 +[2025-02-22 11:49:28,343 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6518 +[2025-02-22 11:49:28,590 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6043 +[2025-02-22 11:49:28,630 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2519 +[2025-02-22 11:49:28,674 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3761 +[2025-02-22 11:49:28,766 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4473 +[2025-02-22 11:49:28,874 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3054 +[2025-02-22 11:49:28,981 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1095 +[2025-02-22 11:49:29,066 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0588 +[2025-02-22 11:49:29,133 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.0161 +[2025-02-22 11:49:29,249 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0757 +[2025-02-22 11:49:29,298 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6208 +[2025-02-22 11:49:29,402 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.5927 +[2025-02-22 11:49:29,509 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7476 +[2025-02-22 11:49:29,556 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7108 +[2025-02-22 11:49:29,684 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0293 +[2025-02-22 11:49:29,727 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2716 +[2025-02-22 11:49:29,937 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0047 +[2025-02-22 11:49:30,039 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1550 +[2025-02-22 11:49:30,119 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.1450 +[2025-02-22 11:49:30,179 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5337 +[2025-02-22 11:49:30,343 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2768 +[2025-02-22 11:49:30,457 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0858 +[2025-02-22 11:49:30,548 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3343 +[2025-02-22 11:49:30,699 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2344 +[2025-02-22 11:49:30,857 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5227 +[2025-02-22 11:49:30,944 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2326 +[2025-02-22 11:49:30,998 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7334 +[2025-02-22 11:49:31,062 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2163 +[2025-02-22 11:49:31,210 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1571 +[2025-02-22 11:49:31,247 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4836 +[2025-02-22 11:49:31,304 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6646 +[2025-02-22 11:49:31,399 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.1767 +[2025-02-22 11:49:31,648 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4470 +[2025-02-22 11:49:31,720 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0208 +[2025-02-22 11:49:31,890 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4636 +[2025-02-22 11:49:31,988 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5321 +[2025-02-22 11:49:42,454 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:49:42,455 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:49:42,455 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] cabinet : 0.2398 0.4658 0.7061 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] bed : 0.3238 0.6891 0.8004 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] chair : 0.6650 0.8466 0.8975 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] sofa : 0.3111 0.5384 0.7721 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] table : 0.4043 0.6280 0.7389 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] door : 0.1843 0.3417 0.4964 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] window : 0.1875 0.3346 0.5207 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] bookshelf : 0.1508 0.4499 0.8185 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] picture : 0.2796 0.4169 0.5325 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] counter : 0.0110 0.0565 0.5247 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] desk : 0.0707 0.2180 0.6749 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] curtain : 0.1796 0.3393 0.5695 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] refridgerator : 0.2532 0.3607 0.4337 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] shower curtain : 0.4192 0.6291 0.7722 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] toilet : 0.7885 0.9816 0.9977 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] sink : 0.3079 0.5462 0.8410 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] bathtub : 0.5667 0.7039 0.8436 +[2025-02-22 11:49:42,455 INFO evaluator.py line 547 2775932] otherfurniture : 0.3254 0.5060 0.6168 +[2025-02-22 11:49:42,455 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:49:42,455 INFO evaluator.py line 554 2775932] average : 0.3149 0.5029 0.6976 +[2025-02-22 11:49:42,455 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:49:42,455 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:49:42,491 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:49:42,494 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:49:51,294 INFO hook.py line 109 2775932] Train: [27/100][50/800] Data 0.003 (0.003) Batch 0.141 (0.146) Remain 02:24:10 loss: -0.4045 Lr: 5.30202e-03 +[2025-02-22 11:49:58,468 INFO hook.py line 109 2775932] Train: [27/100][100/800] Data 0.003 (0.003) Batch 0.154 (0.145) Remain 02:22:39 loss: -0.2132 Lr: 5.29804e-03 +[2025-02-22 11:50:05,624 INFO hook.py line 109 2775932] Train: [27/100][150/800] Data 0.003 (0.003) Batch 0.149 (0.144) Remain 02:21:57 loss: -0.4580 Lr: 5.29404e-03 +[2025-02-22 11:50:13,076 INFO hook.py line 109 2775932] Train: [27/100][200/800] Data 0.003 (0.004) Batch 0.160 (0.145) Remain 02:23:02 loss: -0.4051 Lr: 5.29004e-03 +[2025-02-22 11:50:20,240 INFO hook.py line 109 2775932] Train: [27/100][250/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 02:22:28 loss: -0.6047 Lr: 5.28603e-03 +[2025-02-22 11:50:27,405 INFO hook.py line 109 2775932] Train: [27/100][300/800] Data 0.003 (0.004) Batch 0.174 (0.145) Remain 02:22:04 loss: -0.5194 Lr: 5.28201e-03 +[2025-02-22 11:50:34,412 INFO hook.py line 109 2775932] Train: [27/100][350/800] Data 0.003 (0.003) Batch 0.136 (0.144) Remain 02:21:18 loss: -0.4162 Lr: 5.27798e-03 +[2025-02-22 11:50:41,401 INFO hook.py line 109 2775932] Train: [27/100][400/800] Data 0.002 (0.003) Batch 0.152 (0.144) Remain 02:20:39 loss: -0.6157 Lr: 5.27395e-03 +[2025-02-22 11:50:48,495 INFO hook.py line 109 2775932] Train: [27/100][450/800] Data 0.004 (0.003) Batch 0.148 (0.143) Remain 02:20:21 loss: -0.4727 Lr: 5.26990e-03 +[2025-02-22 11:50:55,421 INFO hook.py line 109 2775932] Train: [27/100][500/800] Data 0.003 (0.003) Batch 0.147 (0.143) Remain 02:19:45 loss: -0.3267 Lr: 5.26584e-03 +[2025-02-22 11:51:02,617 INFO hook.py line 109 2775932] Train: [27/100][550/800] Data 0.003 (0.003) Batch 0.138 (0.143) Remain 02:19:44 loss: -0.3436 Lr: 5.26177e-03 +[2025-02-22 11:51:09,714 INFO hook.py line 109 2775932] Train: [27/100][600/800] Data 0.004 (0.003) Batch 0.125 (0.143) Remain 02:19:32 loss: -0.5347 Lr: 5.25769e-03 +[2025-02-22 11:51:16,899 INFO hook.py line 109 2775932] Train: [27/100][650/800] Data 0.004 (0.003) Batch 0.126 (0.143) Remain 02:19:28 loss: -0.2762 Lr: 5.25360e-03 +[2025-02-22 11:51:24,257 INFO hook.py line 109 2775932] Train: [27/100][700/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 02:19:39 loss: -0.2574 Lr: 5.24951e-03 +[2025-02-22 11:51:31,445 INFO hook.py line 109 2775932] Train: [27/100][750/800] Data 0.003 (0.003) Batch 0.139 (0.143) Remain 02:19:34 loss: -0.6218 Lr: 5.24540e-03 +[2025-02-22 11:51:38,474 INFO hook.py line 109 2775932] Train: [27/100][800/800] Data 0.002 (0.003) Batch 0.127 (0.143) Remain 02:19:17 loss: -0.3381 Lr: 5.24128e-03 +[2025-02-22 11:51:38,474 INFO misc.py line 135 2775932] Train result: loss: -0.3509 seg_loss: 0.2856 bias_l1_loss: 0.2800 bias_cosine_loss: -0.9164 +[2025-02-22 11:51:38,474 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:51:45,661 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6595 +[2025-02-22 11:51:46,396 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2147 +[2025-02-22 11:51:46,469 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3883 +[2025-02-22 11:51:46,541 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5780 +[2025-02-22 11:51:46,611 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5246 +[2025-02-22 11:51:46,736 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8927 +[2025-02-22 11:51:47,006 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4003 +[2025-02-22 11:51:47,036 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4144 +[2025-02-22 11:51:47,184 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2017 +[2025-02-22 11:51:47,243 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2480 +[2025-02-22 11:51:47,505 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0009 +[2025-02-22 11:51:47,611 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1180 +[2025-02-22 11:51:47,685 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5836 +[2025-02-22 11:51:47,790 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2326 +[2025-02-22 11:51:47,868 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.9141 +[2025-02-22 11:51:47,940 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5835 +[2025-02-22 11:51:48,077 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4516 +[2025-02-22 11:51:48,190 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.0801 +[2025-02-22 11:51:48,349 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1035 +[2025-02-22 11:51:48,419 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1765 +[2025-02-22 11:51:48,572 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6056 +[2025-02-22 11:51:48,760 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2924 +[2025-02-22 11:51:48,847 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0148 +[2025-02-22 11:51:48,908 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1153 +[2025-02-22 11:51:48,980 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3307 +[2025-02-22 11:51:49,041 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5419 +[2025-02-22 11:51:49,236 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2691 +[2025-02-22 11:51:49,326 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5266 +[2025-02-22 11:51:49,398 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5924 +[2025-02-22 11:51:49,489 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5673 +[2025-02-22 11:51:50,406 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4351 +[2025-02-22 11:51:50,539 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2667 +[2025-02-22 11:51:50,581 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6168 +[2025-02-22 11:51:50,684 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0024 +[2025-02-22 11:51:50,720 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3826 +[2025-02-22 11:51:50,844 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.3109 +[2025-02-22 11:51:50,921 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5485 +[2025-02-22 11:51:51,062 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5353 +[2025-02-22 11:51:51,232 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4414 +[2025-02-22 11:51:51,463 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0032 +[2025-02-22 11:51:51,614 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3781 +[2025-02-22 11:51:51,656 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0863 +[2025-02-22 11:51:51,710 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6077 +[2025-02-22 11:51:51,939 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6152 +[2025-02-22 11:51:51,973 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2373 +[2025-02-22 11:51:52,008 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3988 +[2025-02-22 11:51:52,103 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7342 +[2025-02-22 11:51:52,216 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0165 +[2025-02-22 11:51:52,307 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0250 +[2025-02-22 11:51:52,392 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4681 +[2025-02-22 11:51:52,454 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1680 +[2025-02-22 11:51:52,572 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1533 +[2025-02-22 11:51:52,606 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4506 +[2025-02-22 11:51:52,700 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3081 +[2025-02-22 11:51:52,781 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7732 +[2025-02-22 11:51:52,818 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6029 +[2025-02-22 11:51:52,950 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1814 +[2025-02-22 11:51:52,981 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2215 +[2025-02-22 11:51:53,176 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1964 +[2025-02-22 11:51:53,267 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2723 +[2025-02-22 11:51:53,336 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5931 +[2025-02-22 11:51:53,401 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5964 +[2025-02-22 11:51:53,571 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1142 +[2025-02-22 11:51:53,670 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6719 +[2025-02-22 11:51:53,739 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3116 +[2025-02-22 11:51:53,862 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2617 +[2025-02-22 11:51:54,031 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2913 +[2025-02-22 11:51:54,119 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5055 +[2025-02-22 11:51:54,172 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6797 +[2025-02-22 11:51:54,221 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2785 +[2025-02-22 11:51:54,377 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0796 +[2025-02-22 11:51:54,414 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4717 +[2025-02-22 11:51:54,459 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6893 +[2025-02-22 11:51:54,560 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4125 +[2025-02-22 11:51:54,757 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6082 +[2025-02-22 11:51:54,845 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2184 +[2025-02-22 11:51:55,008 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3487 +[2025-02-22 11:51:55,105 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6639 +[2025-02-22 11:52:07,726 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:52:07,727 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:52:07,727 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] cabinet : 0.1631 0.3347 0.6071 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] bed : 0.2894 0.5378 0.6790 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] chair : 0.6932 0.8584 0.9079 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] sofa : 0.3414 0.5377 0.8025 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] table : 0.4113 0.6417 0.7444 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] door : 0.1924 0.3904 0.5146 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] window : 0.1750 0.3406 0.5346 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] bookshelf : 0.1394 0.3792 0.5897 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] picture : 0.1303 0.2399 0.3456 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] counter : 0.0249 0.1101 0.4614 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] desk : 0.0623 0.2264 0.6998 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] curtain : 0.1018 0.2714 0.5468 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] refridgerator : 0.3411 0.4711 0.4887 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] shower curtain : 0.5421 0.6922 0.8224 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] toilet : 0.8219 0.9794 0.9975 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] sink : 0.3175 0.6589 0.8724 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] bathtub : 0.5482 0.7054 0.8408 +[2025-02-22 11:52:07,727 INFO evaluator.py line 547 2775932] otherfurniture : 0.3104 0.4874 0.6247 +[2025-02-22 11:52:07,727 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:52:07,727 INFO evaluator.py line 554 2775932] average : 0.3114 0.4924 0.6711 +[2025-02-22 11:52:07,727 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:52:07,727 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:52:07,768 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:52:07,772 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:52:16,672 INFO hook.py line 109 2775932] Train: [28/100][50/800] Data 0.003 (0.008) Batch 0.142 (0.147) Remain 02:23:13 loss: -0.3134 Lr: 5.23716e-03 +[2025-02-22 11:52:24,382 INFO hook.py line 109 2775932] Train: [28/100][100/800] Data 0.002 (0.007) Batch 0.125 (0.151) Remain 02:26:33 loss: -0.3500 Lr: 5.23302e-03 +[2025-02-22 11:52:31,639 INFO hook.py line 109 2775932] Train: [28/100][150/800] Data 0.003 (0.006) Batch 0.145 (0.149) Remain 02:24:33 loss: -0.3875 Lr: 5.22888e-03 +[2025-02-22 11:52:38,639 INFO hook.py line 109 2775932] Train: [28/100][200/800] Data 0.003 (0.005) Batch 0.149 (0.147) Remain 02:22:14 loss: -0.5087 Lr: 5.22472e-03 +[2025-02-22 11:52:46,043 INFO hook.py line 109 2775932] Train: [28/100][250/800] Data 0.003 (0.005) Batch 0.118 (0.147) Remain 02:22:24 loss: -0.3745 Lr: 5.22056e-03 +[2025-02-22 11:52:53,253 INFO hook.py line 109 2775932] Train: [28/100][300/800] Data 0.003 (0.005) Batch 0.153 (0.146) Remain 02:21:50 loss: -0.2340 Lr: 5.21638e-03 +[2025-02-22 11:53:00,878 INFO hook.py line 109 2775932] Train: [28/100][350/800] Data 0.003 (0.005) Batch 0.161 (0.147) Remain 02:22:33 loss: -0.4276 Lr: 5.21220e-03 +[2025-02-22 11:53:08,137 INFO hook.py line 109 2775932] Train: [28/100][400/800] Data 0.004 (0.004) Batch 0.152 (0.147) Remain 02:22:09 loss: -0.4787 Lr: 5.20801e-03 +[2025-02-22 11:53:15,318 INFO hook.py line 109 2775932] Train: [28/100][450/800] Data 0.002 (0.005) Batch 0.142 (0.147) Remain 02:21:40 loss: -0.1741 Lr: 5.20380e-03 +[2025-02-22 11:53:22,457 INFO hook.py line 109 2775932] Train: [28/100][500/800] Data 0.003 (0.004) Batch 0.133 (0.146) Remain 02:21:09 loss: -0.2949 Lr: 5.19959e-03 +[2025-02-22 11:53:29,595 INFO hook.py line 109 2775932] Train: [28/100][550/800] Data 0.003 (0.004) Batch 0.141 (0.146) Remain 02:20:44 loss: -0.4505 Lr: 5.19537e-03 +[2025-02-22 11:53:36,769 INFO hook.py line 109 2775932] Train: [28/100][600/800] Data 0.003 (0.004) Batch 0.127 (0.146) Remain 02:20:24 loss: -0.2731 Lr: 5.19114e-03 +[2025-02-22 11:53:43,922 INFO hook.py line 109 2775932] Train: [28/100][650/800] Data 0.002 (0.004) Batch 0.134 (0.146) Remain 02:20:05 loss: -0.1637 Lr: 5.18690e-03 +[2025-02-22 11:53:51,203 INFO hook.py line 109 2775932] Train: [28/100][700/800] Data 0.003 (0.004) Batch 0.151 (0.146) Remain 02:19:58 loss: -0.4237 Lr: 5.18265e-03 +[2025-02-22 11:53:58,589 INFO hook.py line 109 2775932] Train: [28/100][750/800] Data 0.003 (0.004) Batch 0.148 (0.146) Remain 02:19:59 loss: -0.6194 Lr: 5.17840e-03 +[2025-02-22 11:54:05,385 INFO hook.py line 109 2775932] Train: [28/100][800/800] Data 0.001 (0.004) Batch 0.113 (0.145) Remain 02:19:16 loss: -0.0630 Lr: 5.17413e-03 +[2025-02-22 11:54:05,386 INFO misc.py line 135 2775932] Train result: loss: -0.3475 seg_loss: 0.2837 bias_l1_loss: 0.2835 bias_cosine_loss: -0.9148 +[2025-02-22 11:54:05,386 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:54:12,347 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6294 +[2025-02-22 11:54:13,187 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0339 +[2025-02-22 11:54:13,253 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3309 +[2025-02-22 11:54:13,329 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5307 +[2025-02-22 11:54:13,383 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4601 +[2025-02-22 11:54:13,437 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5630 +[2025-02-22 11:54:13,710 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.2807 +[2025-02-22 11:54:13,741 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3469 +[2025-02-22 11:54:13,874 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0509 +[2025-02-22 11:54:13,938 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3438 +[2025-02-22 11:54:14,215 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1595 +[2025-02-22 11:54:14,330 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1499 +[2025-02-22 11:54:14,406 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.6641 +[2025-02-22 11:54:14,495 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2400 +[2025-02-22 11:54:14,575 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4869 +[2025-02-22 11:54:14,646 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5923 +[2025-02-22 11:54:14,814 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3480 +[2025-02-22 11:54:14,916 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1591 +[2025-02-22 11:54:15,107 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2518 +[2025-02-22 11:54:15,172 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0679 +[2025-02-22 11:54:15,329 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5437 +[2025-02-22 11:54:15,508 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.8603 +[2025-02-22 11:54:15,584 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1495 +[2025-02-22 11:54:15,638 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0471 +[2025-02-22 11:54:15,699 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0930 +[2025-02-22 11:54:15,761 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3080 +[2025-02-22 11:54:15,890 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3870 +[2025-02-22 11:54:16,086 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8277 +[2025-02-22 11:54:16,169 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5172 +[2025-02-22 11:54:16,241 INFO evaluator.py line 595 2775932] Test: [30/78] Loss 0.4500 +[2025-02-22 11:54:17,168 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3411 +[2025-02-22 11:54:17,294 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4362 +[2025-02-22 11:54:17,339 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6427 +[2025-02-22 11:54:17,438 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2382 +[2025-02-22 11:54:17,477 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6388 +[2025-02-22 11:54:17,596 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8448 +[2025-02-22 11:54:17,665 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.1384 +[2025-02-22 11:54:17,839 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5865 +[2025-02-22 11:54:17,977 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5201 +[2025-02-22 11:54:18,183 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1752 +[2025-02-22 11:54:18,359 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3911 +[2025-02-22 11:54:18,408 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.3568 +[2025-02-22 11:54:18,453 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4811 +[2025-02-22 11:54:18,733 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.3197 +[2025-02-22 11:54:18,807 INFO evaluator.py line 595 2775932] Test: [45/78] Loss 0.1323 +[2025-02-22 11:54:18,849 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2945 +[2025-02-22 11:54:18,958 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3498 +[2025-02-22 11:54:19,078 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0750 +[2025-02-22 11:54:19,173 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3732 +[2025-02-22 11:54:19,261 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4863 +[2025-02-22 11:54:19,339 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.2139 +[2025-02-22 11:54:19,481 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1759 +[2025-02-22 11:54:19,534 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6717 +[2025-02-22 11:54:19,634 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3881 +[2025-02-22 11:54:19,724 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7666 +[2025-02-22 11:54:19,771 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7323 +[2025-02-22 11:54:19,901 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1265 +[2025-02-22 11:54:19,946 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0880 +[2025-02-22 11:54:20,170 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3374 +[2025-02-22 11:54:20,273 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0871 +[2025-02-22 11:54:20,340 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6382 +[2025-02-22 11:54:20,427 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3183 +[2025-02-22 11:54:20,610 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2885 +[2025-02-22 11:54:20,732 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.2804 +[2025-02-22 11:54:20,804 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0815 +[2025-02-22 11:54:20,935 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2441 +[2025-02-22 11:54:21,093 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5774 +[2025-02-22 11:54:21,192 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2610 +[2025-02-22 11:54:21,249 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7223 +[2025-02-22 11:54:21,306 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1182 +[2025-02-22 11:54:21,447 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0127 +[2025-02-22 11:54:21,488 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4125 +[2025-02-22 11:54:21,545 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7028 +[2025-02-22 11:54:21,648 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2800 +[2025-02-22 11:54:21,881 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4960 +[2025-02-22 11:54:21,954 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2030 +[2025-02-22 11:54:22,137 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.1470 +[2025-02-22 11:54:22,226 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5838 +[2025-02-22 11:54:34,452 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:54:34,452 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:54:34,452 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] cabinet : 0.2297 0.4346 0.7108 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] bed : 0.3030 0.6588 0.7847 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] chair : 0.6919 0.8563 0.9056 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] sofa : 0.3139 0.5923 0.8089 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] table : 0.3125 0.4725 0.5935 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] door : 0.1229 0.2807 0.4428 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] window : 0.1346 0.2778 0.4404 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] bookshelf : 0.1967 0.4959 0.7513 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] picture : 0.2607 0.3951 0.4863 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] counter : 0.0268 0.1220 0.5132 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] desk : 0.0785 0.2932 0.6721 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] curtain : 0.2022 0.4451 0.6485 +[2025-02-22 11:54:34,452 INFO evaluator.py line 547 2775932] refridgerator : 0.3780 0.5407 0.6929 +[2025-02-22 11:54:34,453 INFO evaluator.py line 547 2775932] shower curtain : 0.3200 0.5181 0.6880 +[2025-02-22 11:54:34,453 INFO evaluator.py line 547 2775932] toilet : 0.7516 0.9649 0.9828 +[2025-02-22 11:54:34,453 INFO evaluator.py line 547 2775932] sink : 0.2631 0.5454 0.7950 +[2025-02-22 11:54:34,453 INFO evaluator.py line 547 2775932] bathtub : 0.3762 0.5327 0.7826 +[2025-02-22 11:54:34,453 INFO evaluator.py line 547 2775932] otherfurniture : 0.3142 0.4759 0.6018 +[2025-02-22 11:54:34,453 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:54:34,453 INFO evaluator.py line 554 2775932] average : 0.2931 0.4946 0.6834 +[2025-02-22 11:54:34,453 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:54:34,453 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:54:34,498 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:54:34,501 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:54:42,825 INFO hook.py line 109 2775932] Train: [29/100][50/800] Data 0.002 (0.003) Batch 0.150 (0.142) Remain 02:16:15 loss: -0.2701 Lr: 5.16985e-03 +[2025-02-22 11:54:50,331 INFO hook.py line 109 2775932] Train: [29/100][100/800] Data 0.003 (0.003) Batch 0.144 (0.146) Remain 02:20:07 loss: -0.3881 Lr: 5.16556e-03 +[2025-02-22 11:54:57,535 INFO hook.py line 109 2775932] Train: [29/100][150/800] Data 0.002 (0.003) Batch 0.123 (0.145) Remain 02:19:18 loss: 0.0818 Lr: 5.16127e-03 +[2025-02-22 11:55:04,775 INFO hook.py line 109 2775932] Train: [29/100][200/800] Data 0.003 (0.003) Batch 0.135 (0.145) Remain 02:19:00 loss: -0.6099 Lr: 5.15696e-03 +[2025-02-22 11:55:12,154 INFO hook.py line 109 2775932] Train: [29/100][250/800] Data 0.003 (0.004) Batch 0.166 (0.146) Remain 02:19:19 loss: -0.3517 Lr: 5.15265e-03 +[2025-02-22 11:55:19,330 INFO hook.py line 109 2775932] Train: [29/100][300/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 02:18:51 loss: -0.2812 Lr: 5.14833e-03 +[2025-02-22 11:55:26,443 INFO hook.py line 109 2775932] Train: [29/100][350/800] Data 0.003 (0.003) Batch 0.164 (0.145) Remain 02:18:17 loss: -0.2943 Lr: 5.14400e-03 +[2025-02-22 11:55:33,364 INFO hook.py line 109 2775932] Train: [29/100][400/800] Data 0.003 (0.003) Batch 0.134 (0.144) Remain 02:17:23 loss: -0.3323 Lr: 5.13965e-03 +[2025-02-22 11:55:40,385 INFO hook.py line 109 2775932] Train: [29/100][450/800] Data 0.003 (0.003) Batch 0.147 (0.144) Remain 02:16:52 loss: -0.4313 Lr: 5.13530e-03 +[2025-02-22 11:55:47,510 INFO hook.py line 109 2775932] Train: [29/100][500/800] Data 0.003 (0.003) Batch 0.147 (0.144) Remain 02:16:38 loss: -0.4488 Lr: 5.13103e-03 +[2025-02-22 11:55:54,570 INFO hook.py line 109 2775932] Train: [29/100][550/800] Data 0.002 (0.003) Batch 0.151 (0.143) Remain 02:16:18 loss: -0.5422 Lr: 5.12666e-03 +[2025-02-22 11:56:01,956 INFO hook.py line 109 2775932] Train: [29/100][600/800] Data 0.002 (0.003) Batch 0.156 (0.144) Remain 02:16:32 loss: -0.1136 Lr: 5.12228e-03 +[2025-02-22 11:56:09,348 INFO hook.py line 109 2775932] Train: [29/100][650/800] Data 0.110 (0.003) Batch 0.269 (0.144) Remain 02:16:43 loss: -0.2350 Lr: 5.11790e-03 +[2025-02-22 11:56:16,698 INFO hook.py line 109 2775932] Train: [29/100][700/800] Data 0.003 (0.003) Batch 0.168 (0.144) Remain 02:16:48 loss: -0.2888 Lr: 5.11350e-03 +[2025-02-22 11:56:23,947 INFO hook.py line 109 2775932] Train: [29/100][750/800] Data 0.003 (0.003) Batch 0.132 (0.144) Remain 02:16:43 loss: -0.5195 Lr: 5.10910e-03 +[2025-02-22 11:56:30,794 INFO hook.py line 109 2775932] Train: [29/100][800/800] Data 0.002 (0.003) Batch 0.113 (0.144) Remain 02:16:10 loss: -0.2481 Lr: 5.10468e-03 +[2025-02-22 11:56:30,795 INFO misc.py line 135 2775932] Train result: loss: -0.3479 seg_loss: 0.2873 bias_l1_loss: 0.2813 bias_cosine_loss: -0.9165 +[2025-02-22 11:56:30,795 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:56:37,817 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6980 +[2025-02-22 11:56:38,575 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2376 +[2025-02-22 11:56:38,634 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4143 +[2025-02-22 11:56:38,708 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3509 +[2025-02-22 11:56:38,770 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5458 +[2025-02-22 11:56:38,822 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7340 +[2025-02-22 11:56:39,082 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3369 +[2025-02-22 11:56:39,115 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5267 +[2025-02-22 11:56:39,258 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0101 +[2025-02-22 11:56:39,312 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.8363 +[2025-02-22 11:56:39,544 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0171 +[2025-02-22 11:56:39,642 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2103 +[2025-02-22 11:56:39,706 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.8726 +[2025-02-22 11:56:39,800 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9129 +[2025-02-22 11:56:39,886 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 1.3240 +[2025-02-22 11:56:39,963 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5821 +[2025-02-22 11:56:40,102 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4187 +[2025-02-22 11:56:40,197 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.7937 +[2025-02-22 11:56:40,331 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.5120 +[2025-02-22 11:56:40,397 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.3110 +[2025-02-22 11:56:40,575 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.4165 +[2025-02-22 11:56:40,766 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4104 +[2025-02-22 11:56:40,855 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2168 +[2025-02-22 11:56:40,908 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1494 +[2025-02-22 11:56:40,983 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1402 +[2025-02-22 11:56:41,038 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4389 +[2025-02-22 11:56:41,161 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0288 +[2025-02-22 11:56:41,250 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6314 +[2025-02-22 11:56:41,319 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4778 +[2025-02-22 11:56:41,390 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.2242 +[2025-02-22 11:56:42,256 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3062 +[2025-02-22 11:56:42,389 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4204 +[2025-02-22 11:56:42,440 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5902 +[2025-02-22 11:56:42,542 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1451 +[2025-02-22 11:56:42,581 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5466 +[2025-02-22 11:56:42,699 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.4591 +[2025-02-22 11:56:42,776 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.2311 +[2025-02-22 11:56:42,941 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5681 +[2025-02-22 11:56:43,067 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5696 +[2025-02-22 11:56:43,259 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0044 +[2025-02-22 11:56:43,410 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3756 +[2025-02-22 11:56:43,461 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0376 +[2025-02-22 11:56:43,502 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6254 +[2025-02-22 11:56:43,789 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4373 +[2025-02-22 11:56:43,834 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2037 +[2025-02-22 11:56:43,867 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4623 +[2025-02-22 11:56:43,946 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.8138 +[2025-02-22 11:56:44,059 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0031 +[2025-02-22 11:56:44,165 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0649 +[2025-02-22 11:56:44,256 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1220 +[2025-02-22 11:56:44,329 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.5882 +[2025-02-22 11:56:44,466 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2062 +[2025-02-22 11:56:44,513 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5681 +[2025-02-22 11:56:44,619 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3121 +[2025-02-22 11:56:44,715 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7406 +[2025-02-22 11:56:44,762 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6692 +[2025-02-22 11:56:44,920 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0937 +[2025-02-22 11:56:44,970 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1367 +[2025-02-22 11:56:45,195 INFO evaluator.py line 595 2775932] Test: [59/78] Loss 0.1422 +[2025-02-22 11:56:45,315 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2789 +[2025-02-22 11:56:45,386 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7495 +[2025-02-22 11:56:45,443 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3473 +[2025-02-22 11:56:45,598 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1887 +[2025-02-22 11:56:45,715 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7323 +[2025-02-22 11:56:45,797 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2824 +[2025-02-22 11:56:45,937 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1175 +[2025-02-22 11:56:46,127 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.1664 +[2025-02-22 11:56:46,211 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0994 +[2025-02-22 11:56:46,257 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7353 +[2025-02-22 11:56:46,308 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.8882 +[2025-02-22 11:56:46,453 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.5254 +[2025-02-22 11:56:46,491 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4245 +[2025-02-22 11:56:46,537 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5459 +[2025-02-22 11:56:46,627 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4355 +[2025-02-22 11:56:46,834 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5652 +[2025-02-22 11:56:46,913 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1895 +[2025-02-22 11:56:47,074 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3034 +[2025-02-22 11:56:47,160 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6002 +[2025-02-22 11:56:58,990 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:56:58,990 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:56:58,990 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] cabinet : 0.1660 0.3028 0.4929 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] bed : 0.3282 0.6505 0.7407 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] chair : 0.6866 0.8435 0.8992 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] sofa : 0.3029 0.5565 0.7095 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] table : 0.2719 0.4700 0.5848 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] door : 0.1661 0.3558 0.5097 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] window : 0.1904 0.3576 0.5838 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] bookshelf : 0.0954 0.3272 0.6107 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] picture : 0.1989 0.3206 0.4010 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] counter : 0.0002 0.0014 0.2122 +[2025-02-22 11:56:58,990 INFO evaluator.py line 547 2775932] desk : 0.0555 0.1711 0.6193 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] curtain : 0.1581 0.2835 0.5238 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] refridgerator : 0.0563 0.1698 0.1930 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] shower curtain : 0.4248 0.5926 0.7159 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] toilet : 0.7304 0.9244 0.9598 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] sink : 0.2367 0.4734 0.7863 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] bathtub : 0.6125 0.7308 0.8322 +[2025-02-22 11:56:58,991 INFO evaluator.py line 547 2775932] otherfurniture : 0.2769 0.4436 0.6043 +[2025-02-22 11:56:58,991 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:56:58,991 INFO evaluator.py line 554 2775932] average : 0.2754 0.4431 0.6100 +[2025-02-22 11:56:58,991 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:56:58,991 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:56:59,033 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:56:59,037 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:57:07,424 INFO hook.py line 109 2775932] Train: [30/100][50/800] Data 0.003 (0.003) Batch 0.122 (0.145) Remain 02:17:27 loss: -0.2773 Lr: 5.10026e-03 +[2025-02-22 11:57:14,766 INFO hook.py line 109 2775932] Train: [30/100][100/800] Data 0.004 (0.005) Batch 0.179 (0.146) Remain 02:18:03 loss: -0.3928 Lr: 5.09583e-03 +[2025-02-22 11:57:21,846 INFO hook.py line 109 2775932] Train: [30/100][150/800] Data 0.003 (0.004) Batch 0.149 (0.145) Remain 02:16:29 loss: -0.4942 Lr: 5.09139e-03 +[2025-02-22 11:57:28,945 INFO hook.py line 109 2775932] Train: [30/100][200/800] Data 0.003 (0.004) Batch 0.144 (0.144) Remain 02:15:45 loss: -0.3922 Lr: 5.08694e-03 +[2025-02-22 11:57:36,146 INFO hook.py line 109 2775932] Train: [30/100][250/800] Data 0.002 (0.004) Batch 0.136 (0.144) Remain 02:15:39 loss: -0.1747 Lr: 5.08248e-03 +[2025-02-22 11:57:43,326 INFO hook.py line 109 2775932] Train: [30/100][300/800] Data 0.002 (0.004) Batch 0.155 (0.144) Remain 02:15:29 loss: -0.4972 Lr: 5.07801e-03 +[2025-02-22 11:57:50,475 INFO hook.py line 109 2775932] Train: [30/100][350/800] Data 0.003 (0.004) Batch 0.142 (0.144) Remain 02:15:14 loss: -0.5450 Lr: 5.07354e-03 +[2025-02-22 11:57:57,754 INFO hook.py line 109 2775932] Train: [30/100][400/800] Data 0.003 (0.003) Batch 0.155 (0.144) Remain 02:15:20 loss: -0.3888 Lr: 5.06905e-03 +[2025-02-22 11:58:04,863 INFO hook.py line 109 2775932] Train: [30/100][450/800] Data 0.003 (0.003) Batch 0.159 (0.144) Remain 02:15:01 loss: -0.2831 Lr: 5.06456e-03 +[2025-02-22 11:58:12,119 INFO hook.py line 109 2775932] Train: [30/100][500/800] Data 0.004 (0.003) Batch 0.135 (0.144) Remain 02:15:02 loss: -0.0340 Lr: 5.06005e-03 +[2025-02-22 11:58:19,284 INFO hook.py line 109 2775932] Train: [30/100][550/800] Data 0.002 (0.003) Batch 0.141 (0.144) Remain 02:14:51 loss: -0.2571 Lr: 5.05554e-03 +[2025-02-22 11:58:26,604 INFO hook.py line 109 2775932] Train: [30/100][600/800] Data 0.003 (0.003) Batch 0.125 (0.144) Remain 02:14:56 loss: -0.3764 Lr: 5.05102e-03 +[2025-02-22 11:58:33,805 INFO hook.py line 109 2775932] Train: [30/100][650/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 02:14:49 loss: -0.4390 Lr: 5.04649e-03 +[2025-02-22 11:58:41,046 INFO hook.py line 109 2775932] Train: [30/100][700/800] Data 0.003 (0.003) Batch 0.145 (0.144) Remain 02:14:45 loss: -0.6313 Lr: 5.04196e-03 +[2025-02-22 11:58:48,158 INFO hook.py line 109 2775932] Train: [30/100][750/800] Data 0.004 (0.003) Batch 0.133 (0.144) Remain 02:14:30 loss: -0.5657 Lr: 5.03741e-03 +[2025-02-22 11:58:55,159 INFO hook.py line 109 2775932] Train: [30/100][800/800] Data 0.002 (0.003) Batch 0.119 (0.144) Remain 02:14:09 loss: -0.2107 Lr: 5.03285e-03 +[2025-02-22 11:58:55,160 INFO misc.py line 135 2775932] Train result: loss: -0.3491 seg_loss: 0.2861 bias_l1_loss: 0.2820 bias_cosine_loss: -0.9172 +[2025-02-22 11:58:55,160 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 11:59:02,287 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6302 +[2025-02-22 11:59:02,627 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3329 +[2025-02-22 11:59:02,981 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3816 +[2025-02-22 11:59:03,072 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5092 +[2025-02-22 11:59:03,152 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5028 +[2025-02-22 11:59:03,212 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7654 +[2025-02-22 11:59:03,506 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4313 +[2025-02-22 11:59:03,535 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.1140 +[2025-02-22 11:59:03,670 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1707 +[2025-02-22 11:59:03,734 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1488 +[2025-02-22 11:59:03,973 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2041 +[2025-02-22 11:59:04,087 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0930 +[2025-02-22 11:59:04,162 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0916 +[2025-02-22 11:59:04,246 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2340 +[2025-02-22 11:59:04,322 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4562 +[2025-02-22 11:59:04,417 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6206 +[2025-02-22 11:59:04,551 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3601 +[2025-02-22 11:59:04,642 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1099 +[2025-02-22 11:59:04,811 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.3240 +[2025-02-22 11:59:04,876 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1096 +[2025-02-22 11:59:05,051 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5169 +[2025-02-22 11:59:05,252 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3256 +[2025-02-22 11:59:05,355 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1359 +[2025-02-22 11:59:05,425 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2449 +[2025-02-22 11:59:05,506 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0219 +[2025-02-22 11:59:05,584 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4885 +[2025-02-22 11:59:05,745 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0017 +[2025-02-22 11:59:05,835 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7310 +[2025-02-22 11:59:05,910 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5355 +[2025-02-22 11:59:05,994 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4153 +[2025-02-22 11:59:06,938 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3426 +[2025-02-22 11:59:07,080 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3002 +[2025-02-22 11:59:07,126 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6959 +[2025-02-22 11:59:07,227 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1529 +[2025-02-22 11:59:07,267 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6973 +[2025-02-22 11:59:07,397 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.5174 +[2025-02-22 11:59:07,465 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5420 +[2025-02-22 11:59:07,600 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5821 +[2025-02-22 11:59:07,754 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0810 +[2025-02-22 11:59:07,953 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7514 +[2025-02-22 11:59:08,120 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3292 +[2025-02-22 11:59:08,176 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0434 +[2025-02-22 11:59:08,221 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5934 +[2025-02-22 11:59:08,495 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5862 +[2025-02-22 11:59:08,542 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3682 +[2025-02-22 11:59:08,591 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5368 +[2025-02-22 11:59:08,684 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5324 +[2025-02-22 11:59:08,805 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1761 +[2025-02-22 11:59:08,904 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1627 +[2025-02-22 11:59:09,000 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1266 +[2025-02-22 11:59:09,088 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.4955 +[2025-02-22 11:59:09,213 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1543 +[2025-02-22 11:59:09,258 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6981 +[2025-02-22 11:59:09,353 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8487 +[2025-02-22 11:59:09,453 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7371 +[2025-02-22 11:59:09,501 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7016 +[2025-02-22 11:59:09,631 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1625 +[2025-02-22 11:59:09,676 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2381 +[2025-02-22 11:59:09,908 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1598 +[2025-02-22 11:59:10,021 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0500 +[2025-02-22 11:59:10,085 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7891 +[2025-02-22 11:59:10,140 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6143 +[2025-02-22 11:59:10,302 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1803 +[2025-02-22 11:59:10,430 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4193 +[2025-02-22 11:59:10,499 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1550 +[2025-02-22 11:59:10,622 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1213 +[2025-02-22 11:59:10,782 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5410 +[2025-02-22 11:59:10,866 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.4759 +[2025-02-22 11:59:10,918 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6996 +[2025-02-22 11:59:10,968 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1266 +[2025-02-22 11:59:11,100 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0023 +[2025-02-22 11:59:11,137 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3256 +[2025-02-22 11:59:11,187 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7394 +[2025-02-22 11:59:11,292 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8272 +[2025-02-22 11:59:11,500 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4968 +[2025-02-22 11:59:11,609 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1515 +[2025-02-22 11:59:11,771 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3170 +[2025-02-22 11:59:11,863 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3965 +[2025-02-22 11:59:22,862 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 11:59:22,862 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 11:59:22,862 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 11:59:22,862 INFO evaluator.py line 547 2775932] cabinet : 0.1970 0.4142 0.6446 +[2025-02-22 11:59:22,862 INFO evaluator.py line 547 2775932] bed : 0.3231 0.6677 0.8545 +[2025-02-22 11:59:22,862 INFO evaluator.py line 547 2775932] chair : 0.7060 0.8634 0.9133 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] sofa : 0.4044 0.6563 0.8229 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] table : 0.3047 0.4874 0.6405 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] door : 0.1826 0.3744 0.5058 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] window : 0.1728 0.3447 0.5796 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] bookshelf : 0.1443 0.4256 0.6897 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] picture : 0.3054 0.4614 0.5742 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] counter : 0.0359 0.1447 0.4870 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] desk : 0.0804 0.3169 0.7187 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] curtain : 0.2000 0.3425 0.5156 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] refridgerator : 0.2787 0.3783 0.4246 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] shower curtain : 0.4285 0.6531 0.8214 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] toilet : 0.7949 0.9643 0.9828 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] sink : 0.2510 0.5017 0.8314 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] bathtub : 0.6075 0.7443 0.8567 +[2025-02-22 11:59:22,863 INFO evaluator.py line 547 2775932] otherfurniture : 0.3669 0.5445 0.6712 +[2025-02-22 11:59:22,863 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 11:59:22,863 INFO evaluator.py line 554 2775932] average : 0.3213 0.5159 0.6963 +[2025-02-22 11:59:22,863 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 11:59:22,863 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 11:59:22,903 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 11:59:22,907 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 11:59:31,044 INFO hook.py line 109 2775932] Train: [31/100][50/800] Data 0.004 (0.003) Batch 0.164 (0.141) Remain 02:11:17 loss: -0.4733 Lr: 5.02829e-03 +[2025-02-22 11:59:38,255 INFO hook.py line 109 2775932] Train: [31/100][100/800] Data 0.003 (0.003) Batch 0.145 (0.143) Remain 02:12:49 loss: -0.2633 Lr: 5.02372e-03 +[2025-02-22 11:59:45,402 INFO hook.py line 109 2775932] Train: [31/100][150/800] Data 0.003 (0.003) Batch 0.146 (0.143) Remain 02:12:49 loss: -0.3075 Lr: 5.01914e-03 +[2025-02-22 11:59:52,532 INFO hook.py line 109 2775932] Train: [31/100][200/800] Data 0.002 (0.003) Batch 0.161 (0.143) Remain 02:12:40 loss: -0.3233 Lr: 5.01455e-03 +[2025-02-22 11:59:59,994 INFO hook.py line 109 2775932] Train: [31/100][250/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 02:13:47 loss: -0.4420 Lr: 5.00995e-03 +[2025-02-22 12:00:07,703 INFO hook.py line 109 2775932] Train: [31/100][300/800] Data 0.003 (0.004) Batch 0.147 (0.146) Remain 02:15:16 loss: -0.4810 Lr: 5.00534e-03 +[2025-02-22 12:00:14,882 INFO hook.py line 109 2775932] Train: [31/100][350/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 02:14:51 loss: -0.2836 Lr: 5.00072e-03 +[2025-02-22 12:00:21,859 INFO hook.py line 109 2775932] Train: [31/100][400/800] Data 0.003 (0.003) Batch 0.166 (0.145) Remain 02:14:03 loss: -0.5815 Lr: 4.99610e-03 +[2025-02-22 12:00:28,950 INFO hook.py line 109 2775932] Train: [31/100][450/800] Data 0.003 (0.003) Batch 0.142 (0.144) Remain 02:13:38 loss: -0.2138 Lr: 4.99147e-03 +[2025-02-22 12:00:36,017 INFO hook.py line 109 2775932] Train: [31/100][500/800] Data 0.002 (0.003) Batch 0.165 (0.144) Remain 02:13:14 loss: -0.0685 Lr: 4.98683e-03 +[2025-02-22 12:00:43,084 INFO hook.py line 109 2775932] Train: [31/100][550/800] Data 0.003 (0.003) Batch 0.138 (0.144) Remain 02:12:53 loss: -0.4638 Lr: 4.98218e-03 +[2025-02-22 12:00:50,667 INFO hook.py line 109 2775932] Train: [31/100][600/800] Data 0.003 (0.003) Batch 0.123 (0.144) Remain 02:13:22 loss: -0.0994 Lr: 4.97752e-03 +[2025-02-22 12:00:57,750 INFO hook.py line 109 2775932] Train: [31/100][650/800] Data 0.003 (0.003) Batch 0.138 (0.144) Remain 02:13:03 loss: -0.3944 Lr: 4.97285e-03 +[2025-02-22 12:01:04,779 INFO hook.py line 109 2775932] Train: [31/100][700/800] Data 0.003 (0.003) Batch 0.148 (0.144) Remain 02:12:41 loss: -0.5285 Lr: 4.96818e-03 +[2025-02-22 12:01:11,738 INFO hook.py line 109 2775932] Train: [31/100][750/800] Data 0.003 (0.003) Batch 0.145 (0.144) Remain 02:12:16 loss: -0.5167 Lr: 4.96349e-03 +[2025-02-22 12:01:18,929 INFO hook.py line 109 2775932] Train: [31/100][800/800] Data 0.003 (0.003) Batch 0.127 (0.144) Remain 02:12:10 loss: -0.2427 Lr: 4.95880e-03 +[2025-02-22 12:01:18,930 INFO misc.py line 135 2775932] Train result: loss: -0.3435 seg_loss: 0.2916 bias_l1_loss: 0.2818 bias_cosine_loss: -0.9169 +[2025-02-22 12:01:18,930 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:01:26,095 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6414 +[2025-02-22 12:01:26,342 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2750 +[2025-02-22 12:01:26,425 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.3733 +[2025-02-22 12:01:26,515 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4886 +[2025-02-22 12:01:26,581 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.3761 +[2025-02-22 12:01:26,636 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7294 +[2025-02-22 12:01:26,931 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3988 +[2025-02-22 12:01:26,973 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3925 +[2025-02-22 12:01:27,143 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0890 +[2025-02-22 12:01:27,211 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1527 +[2025-02-22 12:01:27,469 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0015 +[2025-02-22 12:01:27,615 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1859 +[2025-02-22 12:01:27,706 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5428 +[2025-02-22 12:01:27,815 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2988 +[2025-02-22 12:01:27,918 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8402 +[2025-02-22 12:01:28,009 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5263 +[2025-02-22 12:01:28,150 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5031 +[2025-02-22 12:01:28,267 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1166 +[2025-02-22 12:01:28,439 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0144 +[2025-02-22 12:01:28,512 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3290 +[2025-02-22 12:01:28,655 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5692 +[2025-02-22 12:01:28,850 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0741 +[2025-02-22 12:01:28,922 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0626 +[2025-02-22 12:01:28,974 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2948 +[2025-02-22 12:01:29,035 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4041 +[2025-02-22 12:01:29,092 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4658 +[2025-02-22 12:01:29,237 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1584 +[2025-02-22 12:01:29,335 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0658 +[2025-02-22 12:01:29,403 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4252 +[2025-02-22 12:01:29,474 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4643 +[2025-02-22 12:01:30,374 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3219 +[2025-02-22 12:01:30,507 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.6065 +[2025-02-22 12:01:30,550 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6556 +[2025-02-22 12:01:30,664 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2044 +[2025-02-22 12:01:30,707 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6941 +[2025-02-22 12:01:30,838 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6514 +[2025-02-22 12:01:30,903 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4335 +[2025-02-22 12:01:31,046 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4925 +[2025-02-22 12:01:31,211 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2110 +[2025-02-22 12:01:31,409 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9117 +[2025-02-22 12:01:31,580 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1929 +[2025-02-22 12:01:31,629 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1780 +[2025-02-22 12:01:31,669 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5275 +[2025-02-22 12:01:31,928 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6085 +[2025-02-22 12:01:31,972 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3030 +[2025-02-22 12:01:32,019 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5523 +[2025-02-22 12:01:32,113 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4405 +[2025-02-22 12:01:32,237 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1149 +[2025-02-22 12:01:32,339 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1611 +[2025-02-22 12:01:32,426 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4012 +[2025-02-22 12:01:32,503 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.3952 +[2025-02-22 12:01:32,632 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2735 +[2025-02-22 12:01:32,674 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7307 +[2025-02-22 12:01:32,779 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.6307 +[2025-02-22 12:01:32,866 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7749 +[2025-02-22 12:01:32,905 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7258 +[2025-02-22 12:01:33,037 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1534 +[2025-02-22 12:01:33,078 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3294 +[2025-02-22 12:01:33,307 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.0078 +[2025-02-22 12:01:33,395 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2709 +[2025-02-22 12:01:33,473 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.2572 +[2025-02-22 12:01:33,528 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4215 +[2025-02-22 12:01:33,686 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1112 +[2025-02-22 12:01:33,793 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4069 +[2025-02-22 12:01:33,871 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1377 +[2025-02-22 12:01:33,988 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1506 +[2025-02-22 12:01:34,149 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3170 +[2025-02-22 12:01:34,221 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5347 +[2025-02-22 12:01:34,267 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6661 +[2025-02-22 12:01:34,307 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1635 +[2025-02-22 12:01:34,422 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1024 +[2025-02-22 12:01:34,454 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4135 +[2025-02-22 12:01:34,499 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6972 +[2025-02-22 12:01:34,584 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.0853 +[2025-02-22 12:01:34,773 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6120 +[2025-02-22 12:01:34,839 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2094 +[2025-02-22 12:01:34,985 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5212 +[2025-02-22 12:01:35,061 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6789 +[2025-02-22 12:01:47,765 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:01:47,765 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:01:47,765 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] cabinet : 0.2146 0.4496 0.6740 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] bed : 0.3275 0.6439 0.7902 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] chair : 0.6916 0.8554 0.9107 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] sofa : 0.4094 0.6377 0.8527 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] table : 0.3497 0.5579 0.6994 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] door : 0.1597 0.3231 0.4659 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] window : 0.1123 0.2192 0.3800 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] bookshelf : 0.2127 0.5226 0.7879 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] picture : 0.1917 0.3096 0.4349 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] counter : 0.0188 0.0765 0.4511 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] desk : 0.0588 0.1962 0.5502 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] curtain : 0.1510 0.3431 0.4765 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] refridgerator : 0.2889 0.5006 0.6149 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] shower curtain : 0.4058 0.5764 0.6423 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] toilet : 0.7055 0.9471 0.9815 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] sink : 0.2491 0.5195 0.8763 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] bathtub : 0.6207 0.7939 0.8585 +[2025-02-22 12:01:47,765 INFO evaluator.py line 547 2775932] otherfurniture : 0.3512 0.5446 0.6764 +[2025-02-22 12:01:47,765 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:01:47,765 INFO evaluator.py line 554 2775932] average : 0.3066 0.5009 0.6735 +[2025-02-22 12:01:47,765 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:01:47,766 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:01:47,805 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:01:47,809 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:01:56,531 INFO hook.py line 109 2775932] Train: [32/100][50/800] Data 0.003 (0.007) Batch 0.124 (0.148) Remain 02:15:53 loss: -0.5492 Lr: 4.95410e-03 +[2025-02-22 12:02:03,758 INFO hook.py line 109 2775932] Train: [32/100][100/800] Data 0.003 (0.005) Batch 0.141 (0.146) Remain 02:14:11 loss: -0.2060 Lr: 4.94939e-03 +[2025-02-22 12:02:10,912 INFO hook.py line 109 2775932] Train: [32/100][150/800] Data 0.004 (0.004) Batch 0.141 (0.145) Remain 02:13:07 loss: -0.3052 Lr: 4.94468e-03 +[2025-02-22 12:02:18,307 INFO hook.py line 109 2775932] Train: [32/100][200/800] Data 0.003 (0.005) Batch 0.171 (0.146) Remain 02:13:38 loss: -0.4063 Lr: 4.93995e-03 +[2025-02-22 12:02:25,586 INFO hook.py line 109 2775932] Train: [32/100][250/800] Data 0.002 (0.004) Batch 0.140 (0.146) Remain 02:13:29 loss: -0.3900 Lr: 4.93522e-03 +[2025-02-22 12:02:32,516 INFO hook.py line 109 2775932] Train: [32/100][300/800] Data 0.002 (0.004) Batch 0.128 (0.145) Remain 02:12:16 loss: -0.2439 Lr: 4.93047e-03 +[2025-02-22 12:02:39,692 INFO hook.py line 109 2775932] Train: [32/100][350/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 02:12:00 loss: -0.3481 Lr: 4.92572e-03 +[2025-02-22 12:02:46,742 INFO hook.py line 109 2775932] Train: [32/100][400/800] Data 0.003 (0.004) Batch 0.152 (0.144) Remain 02:11:29 loss: -0.3817 Lr: 4.92097e-03 +[2025-02-22 12:02:53,732 INFO hook.py line 109 2775932] Train: [32/100][450/800] Data 0.002 (0.004) Batch 0.131 (0.144) Remain 02:10:57 loss: -0.3859 Lr: 4.91620e-03 +[2025-02-22 12:03:00,922 INFO hook.py line 109 2775932] Train: [32/100][500/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 02:10:51 loss: -0.5900 Lr: 4.91143e-03 +[2025-02-22 12:03:08,103 INFO hook.py line 109 2775932] Train: [32/100][550/800] Data 0.004 (0.004) Batch 0.127 (0.144) Remain 02:10:44 loss: -0.3964 Lr: 4.90674e-03 +[2025-02-22 12:03:15,345 INFO hook.py line 109 2775932] Train: [32/100][600/800] Data 0.003 (0.004) Batch 0.144 (0.144) Remain 02:10:43 loss: -0.4249 Lr: 4.90195e-03 +[2025-02-22 12:03:22,619 INFO hook.py line 109 2775932] Train: [32/100][650/800] Data 0.003 (0.003) Batch 0.138 (0.144) Remain 02:10:43 loss: -0.3014 Lr: 4.89715e-03 +[2025-02-22 12:03:29,709 INFO hook.py line 109 2775932] Train: [32/100][700/800] Data 0.002 (0.003) Batch 0.154 (0.144) Remain 02:10:28 loss: -0.3192 Lr: 4.89234e-03 +[2025-02-22 12:03:36,664 INFO hook.py line 109 2775932] Train: [32/100][750/800] Data 0.003 (0.003) Batch 0.142 (0.143) Remain 02:10:05 loss: -0.4022 Lr: 4.88753e-03 +[2025-02-22 12:03:43,708 INFO hook.py line 109 2775932] Train: [32/100][800/800] Data 0.003 (0.003) Batch 0.098 (0.143) Remain 02:09:49 loss: -0.4551 Lr: 4.88270e-03 +[2025-02-22 12:03:43,708 INFO misc.py line 135 2775932] Train result: loss: -0.3654 seg_loss: 0.2768 bias_l1_loss: 0.2762 bias_cosine_loss: -0.9184 +[2025-02-22 12:03:43,709 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:03:50,881 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6299 +[2025-02-22 12:03:51,126 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0403 +[2025-02-22 12:03:51,202 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2036 +[2025-02-22 12:03:51,272 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5357 +[2025-02-22 12:03:51,646 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4935 +[2025-02-22 12:03:51,716 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9190 +[2025-02-22 12:03:51,982 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4237 +[2025-02-22 12:03:52,013 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5637 +[2025-02-22 12:03:52,176 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1632 +[2025-02-22 12:03:52,239 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0299 +[2025-02-22 12:03:52,491 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0927 +[2025-02-22 12:03:52,604 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2942 +[2025-02-22 12:03:52,675 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5873 +[2025-02-22 12:03:52,769 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.4084 +[2025-02-22 12:03:52,863 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5684 +[2025-02-22 12:03:52,926 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6368 +[2025-02-22 12:03:53,064 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4063 +[2025-02-22 12:03:53,163 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1780 +[2025-02-22 12:03:53,344 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1555 +[2025-02-22 12:03:53,406 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1516 +[2025-02-22 12:03:53,586 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5981 +[2025-02-22 12:03:53,777 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.5249 +[2025-02-22 12:03:53,872 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1123 +[2025-02-22 12:03:53,942 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0554 +[2025-02-22 12:03:54,032 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2889 +[2025-02-22 12:03:54,098 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3307 +[2025-02-22 12:03:54,260 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3760 +[2025-02-22 12:03:54,362 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7156 +[2025-02-22 12:03:54,445 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6487 +[2025-02-22 12:03:54,522 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4451 +[2025-02-22 12:03:55,396 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3936 +[2025-02-22 12:03:55,546 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7508 +[2025-02-22 12:03:55,607 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7175 +[2025-02-22 12:03:55,714 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2986 +[2025-02-22 12:03:55,760 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5985 +[2025-02-22 12:03:55,891 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.3974 +[2025-02-22 12:03:55,961 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.2582 +[2025-02-22 12:03:56,097 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5989 +[2025-02-22 12:03:56,261 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6046 +[2025-02-22 12:03:56,460 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7733 +[2025-02-22 12:03:56,624 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4381 +[2025-02-22 12:03:56,675 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.2452 +[2025-02-22 12:03:56,724 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.4665 +[2025-02-22 12:03:56,972 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4733 +[2025-02-22 12:03:57,013 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3378 +[2025-02-22 12:03:57,060 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4029 +[2025-02-22 12:03:57,174 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0836 +[2025-02-22 12:03:57,293 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3075 +[2025-02-22 12:03:57,423 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0393 +[2025-02-22 12:03:57,518 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1245 +[2025-02-22 12:03:57,595 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1070 +[2025-02-22 12:03:57,740 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2242 +[2025-02-22 12:03:57,783 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6164 +[2025-02-22 12:03:57,896 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1090 +[2025-02-22 12:03:58,005 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7967 +[2025-02-22 12:03:58,064 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7217 +[2025-02-22 12:03:58,206 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0991 +[2025-02-22 12:03:58,253 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3123 +[2025-02-22 12:03:58,511 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2229 +[2025-02-22 12:03:58,636 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0370 +[2025-02-22 12:03:58,715 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5735 +[2025-02-22 12:03:58,785 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3330 +[2025-02-22 12:03:58,966 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.4916 +[2025-02-22 12:03:59,097 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.2708 +[2025-02-22 12:03:59,184 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4283 +[2025-02-22 12:03:59,328 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1591 +[2025-02-22 12:03:59,527 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4185 +[2025-02-22 12:03:59,615 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0354 +[2025-02-22 12:03:59,670 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7612 +[2025-02-22 12:03:59,727 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0215 +[2025-02-22 12:03:59,886 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.2736 +[2025-02-22 12:03:59,928 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5695 +[2025-02-22 12:03:59,984 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6032 +[2025-02-22 12:04:00,121 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2491 +[2025-02-22 12:04:00,343 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4863 +[2025-02-22 12:04:00,425 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0547 +[2025-02-22 12:04:00,587 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4436 +[2025-02-22 12:04:00,682 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5104 +[2025-02-22 12:04:13,263 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:04:13,263 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:04:13,263 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] cabinet : 0.2047 0.4520 0.6824 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] bed : 0.3123 0.6636 0.8023 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] chair : 0.6969 0.8536 0.9102 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] sofa : 0.3481 0.5817 0.7814 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] table : 0.3300 0.5553 0.6973 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] door : 0.1937 0.4238 0.5704 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] window : 0.1876 0.3580 0.5695 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] bookshelf : 0.2296 0.4880 0.7329 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] picture : 0.2207 0.3540 0.4090 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] counter : 0.0461 0.1934 0.4884 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] desk : 0.1007 0.3299 0.7334 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] curtain : 0.2215 0.3545 0.5622 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] refridgerator : 0.2207 0.3500 0.4035 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] shower curtain : 0.3134 0.4711 0.5064 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] toilet : 0.7727 0.9272 0.9605 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] sink : 0.2357 0.5882 0.7952 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] bathtub : 0.4101 0.6212 0.8033 +[2025-02-22 12:04:13,263 INFO evaluator.py line 547 2775932] otherfurniture : 0.3037 0.4673 0.6136 +[2025-02-22 12:04:13,263 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:04:13,263 INFO evaluator.py line 554 2775932] average : 0.2971 0.5018 0.6679 +[2025-02-22 12:04:13,264 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:04:13,264 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:04:13,311 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:04:13,314 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:04:22,008 INFO hook.py line 109 2775932] Train: [33/100][50/800] Data 0.002 (0.009) Batch 0.168 (0.152) Remain 02:17:49 loss: -0.3936 Lr: 4.87787e-03 +[2025-02-22 12:04:29,541 INFO hook.py line 109 2775932] Train: [33/100][100/800] Data 0.003 (0.007) Batch 0.163 (0.151) Remain 02:16:59 loss: -0.4942 Lr: 4.87303e-03 +[2025-02-22 12:04:36,803 INFO hook.py line 109 2775932] Train: [33/100][150/800] Data 0.003 (0.006) Batch 0.133 (0.149) Remain 02:14:59 loss: -0.5196 Lr: 4.86819e-03 +[2025-02-22 12:04:43,879 INFO hook.py line 109 2775932] Train: [33/100][200/800] Data 0.003 (0.005) Batch 0.126 (0.147) Remain 02:13:04 loss: -0.5094 Lr: 4.86333e-03 +[2025-02-22 12:04:51,122 INFO hook.py line 109 2775932] Train: [33/100][250/800] Data 0.003 (0.005) Batch 0.152 (0.147) Remain 02:12:30 loss: -0.3763 Lr: 4.85847e-03 +[2025-02-22 12:04:58,282 INFO hook.py line 109 2775932] Train: [33/100][300/800] Data 0.003 (0.004) Batch 0.144 (0.146) Remain 02:11:49 loss: -0.5071 Lr: 4.85360e-03 +[2025-02-22 12:05:05,495 INFO hook.py line 109 2775932] Train: [33/100][350/800] Data 0.007 (0.004) Batch 0.147 (0.146) Remain 02:11:27 loss: -0.3862 Lr: 4.84872e-03 +[2025-02-22 12:05:12,801 INFO hook.py line 109 2775932] Train: [33/100][400/800] Data 0.003 (0.004) Batch 0.140 (0.146) Remain 02:11:21 loss: -0.2819 Lr: 4.84383e-03 +[2025-02-22 12:05:19,847 INFO hook.py line 109 2775932] Train: [33/100][450/800] Data 0.002 (0.004) Batch 0.122 (0.145) Remain 02:10:43 loss: -0.4340 Lr: 4.83894e-03 +[2025-02-22 12:05:27,018 INFO hook.py line 109 2775932] Train: [33/100][500/800] Data 0.002 (0.004) Batch 0.129 (0.145) Remain 02:10:25 loss: -0.4127 Lr: 4.83403e-03 +[2025-02-22 12:05:34,546 INFO hook.py line 109 2775932] Train: [33/100][550/800] Data 0.003 (0.004) Batch 0.130 (0.146) Remain 02:10:45 loss: -0.5028 Lr: 4.82912e-03 +[2025-02-22 12:05:41,605 INFO hook.py line 109 2775932] Train: [33/100][600/800] Data 0.002 (0.004) Batch 0.135 (0.145) Remain 02:10:17 loss: -0.4033 Lr: 4.82420e-03 +[2025-02-22 12:05:48,790 INFO hook.py line 109 2775932] Train: [33/100][650/800] Data 0.003 (0.004) Batch 0.131 (0.145) Remain 02:10:03 loss: -0.4535 Lr: 4.81928e-03 +[2025-02-22 12:05:55,923 INFO hook.py line 109 2775932] Train: [33/100][700/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 02:09:46 loss: -0.4258 Lr: 4.81434e-03 +[2025-02-22 12:06:02,918 INFO hook.py line 109 2775932] Train: [33/100][750/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 02:09:20 loss: -0.4840 Lr: 4.80940e-03 +[2025-02-22 12:06:09,997 INFO hook.py line 109 2775932] Train: [33/100][800/800] Data 0.001 (0.003) Batch 0.153 (0.144) Remain 02:09:03 loss: -0.3961 Lr: 4.80445e-03 +[2025-02-22 12:06:09,998 INFO misc.py line 135 2775932] Train result: loss: -0.3737 seg_loss: 0.2718 bias_l1_loss: 0.2738 bias_cosine_loss: -0.9193 +[2025-02-22 12:06:09,998 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:06:17,119 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7037 +[2025-02-22 12:06:17,418 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.0566 +[2025-02-22 12:06:17,510 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4901 +[2025-02-22 12:06:17,586 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4055 +[2025-02-22 12:06:17,725 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5567 +[2025-02-22 12:06:17,797 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8481 +[2025-02-22 12:06:18,079 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3287 +[2025-02-22 12:06:18,109 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4700 +[2025-02-22 12:06:18,254 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0726 +[2025-02-22 12:06:18,309 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3921 +[2025-02-22 12:06:18,545 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1225 +[2025-02-22 12:06:18,658 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1846 +[2025-02-22 12:06:18,726 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.2134 +[2025-02-22 12:06:18,820 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0514 +[2025-02-22 12:06:18,900 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1045 +[2025-02-22 12:06:18,967 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4934 +[2025-02-22 12:06:19,099 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4857 +[2025-02-22 12:06:19,185 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3117 +[2025-02-22 12:06:19,323 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1890 +[2025-02-22 12:06:19,380 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1096 +[2025-02-22 12:06:19,525 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5452 +[2025-02-22 12:06:19,712 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0339 +[2025-02-22 12:06:19,791 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0917 +[2025-02-22 12:06:19,844 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0669 +[2025-02-22 12:06:19,899 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3274 +[2025-02-22 12:06:19,960 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3905 +[2025-02-22 12:06:20,107 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2315 +[2025-02-22 12:06:20,188 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.9468 +[2025-02-22 12:06:20,254 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5615 +[2025-02-22 12:06:20,317 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4729 +[2025-02-22 12:06:21,126 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4652 +[2025-02-22 12:06:21,244 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3173 +[2025-02-22 12:06:21,301 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6675 +[2025-02-22 12:06:21,387 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0104 +[2025-02-22 12:06:21,420 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6417 +[2025-02-22 12:06:21,522 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1791 +[2025-02-22 12:06:21,586 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4667 +[2025-02-22 12:06:21,702 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5542 +[2025-02-22 12:06:21,829 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2243 +[2025-02-22 12:06:22,004 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5876 +[2025-02-22 12:06:22,143 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6405 +[2025-02-22 12:06:22,183 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0910 +[2025-02-22 12:06:22,236 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5803 +[2025-02-22 12:06:22,481 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6003 +[2025-02-22 12:06:22,513 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4451 +[2025-02-22 12:06:22,549 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5489 +[2025-02-22 12:06:22,662 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3232 +[2025-02-22 12:06:22,777 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0734 +[2025-02-22 12:06:22,887 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.3686 +[2025-02-22 12:06:22,972 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2057 +[2025-02-22 12:06:23,042 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1311 +[2025-02-22 12:06:23,169 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2405 +[2025-02-22 12:06:23,207 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7228 +[2025-02-22 12:06:23,308 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 3.0288 +[2025-02-22 12:06:23,432 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7578 +[2025-02-22 12:06:23,477 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7468 +[2025-02-22 12:06:23,619 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0754 +[2025-02-22 12:06:23,659 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3640 +[2025-02-22 12:06:23,874 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2225 +[2025-02-22 12:06:23,980 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0660 +[2025-02-22 12:06:24,050 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8817 +[2025-02-22 12:06:24,117 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5205 +[2025-02-22 12:06:24,272 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0275 +[2025-02-22 12:06:24,383 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.8051 +[2025-02-22 12:06:24,448 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1829 +[2025-02-22 12:06:24,716 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0270 +[2025-02-22 12:06:24,889 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3699 +[2025-02-22 12:06:24,974 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1474 +[2025-02-22 12:06:25,023 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6786 +[2025-02-22 12:06:25,072 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1529 +[2025-02-22 12:06:25,222 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0124 +[2025-02-22 12:06:25,258 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5353 +[2025-02-22 12:06:25,321 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6399 +[2025-02-22 12:06:25,415 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 3.5995 +[2025-02-22 12:06:25,608 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5682 +[2025-02-22 12:06:25,689 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1655 +[2025-02-22 12:06:25,868 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4665 +[2025-02-22 12:06:25,954 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4974 +[2025-02-22 12:06:39,787 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:06:39,787 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:06:39,787 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] cabinet : 0.2084 0.4250 0.6963 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] bed : 0.3611 0.7226 0.8393 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] chair : 0.7250 0.8959 0.9369 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] sofa : 0.3565 0.5700 0.8229 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] table : 0.3845 0.5629 0.6950 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] door : 0.1935 0.3958 0.5421 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] window : 0.1538 0.3242 0.5075 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] bookshelf : 0.1414 0.4675 0.8296 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] picture : 0.2714 0.4250 0.5136 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] counter : 0.0344 0.1129 0.5785 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] desk : 0.0653 0.2664 0.6675 +[2025-02-22 12:06:39,787 INFO evaluator.py line 547 2775932] curtain : 0.2255 0.3623 0.6179 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] refridgerator : 0.2764 0.3775 0.4340 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] shower curtain : 0.4176 0.6194 0.6194 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] toilet : 0.7764 0.9297 0.9464 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] sink : 0.2444 0.5029 0.8113 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] bathtub : 0.6145 0.7953 0.8588 +[2025-02-22 12:06:39,788 INFO evaluator.py line 547 2775932] otherfurniture : 0.3846 0.5659 0.7031 +[2025-02-22 12:06:39,788 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:06:39,788 INFO evaluator.py line 554 2775932] average : 0.3242 0.5179 0.7011 +[2025-02-22 12:06:39,788 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:06:39,788 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:06:39,829 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:06:39,832 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:06:48,646 INFO hook.py line 109 2775932] Train: [34/100][50/800] Data 0.003 (0.003) Batch 0.145 (0.143) Remain 02:07:18 loss: -0.3927 Lr: 4.79950e-03 +[2025-02-22 12:06:55,957 INFO hook.py line 109 2775932] Train: [34/100][100/800] Data 0.003 (0.003) Batch 0.155 (0.144) Remain 02:08:49 loss: -0.2985 Lr: 4.79453e-03 +[2025-02-22 12:07:03,021 INFO hook.py line 109 2775932] Train: [34/100][150/800] Data 0.003 (0.003) Batch 0.155 (0.143) Remain 02:07:43 loss: -0.5755 Lr: 4.78956e-03 +[2025-02-22 12:07:10,069 INFO hook.py line 109 2775932] Train: [34/100][200/800] Data 0.002 (0.003) Batch 0.129 (0.143) Remain 02:07:04 loss: -0.3549 Lr: 4.78458e-03 +[2025-02-22 12:07:17,384 INFO hook.py line 109 2775932] Train: [34/100][250/800] Data 0.003 (0.004) Batch 0.156 (0.143) Remain 02:07:34 loss: -0.2016 Lr: 4.77959e-03 +[2025-02-22 12:07:24,717 INFO hook.py line 109 2775932] Train: [34/100][300/800] Data 0.003 (0.004) Batch 0.122 (0.144) Remain 02:07:56 loss: -0.2843 Lr: 4.77460e-03 +[2025-02-22 12:07:31,841 INFO hook.py line 109 2775932] Train: [34/100][350/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 02:07:37 loss: -0.1290 Lr: 4.76959e-03 +[2025-02-22 12:07:39,039 INFO hook.py line 109 2775932] Train: [34/100][400/800] Data 0.003 (0.003) Batch 0.141 (0.144) Remain 02:07:31 loss: -0.3145 Lr: 4.76458e-03 +[2025-02-22 12:07:46,657 INFO hook.py line 109 2775932] Train: [34/100][450/800] Data 0.003 (0.003) Batch 0.156 (0.145) Remain 02:08:14 loss: -0.3378 Lr: 4.75956e-03 +[2025-02-22 12:07:53,997 INFO hook.py line 109 2775932] Train: [34/100][500/800] Data 0.003 (0.003) Batch 0.137 (0.145) Remain 02:08:18 loss: -0.3966 Lr: 4.75454e-03 +[2025-02-22 12:08:01,289 INFO hook.py line 109 2775932] Train: [34/100][550/800] Data 0.003 (0.003) Batch 0.159 (0.145) Remain 02:08:15 loss: -0.4641 Lr: 4.74951e-03 +[2025-02-22 12:08:08,491 INFO hook.py line 109 2775932] Train: [34/100][600/800] Data 0.002 (0.003) Batch 0.166 (0.145) Remain 02:08:03 loss: -0.1684 Lr: 4.74447e-03 +[2025-02-22 12:08:15,632 INFO hook.py line 109 2775932] Train: [34/100][650/800] Data 0.003 (0.003) Batch 0.136 (0.145) Remain 02:07:47 loss: -0.3560 Lr: 4.73942e-03 +[2025-02-22 12:08:22,988 INFO hook.py line 109 2775932] Train: [34/100][700/800] Data 0.002 (0.003) Batch 0.123 (0.145) Remain 02:07:48 loss: -0.3625 Lr: 4.73436e-03 +[2025-02-22 12:08:30,141 INFO hook.py line 109 2775932] Train: [34/100][750/800] Data 0.002 (0.003) Batch 0.161 (0.145) Remain 02:07:34 loss: -0.4524 Lr: 4.72930e-03 +[2025-02-22 12:08:37,104 INFO hook.py line 109 2775932] Train: [34/100][800/800] Data 0.002 (0.003) Batch 0.114 (0.144) Remain 02:07:09 loss: -0.2082 Lr: 4.72423e-03 +[2025-02-22 12:08:37,105 INFO misc.py line 135 2775932] Train result: loss: -0.3585 seg_loss: 0.2809 bias_l1_loss: 0.2791 bias_cosine_loss: -0.9185 +[2025-02-22 12:08:37,105 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:08:44,084 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7260 +[2025-02-22 12:08:45,025 INFO evaluator.py line 595 2775932] Test: [2/78] Loss 0.1444 +[2025-02-22 12:08:45,087 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4921 +[2025-02-22 12:08:45,163 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4256 +[2025-02-22 12:08:45,230 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5322 +[2025-02-22 12:08:45,302 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7105 +[2025-02-22 12:08:45,592 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4115 +[2025-02-22 12:08:45,620 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3993 +[2025-02-22 12:08:45,785 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0300 +[2025-02-22 12:08:45,841 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2403 +[2025-02-22 12:08:46,087 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3634 +[2025-02-22 12:08:46,221 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1248 +[2025-02-22 12:08:46,306 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.7903 +[2025-02-22 12:08:46,407 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0533 +[2025-02-22 12:08:46,486 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.9139 +[2025-02-22 12:08:46,574 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4991 +[2025-02-22 12:08:46,704 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2769 +[2025-02-22 12:08:46,792 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.5713 +[2025-02-22 12:08:46,953 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1441 +[2025-02-22 12:08:47,014 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2335 +[2025-02-22 12:08:47,163 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5529 +[2025-02-22 12:08:47,320 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3599 +[2025-02-22 12:08:47,397 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.5226 +[2025-02-22 12:08:47,449 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2102 +[2025-02-22 12:08:47,504 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2432 +[2025-02-22 12:08:47,561 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3332 +[2025-02-22 12:08:47,695 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4286 +[2025-02-22 12:08:47,785 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8808 +[2025-02-22 12:08:47,865 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5548 +[2025-02-22 12:08:47,931 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4877 +[2025-02-22 12:08:48,766 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3007 +[2025-02-22 12:08:48,923 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5586 +[2025-02-22 12:08:48,968 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6912 +[2025-02-22 12:08:49,101 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2286 +[2025-02-22 12:08:49,140 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5822 +[2025-02-22 12:08:49,263 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0664 +[2025-02-22 12:08:49,332 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4596 +[2025-02-22 12:08:49,480 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5120 +[2025-02-22 12:08:49,643 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8330 +[2025-02-22 12:08:49,857 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8222 +[2025-02-22 12:08:50,025 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3510 +[2025-02-22 12:08:50,084 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0561 +[2025-02-22 12:08:50,131 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5492 +[2025-02-22 12:08:50,395 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4823 +[2025-02-22 12:08:50,441 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2856 +[2025-02-22 12:08:50,483 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.6141 +[2025-02-22 12:08:50,594 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.9628 +[2025-02-22 12:08:50,703 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0575 +[2025-02-22 12:08:50,799 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0360 +[2025-02-22 12:08:50,880 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.7357 +[2025-02-22 12:08:50,955 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0010 +[2025-02-22 12:08:51,082 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.0381 +[2025-02-22 12:08:51,125 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7184 +[2025-02-22 12:08:51,222 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1690 +[2025-02-22 12:08:51,312 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7848 +[2025-02-22 12:08:51,357 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7354 +[2025-02-22 12:08:51,486 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2479 +[2025-02-22 12:08:51,538 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3886 +[2025-02-22 12:08:51,759 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2938 +[2025-02-22 12:08:51,857 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0393 +[2025-02-22 12:08:51,945 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.9551 +[2025-02-22 12:08:52,000 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.1819 +[2025-02-22 12:08:52,165 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0798 +[2025-02-22 12:08:52,284 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6345 +[2025-02-22 12:08:52,387 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.4285 +[2025-02-22 12:08:52,496 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3180 +[2025-02-22 12:08:52,639 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3608 +[2025-02-22 12:08:52,709 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.7701 +[2025-02-22 12:08:52,757 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8087 +[2025-02-22 12:08:52,802 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2813 +[2025-02-22 12:08:52,952 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.3419 +[2025-02-22 12:08:52,985 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3796 +[2025-02-22 12:08:53,033 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7505 +[2025-02-22 12:08:53,120 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.1399 +[2025-02-22 12:08:53,305 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4068 +[2025-02-22 12:08:53,380 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2842 +[2025-02-22 12:08:53,538 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4739 +[2025-02-22 12:08:53,630 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.3736 +[2025-02-22 12:09:04,787 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:09:04,787 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:09:04,787 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] cabinet : 0.1895 0.4131 0.6598 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] bed : 0.2922 0.6256 0.7362 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] chair : 0.6985 0.8600 0.9119 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] sofa : 0.3278 0.5013 0.8034 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] table : 0.3311 0.5464 0.6714 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] door : 0.1194 0.2421 0.3764 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] window : 0.1586 0.3256 0.5243 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] bookshelf : 0.1654 0.4531 0.6685 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] picture : 0.1719 0.2839 0.3584 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] counter : 0.0327 0.1386 0.5836 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] desk : 0.1176 0.3326 0.8039 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] curtain : 0.2087 0.3590 0.5185 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] refridgerator : 0.2365 0.3033 0.3354 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] shower curtain : 0.3330 0.5690 0.6233 +[2025-02-22 12:09:04,787 INFO evaluator.py line 547 2775932] toilet : 0.6559 0.8183 0.9135 +[2025-02-22 12:09:04,788 INFO evaluator.py line 547 2775932] sink : 0.2384 0.4692 0.7967 +[2025-02-22 12:09:04,788 INFO evaluator.py line 547 2775932] bathtub : 0.6153 0.7617 0.8673 +[2025-02-22 12:09:04,788 INFO evaluator.py line 547 2775932] otherfurniture : 0.3589 0.5433 0.6629 +[2025-02-22 12:09:04,788 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:09:04,788 INFO evaluator.py line 554 2775932] average : 0.2917 0.4748 0.6564 +[2025-02-22 12:09:04,788 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:09:04,788 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:09:04,825 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:09:04,830 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:09:13,306 INFO hook.py line 109 2775932] Train: [35/100][50/800] Data 0.004 (0.008) Batch 0.160 (0.147) Remain 02:09:22 loss: -0.2447 Lr: 4.71915e-03 +[2025-02-22 12:09:20,740 INFO hook.py line 109 2775932] Train: [35/100][100/800] Data 0.003 (0.007) Batch 0.116 (0.148) Remain 02:09:56 loss: -0.5261 Lr: 4.71407e-03 +[2025-02-22 12:09:27,919 INFO hook.py line 109 2775932] Train: [35/100][150/800] Data 0.003 (0.006) Batch 0.157 (0.146) Remain 02:08:31 loss: -0.4859 Lr: 4.70898e-03 +[2025-02-22 12:09:35,206 INFO hook.py line 109 2775932] Train: [35/100][200/800] Data 0.003 (0.005) Batch 0.145 (0.146) Remain 02:08:13 loss: -0.4994 Lr: 4.70388e-03 +[2025-02-22 12:09:42,395 INFO hook.py line 109 2775932] Train: [35/100][250/800] Data 0.003 (0.005) Batch 0.140 (0.146) Remain 02:07:40 loss: -0.3518 Lr: 4.69877e-03 +[2025-02-22 12:09:49,762 INFO hook.py line 109 2775932] Train: [35/100][300/800] Data 0.003 (0.004) Batch 0.144 (0.146) Remain 02:07:46 loss: -0.4790 Lr: 4.69366e-03 +[2025-02-22 12:09:56,913 INFO hook.py line 109 2775932] Train: [35/100][350/800] Data 0.003 (0.004) Batch 0.147 (0.146) Remain 02:07:16 loss: -0.2900 Lr: 4.68853e-03 +[2025-02-22 12:10:04,004 INFO hook.py line 109 2775932] Train: [35/100][400/800] Data 0.003 (0.004) Batch 0.157 (0.145) Remain 02:06:44 loss: -0.3276 Lr: 4.68341e-03 +[2025-02-22 12:10:10,972 INFO hook.py line 109 2775932] Train: [35/100][450/800] Data 0.004 (0.004) Batch 0.132 (0.144) Remain 02:06:03 loss: -0.5315 Lr: 4.67827e-03 +[2025-02-22 12:10:18,296 INFO hook.py line 109 2775932] Train: [35/100][500/800] Data 0.002 (0.004) Batch 0.138 (0.145) Remain 02:06:06 loss: -0.4383 Lr: 4.67313e-03 +[2025-02-22 12:10:25,330 INFO hook.py line 109 2775932] Train: [35/100][550/800] Data 0.003 (0.004) Batch 0.130 (0.144) Remain 02:05:40 loss: -0.5677 Lr: 4.66798e-03 +[2025-02-22 12:10:32,410 INFO hook.py line 109 2775932] Train: [35/100][600/800] Data 0.003 (0.004) Batch 0.152 (0.144) Remain 02:05:21 loss: -0.6807 Lr: 4.66282e-03 +[2025-02-22 12:10:39,584 INFO hook.py line 109 2775932] Train: [35/100][650/800] Data 0.004 (0.004) Batch 0.145 (0.144) Remain 02:05:11 loss: -0.3504 Lr: 4.65766e-03 +[2025-02-22 12:10:46,681 INFO hook.py line 109 2775932] Train: [35/100][700/800] Data 0.003 (0.004) Batch 0.152 (0.144) Remain 02:04:56 loss: -0.3790 Lr: 4.65249e-03 +[2025-02-22 12:10:54,169 INFO hook.py line 109 2775932] Train: [35/100][750/800] Data 0.003 (0.004) Batch 0.154 (0.144) Remain 02:05:09 loss: -0.5187 Lr: 4.64731e-03 +[2025-02-22 12:11:01,036 INFO hook.py line 109 2775932] Train: [35/100][800/800] Data 0.001 (0.003) Batch 0.113 (0.144) Remain 02:04:39 loss: -0.3821 Lr: 4.64212e-03 +[2025-02-22 12:11:01,036 INFO misc.py line 135 2775932] Train result: loss: -0.3876 seg_loss: 0.2632 bias_l1_loss: 0.2696 bias_cosine_loss: -0.9205 +[2025-02-22 12:11:01,037 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:11:08,132 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6980 +[2025-02-22 12:11:08,426 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3024 +[2025-02-22 12:11:08,588 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4699 +[2025-02-22 12:11:08,667 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5612 +[2025-02-22 12:11:08,731 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5886 +[2025-02-22 12:11:08,802 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5821 +[2025-02-22 12:11:09,160 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5104 +[2025-02-22 12:11:09,191 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5257 +[2025-02-22 12:11:09,339 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.1303 +[2025-02-22 12:11:09,404 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0541 +[2025-02-22 12:11:09,657 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0165 +[2025-02-22 12:11:09,776 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.3829 +[2025-02-22 12:11:09,845 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.6538 +[2025-02-22 12:11:09,929 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8140 +[2025-02-22 12:11:10,010 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3154 +[2025-02-22 12:11:10,098 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5681 +[2025-02-22 12:11:10,237 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4957 +[2025-02-22 12:11:10,333 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3200 +[2025-02-22 12:11:10,513 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0444 +[2025-02-22 12:11:10,584 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1531 +[2025-02-22 12:11:10,736 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5414 +[2025-02-22 12:11:10,920 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3738 +[2025-02-22 12:11:10,995 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2135 +[2025-02-22 12:11:11,075 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1534 +[2025-02-22 12:11:11,138 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0201 +[2025-02-22 12:11:11,196 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5691 +[2025-02-22 12:11:11,346 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2587 +[2025-02-22 12:11:11,438 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6511 +[2025-02-22 12:11:11,549 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5951 +[2025-02-22 12:11:11,620 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5317 +[2025-02-22 12:11:12,483 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3473 +[2025-02-22 12:11:12,603 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4211 +[2025-02-22 12:11:12,643 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7091 +[2025-02-22 12:11:12,739 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2506 +[2025-02-22 12:11:12,779 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6631 +[2025-02-22 12:11:12,904 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1857 +[2025-02-22 12:11:12,984 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5632 +[2025-02-22 12:11:13,114 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5562 +[2025-02-22 12:11:13,288 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0460 +[2025-02-22 12:11:13,502 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6902 +[2025-02-22 12:11:13,677 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1485 +[2025-02-22 12:11:13,728 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0089 +[2025-02-22 12:11:13,773 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6651 +[2025-02-22 12:11:14,046 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5474 +[2025-02-22 12:11:14,086 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2807 +[2025-02-22 12:11:14,125 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4179 +[2025-02-22 12:11:14,227 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7030 +[2025-02-22 12:11:14,347 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1882 +[2025-02-22 12:11:14,449 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2082 +[2025-02-22 12:11:14,539 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0510 +[2025-02-22 12:11:14,617 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1077 +[2025-02-22 12:11:14,761 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4285 +[2025-02-22 12:11:14,799 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6563 +[2025-02-22 12:11:14,904 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8226 +[2025-02-22 12:11:14,998 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7845 +[2025-02-22 12:11:15,050 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7337 +[2025-02-22 12:11:15,184 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2548 +[2025-02-22 12:11:15,223 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3501 +[2025-02-22 12:11:15,448 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2794 +[2025-02-22 12:11:15,544 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2385 +[2025-02-22 12:11:15,617 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7490 +[2025-02-22 12:11:15,672 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5368 +[2025-02-22 12:11:15,839 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1529 +[2025-02-22 12:11:15,956 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3403 +[2025-02-22 12:11:16,026 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3369 +[2025-02-22 12:11:16,163 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2143 +[2025-02-22 12:11:16,357 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5833 +[2025-02-22 12:11:16,443 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0513 +[2025-02-22 12:11:16,502 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7358 +[2025-02-22 12:11:16,558 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2632 +[2025-02-22 12:11:16,726 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1676 +[2025-02-22 12:11:16,767 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5364 +[2025-02-22 12:11:16,829 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7275 +[2025-02-22 12:11:16,931 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.9308 +[2025-02-22 12:11:17,142 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5552 +[2025-02-22 12:11:17,221 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0554 +[2025-02-22 12:11:17,399 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4638 +[2025-02-22 12:11:17,489 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5143 +[2025-02-22 12:11:31,002 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:11:31,002 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:11:31,003 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] cabinet : 0.2548 0.4926 0.6930 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] bed : 0.3518 0.6991 0.8400 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] chair : 0.7177 0.8830 0.9308 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] sofa : 0.3297 0.5505 0.8036 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] table : 0.3692 0.6246 0.7500 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] door : 0.2071 0.4196 0.5524 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] window : 0.1566 0.3120 0.5558 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] bookshelf : 0.1992 0.4548 0.6844 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] picture : 0.2207 0.3359 0.3943 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] counter : 0.0242 0.0710 0.4770 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] desk : 0.0951 0.2646 0.7171 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] curtain : 0.2849 0.4137 0.6008 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] refridgerator : 0.2557 0.3148 0.3500 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] shower curtain : 0.4517 0.6180 0.8045 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] toilet : 0.8092 0.9957 0.9957 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] sink : 0.3035 0.5628 0.8173 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] bathtub : 0.5908 0.8197 0.8343 +[2025-02-22 12:11:31,003 INFO evaluator.py line 547 2775932] otherfurniture : 0.3693 0.5522 0.6666 +[2025-02-22 12:11:31,003 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:11:31,003 INFO evaluator.py line 554 2775932] average : 0.3328 0.5214 0.6926 +[2025-02-22 12:11:31,003 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:11:31,003 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:11:31,048 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:11:31,051 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:11:39,702 INFO hook.py line 109 2775932] Train: [36/100][50/800] Data 0.003 (0.003) Batch 0.148 (0.145) Remain 02:05:51 loss: -0.4150 Lr: 4.63693e-03 +[2025-02-22 12:11:46,833 INFO hook.py line 109 2775932] Train: [36/100][100/800] Data 0.003 (0.003) Batch 0.153 (0.144) Remain 02:04:30 loss: -0.3209 Lr: 4.63173e-03 +[2025-02-22 12:11:54,023 INFO hook.py line 109 2775932] Train: [36/100][150/800] Data 0.002 (0.003) Batch 0.149 (0.144) Remain 02:04:21 loss: -0.4794 Lr: 4.62652e-03 +[2025-02-22 12:12:01,269 INFO hook.py line 109 2775932] Train: [36/100][200/800] Data 0.006 (0.003) Batch 0.145 (0.144) Remain 02:04:27 loss: -0.3935 Lr: 4.62131e-03 +[2025-02-22 12:12:08,450 INFO hook.py line 109 2775932] Train: [36/100][250/800] Data 0.002 (0.003) Batch 0.141 (0.144) Remain 02:04:14 loss: -0.4516 Lr: 4.61609e-03 +[2025-02-22 12:12:15,897 INFO hook.py line 109 2775932] Train: [36/100][300/800] Data 0.005 (0.004) Batch 0.164 (0.145) Remain 02:04:49 loss: -0.1408 Lr: 4.61086e-03 +[2025-02-22 12:12:23,149 INFO hook.py line 109 2775932] Train: [36/100][350/800] Data 0.003 (0.003) Batch 0.140 (0.145) Remain 02:04:43 loss: -0.5708 Lr: 4.60563e-03 +[2025-02-22 12:12:30,329 INFO hook.py line 109 2775932] Train: [36/100][400/800] Data 0.003 (0.003) Batch 0.147 (0.145) Remain 02:04:28 loss: -0.5235 Lr: 4.60039e-03 +[2025-02-22 12:12:37,464 INFO hook.py line 109 2775932] Train: [36/100][450/800] Data 0.003 (0.003) Batch 0.147 (0.145) Remain 02:04:09 loss: -0.2669 Lr: 4.59514e-03 +[2025-02-22 12:12:44,510 INFO hook.py line 109 2775932] Train: [36/100][500/800] Data 0.002 (0.003) Batch 0.175 (0.144) Remain 02:03:43 loss: -0.5734 Lr: 4.58989e-03 +[2025-02-22 12:12:51,731 INFO hook.py line 109 2775932] Train: [36/100][550/800] Data 0.003 (0.003) Batch 0.126 (0.144) Remain 02:03:37 loss: -0.4410 Lr: 4.58463e-03 +[2025-02-22 12:12:58,762 INFO hook.py line 109 2775932] Train: [36/100][600/800] Data 0.004 (0.003) Batch 0.133 (0.144) Remain 02:03:14 loss: -0.5083 Lr: 4.57936e-03 +[2025-02-22 12:13:05,907 INFO hook.py line 109 2775932] Train: [36/100][650/800] Data 0.003 (0.003) Batch 0.156 (0.144) Remain 02:03:03 loss: -0.3983 Lr: 4.57408e-03 +[2025-02-22 12:13:13,245 INFO hook.py line 109 2775932] Train: [36/100][700/800] Data 0.002 (0.003) Batch 0.164 (0.144) Remain 02:03:07 loss: -0.3313 Lr: 4.56880e-03 +[2025-02-22 12:13:20,341 INFO hook.py line 109 2775932] Train: [36/100][750/800] Data 0.003 (0.003) Batch 0.144 (0.144) Remain 02:02:53 loss: -0.5038 Lr: 4.56351e-03 +[2025-02-22 12:13:27,227 INFO hook.py line 109 2775932] Train: [36/100][800/800] Data 0.002 (0.003) Batch 0.198 (0.143) Remain 02:02:26 loss: -0.4431 Lr: 4.55822e-03 +[2025-02-22 12:13:27,228 INFO misc.py line 135 2775932] Train result: loss: -0.3925 seg_loss: 0.2570 bias_l1_loss: 0.2718 bias_cosine_loss: -0.9213 +[2025-02-22 12:13:27,229 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:13:34,410 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6910 +[2025-02-22 12:13:35,229 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0833 +[2025-02-22 12:13:35,304 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4275 +[2025-02-22 12:13:35,392 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6271 +[2025-02-22 12:13:35,456 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5744 +[2025-02-22 12:13:35,517 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.6231 +[2025-02-22 12:13:35,817 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3644 +[2025-02-22 12:13:35,850 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3976 +[2025-02-22 12:13:36,004 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0376 +[2025-02-22 12:13:36,071 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.8959 +[2025-02-22 12:13:36,326 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3018 +[2025-02-22 12:13:36,431 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2772 +[2025-02-22 12:13:36,510 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.2840 +[2025-02-22 12:13:36,592 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1671 +[2025-02-22 12:13:36,686 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5635 +[2025-02-22 12:13:36,755 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6259 +[2025-02-22 12:13:36,890 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2503 +[2025-02-22 12:13:36,987 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.1104 +[2025-02-22 12:13:37,139 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0014 +[2025-02-22 12:13:37,201 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0222 +[2025-02-22 12:13:37,358 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6564 +[2025-02-22 12:13:37,509 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.7898 +[2025-02-22 12:13:37,576 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0794 +[2025-02-22 12:13:37,626 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2403 +[2025-02-22 12:13:37,694 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4374 +[2025-02-22 12:13:37,772 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3750 +[2025-02-22 12:13:37,887 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.6396 +[2025-02-22 12:13:37,986 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.2450 +[2025-02-22 12:13:38,051 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5434 +[2025-02-22 12:13:38,122 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4468 +[2025-02-22 12:13:39,043 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3678 +[2025-02-22 12:13:39,180 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.3646 +[2025-02-22 12:13:39,223 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6916 +[2025-02-22 12:13:39,316 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0287 +[2025-02-22 12:13:39,350 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6602 +[2025-02-22 12:13:39,461 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9996 +[2025-02-22 12:13:39,523 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6209 +[2025-02-22 12:13:39,742 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5175 +[2025-02-22 12:13:39,877 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6905 +[2025-02-22 12:13:40,056 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7302 +[2025-02-22 12:13:40,207 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.2425 +[2025-02-22 12:13:40,250 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1372 +[2025-02-22 12:13:40,290 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6101 +[2025-02-22 12:13:40,499 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5598 +[2025-02-22 12:13:40,533 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4010 +[2025-02-22 12:13:40,572 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4835 +[2025-02-22 12:13:40,697 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1958 +[2025-02-22 12:13:40,813 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0734 +[2025-02-22 12:13:40,924 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.7636 +[2025-02-22 12:13:41,011 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1552 +[2025-02-22 12:13:41,097 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1928 +[2025-02-22 12:13:41,239 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3278 +[2025-02-22 12:13:41,301 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7054 +[2025-02-22 12:13:41,387 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3386 +[2025-02-22 12:13:41,486 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7830 +[2025-02-22 12:13:41,534 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5606 +[2025-02-22 12:13:41,671 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0687 +[2025-02-22 12:13:41,721 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3636 +[2025-02-22 12:13:41,945 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1245 +[2025-02-22 12:13:42,059 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1443 +[2025-02-22 12:13:42,143 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.2977 +[2025-02-22 12:13:42,203 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3764 +[2025-02-22 12:13:42,360 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1460 +[2025-02-22 12:13:42,482 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7837 +[2025-02-22 12:13:42,550 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0363 +[2025-02-22 12:13:42,668 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0427 +[2025-02-22 12:13:42,835 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5192 +[2025-02-22 12:13:42,925 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1057 +[2025-02-22 12:13:42,978 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7526 +[2025-02-22 12:13:43,034 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.4384 +[2025-02-22 12:13:43,180 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.6333 +[2025-02-22 12:13:43,222 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4190 +[2025-02-22 12:13:43,273 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6580 +[2025-02-22 12:13:43,364 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7639 +[2025-02-22 12:13:43,550 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5476 +[2025-02-22 12:13:43,635 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2378 +[2025-02-22 12:13:43,819 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4480 +[2025-02-22 12:13:43,904 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.2828 +[2025-02-22 12:13:54,741 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:13:54,741 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:13:54,741 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:13:54,741 INFO evaluator.py line 547 2775932] cabinet : 0.2140 0.4180 0.6525 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] bed : 0.3339 0.6593 0.8323 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] chair : 0.6958 0.8532 0.9005 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] sofa : 0.3762 0.6036 0.8020 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] table : 0.3677 0.5661 0.6824 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] door : 0.2118 0.4100 0.5701 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] window : 0.1679 0.3337 0.5231 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] bookshelf : 0.0568 0.2176 0.4381 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] picture : 0.1700 0.2680 0.3349 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] counter : 0.0359 0.1093 0.5871 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] desk : 0.0962 0.3632 0.8148 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] curtain : 0.2272 0.3856 0.5936 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] refridgerator : 0.2873 0.4208 0.4700 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] shower curtain : 0.4433 0.5912 0.6966 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] toilet : 0.8003 0.9828 0.9828 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] sink : 0.3053 0.6082 0.7856 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] bathtub : 0.6009 0.7577 0.8660 +[2025-02-22 12:13:54,742 INFO evaluator.py line 547 2775932] otherfurniture : 0.2269 0.4136 0.5653 +[2025-02-22 12:13:54,742 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:13:54,742 INFO evaluator.py line 554 2775932] average : 0.3121 0.4979 0.6721 +[2025-02-22 12:13:54,742 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:13:54,742 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:13:54,784 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:13:54,788 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:14:03,098 INFO hook.py line 109 2775932] Train: [37/100][50/800] Data 0.002 (0.003) Batch 0.150 (0.141) Remain 02:00:15 loss: 0.7542 Lr: 4.55292e-03 +[2025-02-22 12:14:10,360 INFO hook.py line 109 2775932] Train: [37/100][100/800] Data 0.003 (0.003) Batch 0.148 (0.143) Remain 02:01:58 loss: -0.5635 Lr: 4.54761e-03 +[2025-02-22 12:14:17,623 INFO hook.py line 109 2775932] Train: [37/100][150/800] Data 0.002 (0.004) Batch 0.119 (0.144) Remain 02:02:26 loss: -0.2173 Lr: 4.54240e-03 +[2025-02-22 12:14:24,856 INFO hook.py line 109 2775932] Train: [37/100][200/800] Data 0.004 (0.004) Batch 0.154 (0.144) Remain 02:02:29 loss: -0.1047 Lr: 4.53708e-03 +[2025-02-22 12:14:32,116 INFO hook.py line 109 2775932] Train: [37/100][250/800] Data 0.003 (0.004) Batch 0.160 (0.144) Remain 02:02:33 loss: -0.0751 Lr: 4.53175e-03 +[2025-02-22 12:14:39,329 INFO hook.py line 109 2775932] Train: [37/100][300/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 02:02:25 loss: -0.2829 Lr: 4.52642e-03 +[2025-02-22 12:14:46,610 INFO hook.py line 109 2775932] Train: [37/100][350/800] Data 0.004 (0.003) Batch 0.143 (0.145) Remain 02:02:28 loss: -0.3615 Lr: 4.52108e-03 +[2025-02-22 12:14:53,838 INFO hook.py line 109 2775932] Train: [37/100][400/800] Data 0.003 (0.003) Batch 0.158 (0.145) Remain 02:02:21 loss: -0.3313 Lr: 4.51573e-03 +[2025-02-22 12:15:00,975 INFO hook.py line 109 2775932] Train: [37/100][450/800] Data 0.004 (0.003) Batch 0.134 (0.144) Remain 02:02:03 loss: -0.3377 Lr: 4.51038e-03 +[2025-02-22 12:15:08,102 INFO hook.py line 109 2775932] Train: [37/100][500/800] Data 0.003 (0.003) Batch 0.158 (0.144) Remain 02:01:47 loss: -0.3384 Lr: 4.50502e-03 +[2025-02-22 12:15:15,344 INFO hook.py line 109 2775932] Train: [37/100][550/800] Data 0.003 (0.003) Batch 0.166 (0.144) Remain 02:01:43 loss: -0.1704 Lr: 4.49965e-03 +[2025-02-22 12:15:22,474 INFO hook.py line 109 2775932] Train: [37/100][600/800] Data 0.003 (0.003) Batch 0.155 (0.144) Remain 02:01:29 loss: -0.2381 Lr: 4.49428e-03 +[2025-02-22 12:15:29,775 INFO hook.py line 109 2775932] Train: [37/100][650/800] Data 0.003 (0.003) Batch 0.132 (0.144) Remain 02:01:30 loss: -0.4230 Lr: 4.48890e-03 +[2025-02-22 12:15:37,263 INFO hook.py line 109 2775932] Train: [37/100][700/800] Data 0.003 (0.003) Batch 0.134 (0.145) Remain 02:01:42 loss: -0.5002 Lr: 4.48351e-03 +[2025-02-22 12:15:44,463 INFO hook.py line 109 2775932] Train: [37/100][750/800] Data 0.002 (0.003) Batch 0.144 (0.145) Remain 02:01:33 loss: -0.4352 Lr: 4.47812e-03 +[2025-02-22 12:15:51,271 INFO hook.py line 109 2775932] Train: [37/100][800/800] Data 0.002 (0.003) Batch 0.127 (0.144) Remain 02:00:59 loss: -0.3913 Lr: 4.47272e-03 +[2025-02-22 12:15:51,271 INFO misc.py line 135 2775932] Train result: loss: -0.3822 seg_loss: 0.2661 bias_l1_loss: 0.2718 bias_cosine_loss: -0.9202 +[2025-02-22 12:15:51,272 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:15:58,212 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6223 +[2025-02-22 12:15:58,615 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2588 +[2025-02-22 12:15:58,679 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4785 +[2025-02-22 12:15:58,782 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5575 +[2025-02-22 12:15:58,979 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5473 +[2025-02-22 12:15:59,032 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0116 +[2025-02-22 12:15:59,373 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.1137 +[2025-02-22 12:15:59,421 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5164 +[2025-02-22 12:15:59,583 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2826 +[2025-02-22 12:15:59,642 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1369 +[2025-02-22 12:15:59,909 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0674 +[2025-02-22 12:16:00,034 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1688 +[2025-02-22 12:16:00,110 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.2329 +[2025-02-22 12:16:00,198 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8542 +[2025-02-22 12:16:00,310 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7186 +[2025-02-22 12:16:00,375 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6042 +[2025-02-22 12:16:00,523 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3524 +[2025-02-22 12:16:00,626 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0871 +[2025-02-22 12:16:00,835 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0153 +[2025-02-22 12:16:00,909 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2815 +[2025-02-22 12:16:01,068 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5584 +[2025-02-22 12:16:01,252 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0674 +[2025-02-22 12:16:01,330 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0245 +[2025-02-22 12:16:01,385 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1425 +[2025-02-22 12:16:01,455 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1401 +[2025-02-22 12:16:01,541 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5281 +[2025-02-22 12:16:01,688 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0825 +[2025-02-22 12:16:01,783 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8233 +[2025-02-22 12:16:01,856 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5880 +[2025-02-22 12:16:01,934 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5315 +[2025-02-22 12:16:03,024 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4502 +[2025-02-22 12:16:03,167 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2090 +[2025-02-22 12:16:03,212 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7093 +[2025-02-22 12:16:03,335 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3000 +[2025-02-22 12:16:03,375 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6597 +[2025-02-22 12:16:03,529 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1233 +[2025-02-22 12:16:03,599 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5512 +[2025-02-22 12:16:03,764 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6461 +[2025-02-22 12:16:03,928 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5304 +[2025-02-22 12:16:04,171 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5905 +[2025-02-22 12:16:04,355 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4632 +[2025-02-22 12:16:04,406 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0842 +[2025-02-22 12:16:04,449 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5367 +[2025-02-22 12:16:04,749 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5696 +[2025-02-22 12:16:04,793 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3629 +[2025-02-22 12:16:04,835 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4016 +[2025-02-22 12:16:04,945 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2713 +[2025-02-22 12:16:05,075 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0494 +[2025-02-22 12:16:05,192 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1132 +[2025-02-22 12:16:05,286 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3368 +[2025-02-22 12:16:05,361 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0216 +[2025-02-22 12:16:05,497 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2283 +[2025-02-22 12:16:05,537 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6164 +[2025-02-22 12:16:05,637 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3266 +[2025-02-22 12:16:05,743 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7985 +[2025-02-22 12:16:05,801 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7794 +[2025-02-22 12:16:05,943 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1487 +[2025-02-22 12:16:05,993 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1515 +[2025-02-22 12:16:06,262 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3593 +[2025-02-22 12:16:06,381 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0589 +[2025-02-22 12:16:06,461 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8270 +[2025-02-22 12:16:06,546 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5613 +[2025-02-22 12:16:06,764 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1435 +[2025-02-22 12:16:06,876 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6315 +[2025-02-22 12:16:06,951 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.6606 +[2025-02-22 12:16:07,089 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2041 +[2025-02-22 12:16:07,286 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3698 +[2025-02-22 12:16:07,375 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2496 +[2025-02-22 12:16:07,429 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7400 +[2025-02-22 12:16:07,485 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1028 +[2025-02-22 12:16:07,638 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0162 +[2025-02-22 12:16:07,675 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5464 +[2025-02-22 12:16:07,728 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6511 +[2025-02-22 12:16:07,819 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.9170 +[2025-02-22 12:16:08,049 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6583 +[2025-02-22 12:16:08,133 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2040 +[2025-02-22 12:16:08,344 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.1730 +[2025-02-22 12:16:08,430 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6008 +[2025-02-22 12:16:21,368 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:16:21,369 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:16:21,369 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] cabinet : 0.2483 0.4710 0.7012 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] bed : 0.3059 0.5878 0.7120 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] chair : 0.7350 0.8977 0.9427 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] sofa : 0.3256 0.5457 0.7666 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] table : 0.4003 0.6436 0.7851 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] door : 0.2215 0.4490 0.5882 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] window : 0.1776 0.3643 0.5517 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] bookshelf : 0.1729 0.4764 0.7237 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] picture : 0.2180 0.3447 0.4533 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] counter : 0.0302 0.0902 0.5527 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] desk : 0.0646 0.1919 0.5332 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] curtain : 0.2858 0.4641 0.6505 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] refridgerator : 0.2551 0.3509 0.4173 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] shower curtain : 0.4537 0.6568 0.7800 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] toilet : 0.8179 0.9812 0.9979 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] sink : 0.3066 0.5921 0.8002 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] bathtub : 0.3829 0.5462 0.8164 +[2025-02-22 12:16:21,369 INFO evaluator.py line 547 2775932] otherfurniture : 0.3620 0.5358 0.6744 +[2025-02-22 12:16:21,369 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:16:21,369 INFO evaluator.py line 554 2775932] average : 0.3202 0.5105 0.6915 +[2025-02-22 12:16:21,369 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:16:21,369 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:16:21,422 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:16:21,426 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:16:30,566 INFO hook.py line 109 2775932] Train: [38/100][50/800] Data 0.003 (0.013) Batch 0.140 (0.154) Remain 02:09:11 loss: -0.4617 Lr: 4.46732e-03 +[2025-02-22 12:16:37,770 INFO hook.py line 109 2775932] Train: [38/100][100/800] Data 0.003 (0.008) Batch 0.131 (0.149) Remain 02:04:47 loss: -0.5135 Lr: 4.46190e-03 +[2025-02-22 12:16:45,124 INFO hook.py line 109 2775932] Train: [38/100][150/800] Data 0.002 (0.006) Batch 0.142 (0.148) Remain 02:04:09 loss: -0.3447 Lr: 4.45649e-03 +[2025-02-22 12:16:52,441 INFO hook.py line 109 2775932] Train: [38/100][200/800] Data 0.002 (0.005) Batch 0.123 (0.148) Remain 02:03:37 loss: -0.6188 Lr: 4.45106e-03 +[2025-02-22 12:16:59,388 INFO hook.py line 109 2775932] Train: [38/100][250/800] Data 0.003 (0.005) Batch 0.124 (0.146) Remain 02:02:00 loss: -0.5746 Lr: 4.44563e-03 +[2025-02-22 12:17:06,457 INFO hook.py line 109 2775932] Train: [38/100][300/800] Data 0.002 (0.005) Batch 0.132 (0.145) Remain 02:01:14 loss: -0.5553 Lr: 4.44020e-03 +[2025-02-22 12:17:13,743 INFO hook.py line 109 2775932] Train: [38/100][350/800] Data 0.003 (0.004) Batch 0.133 (0.145) Remain 02:01:11 loss: 0.1523 Lr: 4.43476e-03 +[2025-02-22 12:17:20,851 INFO hook.py line 109 2775932] Train: [38/100][400/800] Data 0.003 (0.004) Batch 0.133 (0.145) Remain 02:00:44 loss: 0.0877 Lr: 4.42931e-03 +[2025-02-22 12:17:27,953 INFO hook.py line 109 2775932] Train: [38/100][450/800] Data 0.002 (0.004) Batch 0.139 (0.145) Remain 02:00:20 loss: -0.4821 Lr: 4.42385e-03 +[2025-02-22 12:17:35,042 INFO hook.py line 109 2775932] Train: [38/100][500/800] Data 0.003 (0.004) Batch 0.131 (0.144) Remain 01:59:59 loss: -0.4363 Lr: 4.41839e-03 +[2025-02-22 12:17:42,588 INFO hook.py line 109 2775932] Train: [38/100][550/800] Data 0.003 (0.004) Batch 0.129 (0.145) Remain 02:00:22 loss: -0.4839 Lr: 4.41293e-03 +[2025-02-22 12:17:49,733 INFO hook.py line 109 2775932] Train: [38/100][600/800] Data 0.003 (0.004) Batch 0.147 (0.145) Remain 02:00:07 loss: -0.1982 Lr: 4.40745e-03 +[2025-02-22 12:17:57,227 INFO hook.py line 109 2775932] Train: [38/100][650/800] Data 0.003 (0.004) Batch 0.136 (0.145) Remain 02:00:19 loss: -0.5537 Lr: 4.40198e-03 +[2025-02-22 12:18:04,169 INFO hook.py line 109 2775932] Train: [38/100][700/800] Data 0.002 (0.004) Batch 0.158 (0.145) Remain 01:59:50 loss: -0.5707 Lr: 4.39649e-03 +[2025-02-22 12:18:11,252 INFO hook.py line 109 2775932] Train: [38/100][750/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 01:59:32 loss: 0.0739 Lr: 4.39100e-03 +[2025-02-22 12:18:18,156 INFO hook.py line 109 2775932] Train: [38/100][800/800] Data 0.003 (0.004) Batch 0.134 (0.144) Remain 01:59:05 loss: -0.4846 Lr: 4.38551e-03 +[2025-02-22 12:18:18,157 INFO misc.py line 135 2775932] Train result: loss: -0.3935 seg_loss: 0.2601 bias_l1_loss: 0.2686 bias_cosine_loss: -0.9223 +[2025-02-22 12:18:18,157 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:18:25,282 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7462 +[2025-02-22 12:18:25,557 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4115 +[2025-02-22 12:18:25,719 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5087 +[2025-02-22 12:18:25,821 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5933 +[2025-02-22 12:18:25,919 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5701 +[2025-02-22 12:18:25,969 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8211 +[2025-02-22 12:18:26,248 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3931 +[2025-02-22 12:18:26,280 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4235 +[2025-02-22 12:18:26,416 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2905 +[2025-02-22 12:18:26,477 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0750 +[2025-02-22 12:18:26,731 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0821 +[2025-02-22 12:18:26,849 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0349 +[2025-02-22 12:18:26,926 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.0025 +[2025-02-22 12:18:27,025 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9200 +[2025-02-22 12:18:27,109 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.7122 +[2025-02-22 12:18:27,189 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4923 +[2025-02-22 12:18:27,313 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3070 +[2025-02-22 12:18:27,405 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2704 +[2025-02-22 12:18:27,550 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0061 +[2025-02-22 12:18:27,607 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3111 +[2025-02-22 12:18:27,764 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5432 +[2025-02-22 12:18:27,932 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3100 +[2025-02-22 12:18:28,008 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0681 +[2025-02-22 12:18:28,059 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2105 +[2025-02-22 12:18:28,116 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1533 +[2025-02-22 12:18:28,172 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5408 +[2025-02-22 12:18:28,304 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0361 +[2025-02-22 12:18:28,395 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.9216 +[2025-02-22 12:18:28,463 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5478 +[2025-02-22 12:18:28,536 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6867 +[2025-02-22 12:18:29,328 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4367 +[2025-02-22 12:18:29,442 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2941 +[2025-02-22 12:18:29,511 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6564 +[2025-02-22 12:18:29,601 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2517 +[2025-02-22 12:18:29,633 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6275 +[2025-02-22 12:18:29,740 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0265 +[2025-02-22 12:18:29,805 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5577 +[2025-02-22 12:18:29,921 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.4391 +[2025-02-22 12:18:30,081 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2173 +[2025-02-22 12:18:30,273 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6402 +[2025-02-22 12:18:30,420 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5657 +[2025-02-22 12:18:30,463 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0759 +[2025-02-22 12:18:30,498 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6969 +[2025-02-22 12:18:30,741 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4747 +[2025-02-22 12:18:30,788 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4340 +[2025-02-22 12:18:30,828 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4985 +[2025-02-22 12:18:30,914 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4596 +[2025-02-22 12:18:31,024 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2368 +[2025-02-22 12:18:31,114 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0612 +[2025-02-22 12:18:31,204 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1242 +[2025-02-22 12:18:31,273 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2576 +[2025-02-22 12:18:31,396 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3011 +[2025-02-22 12:18:31,430 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6064 +[2025-02-22 12:18:31,541 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2538 +[2025-02-22 12:18:31,619 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7546 +[2025-02-22 12:18:31,659 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7459 +[2025-02-22 12:18:31,774 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.1754 +[2025-02-22 12:18:31,806 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3783 +[2025-02-22 12:18:31,994 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2496 +[2025-02-22 12:18:32,084 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0586 +[2025-02-22 12:18:32,140 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7612 +[2025-02-22 12:18:32,190 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4112 +[2025-02-22 12:18:32,323 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0029 +[2025-02-22 12:18:32,420 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3622 +[2025-02-22 12:18:32,480 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0528 +[2025-02-22 12:18:32,596 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1742 +[2025-02-22 12:18:32,737 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5989 +[2025-02-22 12:18:32,843 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2804 +[2025-02-22 12:18:32,888 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6317 +[2025-02-22 12:18:32,929 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0956 +[2025-02-22 12:18:33,057 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1747 +[2025-02-22 12:18:33,086 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5093 +[2025-02-22 12:18:33,127 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6308 +[2025-02-22 12:18:33,215 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.0777 +[2025-02-22 12:18:33,389 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3166 +[2025-02-22 12:18:33,470 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0540 +[2025-02-22 12:18:33,622 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.2978 +[2025-02-22 12:18:33,701 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5814 +[2025-02-22 12:18:46,075 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:18:46,075 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:18:46,075 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] cabinet : 0.2477 0.5034 0.7328 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] bed : 0.3697 0.7160 0.8455 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] chair : 0.6969 0.8632 0.9129 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] sofa : 0.3213 0.5517 0.7743 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] table : 0.3821 0.6052 0.7494 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] door : 0.2059 0.4250 0.5623 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] window : 0.1946 0.3773 0.5675 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] bookshelf : 0.2533 0.5954 0.7339 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] picture : 0.1825 0.2864 0.4013 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] counter : 0.0310 0.1178 0.6377 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] desk : 0.1466 0.3990 0.7534 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] curtain : 0.2473 0.4798 0.7251 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] refridgerator : 0.3083 0.4035 0.4682 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] shower curtain : 0.4985 0.6582 0.7784 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] toilet : 0.8570 0.9816 0.9980 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] sink : 0.2704 0.4994 0.8378 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] bathtub : 0.5705 0.7019 0.8343 +[2025-02-22 12:18:46,076 INFO evaluator.py line 547 2775932] otherfurniture : 0.3325 0.5180 0.6788 +[2025-02-22 12:18:46,076 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:18:46,076 INFO evaluator.py line 554 2775932] average : 0.3398 0.5379 0.7218 +[2025-02-22 12:18:46,076 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:18:46,076 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:18:46,113 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:18:46,118 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:18:54,685 INFO hook.py line 109 2775932] Train: [39/100][50/800] Data 0.004 (0.003) Batch 0.162 (0.144) Remain 01:58:51 loss: -0.4948 Lr: 4.38000e-03 +[2025-02-22 12:19:01,859 INFO hook.py line 109 2775932] Train: [39/100][100/800] Data 0.003 (0.003) Batch 0.120 (0.144) Remain 01:58:32 loss: -0.5885 Lr: 4.37449e-03 +[2025-02-22 12:19:08,969 INFO hook.py line 109 2775932] Train: [39/100][150/800] Data 0.002 (0.003) Batch 0.166 (0.143) Remain 01:58:00 loss: -0.4469 Lr: 4.36898e-03 +[2025-02-22 12:19:16,182 INFO hook.py line 109 2775932] Train: [39/100][200/800] Data 0.002 (0.003) Batch 0.150 (0.143) Remain 01:58:07 loss: -0.4867 Lr: 4.36346e-03 +[2025-02-22 12:19:23,309 INFO hook.py line 109 2775932] Train: [39/100][250/800] Data 0.003 (0.004) Batch 0.131 (0.143) Remain 01:57:50 loss: -0.5600 Lr: 4.35794e-03 +[2025-02-22 12:19:30,422 INFO hook.py line 109 2775932] Train: [39/100][300/800] Data 0.003 (0.004) Batch 0.133 (0.143) Remain 01:57:34 loss: -0.4263 Lr: 4.35240e-03 +[2025-02-22 12:19:37,985 INFO hook.py line 109 2775932] Train: [39/100][350/800] Data 0.003 (0.004) Batch 0.149 (0.144) Remain 01:58:25 loss: -0.0741 Lr: 4.34687e-03 +[2025-02-22 12:19:44,804 INFO hook.py line 109 2775932] Train: [39/100][400/800] Data 0.003 (0.004) Batch 0.125 (0.143) Remain 01:57:29 loss: -0.5388 Lr: 4.34132e-03 +[2025-02-22 12:19:51,831 INFO hook.py line 109 2775932] Train: [39/100][450/800] Data 0.002 (0.004) Batch 0.145 (0.143) Remain 01:57:07 loss: -0.3244 Lr: 4.33577e-03 +[2025-02-22 12:19:58,970 INFO hook.py line 109 2775932] Train: [39/100][500/800] Data 0.002 (0.003) Batch 0.135 (0.143) Remain 01:56:59 loss: -0.4858 Lr: 4.33022e-03 +[2025-02-22 12:20:06,250 INFO hook.py line 109 2775932] Train: [39/100][550/800] Data 0.003 (0.003) Batch 0.161 (0.143) Remain 01:57:03 loss: -0.3433 Lr: 4.32466e-03 +[2025-02-22 12:20:13,353 INFO hook.py line 109 2775932] Train: [39/100][600/800] Data 0.003 (0.003) Batch 0.153 (0.143) Remain 01:56:51 loss: -0.5640 Lr: 4.31909e-03 +[2025-02-22 12:20:20,908 INFO hook.py line 109 2775932] Train: [39/100][650/800] Data 0.003 (0.003) Batch 0.151 (0.144) Remain 01:57:15 loss: -0.5703 Lr: 4.31352e-03 +[2025-02-22 12:20:27,980 INFO hook.py line 109 2775932] Train: [39/100][700/800] Data 0.003 (0.003) Batch 0.127 (0.144) Remain 01:56:59 loss: -0.0592 Lr: 4.30795e-03 +[2025-02-22 12:20:35,064 INFO hook.py line 109 2775932] Train: [39/100][750/800] Data 0.003 (0.003) Batch 0.121 (0.143) Remain 01:56:46 loss: -0.4790 Lr: 4.30236e-03 +[2025-02-22 12:20:42,232 INFO hook.py line 109 2775932] Train: [39/100][800/800] Data 0.003 (0.003) Batch 0.128 (0.143) Remain 01:56:39 loss: -0.0551 Lr: 4.29678e-03 +[2025-02-22 12:20:42,233 INFO misc.py line 135 2775932] Train result: loss: -0.4111 seg_loss: 0.2503 bias_l1_loss: 0.2635 bias_cosine_loss: -0.9249 +[2025-02-22 12:20:42,233 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:20:49,523 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7096 +[2025-02-22 12:20:50,567 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.0429 +[2025-02-22 12:20:50,642 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.2709 +[2025-02-22 12:20:50,711 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4677 +[2025-02-22 12:20:50,778 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5386 +[2025-02-22 12:20:50,835 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7573 +[2025-02-22 12:20:51,116 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3337 +[2025-02-22 12:20:51,147 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5236 +[2025-02-22 12:20:51,306 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.2323 +[2025-02-22 12:20:51,361 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.4173 +[2025-02-22 12:20:51,625 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1389 +[2025-02-22 12:20:51,762 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0095 +[2025-02-22 12:20:51,843 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.1107 +[2025-02-22 12:20:51,940 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7571 +[2025-02-22 12:20:52,037 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6035 +[2025-02-22 12:20:52,111 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5584 +[2025-02-22 12:20:52,266 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3607 +[2025-02-22 12:20:52,358 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1455 +[2025-02-22 12:20:52,527 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2463 +[2025-02-22 12:20:52,599 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0813 +[2025-02-22 12:20:52,779 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5930 +[2025-02-22 12:20:52,947 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4290 +[2025-02-22 12:20:53,036 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0558 +[2025-02-22 12:20:53,099 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1411 +[2025-02-22 12:20:53,175 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3077 +[2025-02-22 12:20:53,248 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.1364 +[2025-02-22 12:20:53,392 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.6292 +[2025-02-22 12:20:53,499 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.1929 +[2025-02-22 12:20:53,576 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6183 +[2025-02-22 12:20:53,655 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3909 +[2025-02-22 12:20:54,546 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3735 +[2025-02-22 12:20:54,693 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.9360 +[2025-02-22 12:20:54,737 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4602 +[2025-02-22 12:20:54,860 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1326 +[2025-02-22 12:20:54,899 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5026 +[2025-02-22 12:20:55,032 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2969 +[2025-02-22 12:20:55,109 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4693 +[2025-02-22 12:20:55,242 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5571 +[2025-02-22 12:20:55,376 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4814 +[2025-02-22 12:20:55,602 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8387 +[2025-02-22 12:20:55,755 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5864 +[2025-02-22 12:20:55,799 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.2833 +[2025-02-22 12:20:55,841 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5866 +[2025-02-22 12:20:56,087 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4708 +[2025-02-22 12:20:56,125 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3102 +[2025-02-22 12:20:56,166 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.3828 +[2025-02-22 12:20:56,254 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2575 +[2025-02-22 12:20:56,360 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0263 +[2025-02-22 12:20:56,489 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.4327 +[2025-02-22 12:20:56,578 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0113 +[2025-02-22 12:20:56,658 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2338 +[2025-02-22 12:20:56,813 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1551 +[2025-02-22 12:20:56,856 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6427 +[2025-02-22 12:20:56,971 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8324 +[2025-02-22 12:20:57,074 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7018 +[2025-02-22 12:20:57,123 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5457 +[2025-02-22 12:20:57,266 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0720 +[2025-02-22 12:20:57,320 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.0425 +[2025-02-22 12:20:57,542 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1771 +[2025-02-22 12:20:57,659 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1252 +[2025-02-22 12:20:57,746 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.8426 +[2025-02-22 12:20:57,821 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3142 +[2025-02-22 12:20:58,010 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.3349 +[2025-02-22 12:20:58,132 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.8965 +[2025-02-22 12:20:58,229 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0954 +[2025-02-22 12:20:58,364 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0077 +[2025-02-22 12:20:58,577 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.0486 +[2025-02-22 12:20:58,672 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0980 +[2025-02-22 12:20:58,729 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7135 +[2025-02-22 12:20:58,783 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0366 +[2025-02-22 12:20:58,976 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.0978 +[2025-02-22 12:20:59,014 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6270 +[2025-02-22 12:20:59,074 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.4746 +[2025-02-22 12:20:59,178 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2319 +[2025-02-22 12:20:59,409 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5010 +[2025-02-22 12:20:59,496 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0445 +[2025-02-22 12:20:59,682 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.1643 +[2025-02-22 12:20:59,779 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6059 +[2025-02-22 12:21:11,451 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:21:11,451 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:21:11,451 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] cabinet : 0.2501 0.4814 0.6757 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] bed : 0.2998 0.6606 0.8112 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] chair : 0.6996 0.8480 0.8985 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] sofa : 0.3289 0.5903 0.8121 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] table : 0.3405 0.5944 0.7395 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] door : 0.1884 0.4341 0.6130 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] window : 0.1447 0.2978 0.5181 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] bookshelf : 0.0342 0.1236 0.4037 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] picture : 0.1816 0.2651 0.3436 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] counter : 0.0466 0.1570 0.6068 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] desk : 0.0664 0.2243 0.6371 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] curtain : 0.2792 0.4329 0.6468 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] refridgerator : 0.1739 0.2416 0.3122 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] shower curtain : 0.4336 0.5762 0.6835 +[2025-02-22 12:21:11,451 INFO evaluator.py line 547 2775932] toilet : 0.7827 0.9435 0.9780 +[2025-02-22 12:21:11,452 INFO evaluator.py line 547 2775932] sink : 0.2815 0.4970 0.7993 +[2025-02-22 12:21:11,452 INFO evaluator.py line 547 2775932] bathtub : 0.5807 0.6910 0.8452 +[2025-02-22 12:21:11,452 INFO evaluator.py line 547 2775932] otherfurniture : 0.2310 0.3802 0.5445 +[2025-02-22 12:21:11,452 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:21:11,452 INFO evaluator.py line 554 2775932] average : 0.2969 0.4688 0.6594 +[2025-02-22 12:21:11,452 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:21:11,452 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:21:11,491 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:21:11,495 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:21:19,916 INFO hook.py line 109 2775932] Train: [40/100][50/800] Data 0.003 (0.003) Batch 0.145 (0.142) Remain 01:55:20 loss: -0.5922 Lr: 4.29118e-03 +[2025-02-22 12:21:27,338 INFO hook.py line 109 2775932] Train: [40/100][100/800] Data 0.003 (0.006) Batch 0.149 (0.145) Remain 01:57:56 loss: -0.4154 Lr: 4.28558e-03 +[2025-02-22 12:21:34,200 INFO hook.py line 109 2775932] Train: [40/100][150/800] Data 0.003 (0.005) Batch 0.125 (0.143) Remain 01:55:35 loss: -0.4904 Lr: 4.27998e-03 +[2025-02-22 12:21:41,334 INFO hook.py line 109 2775932] Train: [40/100][200/800] Data 0.004 (0.004) Batch 0.149 (0.143) Remain 01:55:29 loss: -0.2288 Lr: 4.27437e-03 +[2025-02-22 12:21:48,405 INFO hook.py line 109 2775932] Train: [40/100][250/800] Data 0.003 (0.004) Batch 0.161 (0.142) Remain 01:55:11 loss: -0.4760 Lr: 4.26875e-03 +[2025-02-22 12:21:55,511 INFO hook.py line 109 2775932] Train: [40/100][300/800] Data 0.003 (0.004) Batch 0.128 (0.142) Remain 01:55:02 loss: -0.4938 Lr: 4.26313e-03 +[2025-02-22 12:22:02,663 INFO hook.py line 109 2775932] Train: [40/100][350/800] Data 0.003 (0.004) Batch 0.147 (0.142) Remain 01:55:00 loss: -0.7050 Lr: 4.25750e-03 +[2025-02-22 12:22:09,805 INFO hook.py line 109 2775932] Train: [40/100][400/800] Data 0.002 (0.004) Batch 0.138 (0.142) Remain 01:54:55 loss: -0.5695 Lr: 4.25187e-03 +[2025-02-22 12:22:16,904 INFO hook.py line 109 2775932] Train: [40/100][450/800] Data 0.004 (0.004) Batch 0.132 (0.142) Remain 01:54:45 loss: -0.3222 Lr: 4.24624e-03 +[2025-02-22 12:22:24,215 INFO hook.py line 109 2775932] Train: [40/100][500/800] Data 0.002 (0.003) Batch 0.148 (0.143) Remain 01:54:57 loss: -0.2307 Lr: 4.24059e-03 +[2025-02-22 12:22:31,312 INFO hook.py line 109 2775932] Train: [40/100][550/800] Data 0.005 (0.003) Batch 0.159 (0.143) Remain 01:54:46 loss: -0.3061 Lr: 4.23495e-03 +[2025-02-22 12:22:38,506 INFO hook.py line 109 2775932] Train: [40/100][600/800] Data 0.003 (0.003) Batch 0.124 (0.143) Remain 01:54:43 loss: -0.4002 Lr: 4.22929e-03 +[2025-02-22 12:22:45,636 INFO hook.py line 109 2775932] Train: [40/100][650/800] Data 0.003 (0.003) Batch 0.141 (0.143) Remain 01:54:35 loss: -0.3338 Lr: 4.22363e-03 +[2025-02-22 12:22:52,767 INFO hook.py line 109 2775932] Train: [40/100][700/800] Data 0.003 (0.003) Batch 0.145 (0.143) Remain 01:54:28 loss: -0.0508 Lr: 4.21797e-03 +[2025-02-22 12:23:00,209 INFO hook.py line 109 2775932] Train: [40/100][750/800] Data 0.003 (0.003) Batch 0.173 (0.143) Remain 01:54:40 loss: -0.4514 Lr: 4.21230e-03 +[2025-02-22 12:23:07,013 INFO hook.py line 109 2775932] Train: [40/100][800/800] Data 0.001 (0.003) Batch 0.118 (0.143) Remain 01:54:11 loss: -0.2954 Lr: 4.20663e-03 +[2025-02-22 12:23:07,014 INFO misc.py line 135 2775932] Train result: loss: -0.3909 seg_loss: 0.2595 bias_l1_loss: 0.2703 bias_cosine_loss: -0.9208 +[2025-02-22 12:23:07,014 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:23:14,165 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6707 +[2025-02-22 12:23:15,150 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2279 +[2025-02-22 12:23:15,237 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4085 +[2025-02-22 12:23:15,310 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5574 +[2025-02-22 12:23:15,397 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5048 +[2025-02-22 12:23:15,464 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8706 +[2025-02-22 12:23:15,728 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3237 +[2025-02-22 12:23:15,759 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4984 +[2025-02-22 12:23:15,901 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1840 +[2025-02-22 12:23:15,952 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0799 +[2025-02-22 12:23:16,210 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0197 +[2025-02-22 12:23:16,336 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0642 +[2025-02-22 12:23:16,423 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5124 +[2025-02-22 12:23:16,521 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.2946 +[2025-02-22 12:23:16,606 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.9093 +[2025-02-22 12:23:16,705 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5098 +[2025-02-22 12:23:16,879 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4534 +[2025-02-22 12:23:16,992 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.2970 +[2025-02-22 12:23:17,189 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2201 +[2025-02-22 12:23:17,287 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1318 +[2025-02-22 12:23:17,466 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6007 +[2025-02-22 12:23:17,675 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3532 +[2025-02-22 12:23:17,772 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.3341 +[2025-02-22 12:23:17,832 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0022 +[2025-02-22 12:23:17,909 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3346 +[2025-02-22 12:23:17,969 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5441 +[2025-02-22 12:23:18,153 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1648 +[2025-02-22 12:23:18,299 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5605 +[2025-02-22 12:23:18,381 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6476 +[2025-02-22 12:23:18,455 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4638 +[2025-02-22 12:23:19,411 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5005 +[2025-02-22 12:23:19,540 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2454 +[2025-02-22 12:23:19,584 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6489 +[2025-02-22 12:23:19,683 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0962 +[2025-02-22 12:23:19,724 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6105 +[2025-02-22 12:23:19,859 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9731 +[2025-02-22 12:23:19,925 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5450 +[2025-02-22 12:23:20,066 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6190 +[2025-02-22 12:23:20,222 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5994 +[2025-02-22 12:23:20,452 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6096 +[2025-02-22 12:23:20,617 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4764 +[2025-02-22 12:23:20,667 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0776 +[2025-02-22 12:23:20,708 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6347 +[2025-02-22 12:23:20,959 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5846 +[2025-02-22 12:23:21,002 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3173 +[2025-02-22 12:23:21,044 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5362 +[2025-02-22 12:23:21,129 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5482 +[2025-02-22 12:23:21,246 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2576 +[2025-02-22 12:23:21,353 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0544 +[2025-02-22 12:23:21,492 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.7342 +[2025-02-22 12:23:21,571 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1061 +[2025-02-22 12:23:21,698 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3776 +[2025-02-22 12:23:21,749 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5876 +[2025-02-22 12:23:21,866 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3914 +[2025-02-22 12:23:21,956 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8263 +[2025-02-22 12:23:22,003 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7698 +[2025-02-22 12:23:22,133 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2602 +[2025-02-22 12:23:22,171 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3383 +[2025-02-22 12:23:22,395 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1250 +[2025-02-22 12:23:22,505 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0505 +[2025-02-22 12:23:22,584 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7934 +[2025-02-22 12:23:22,663 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4810 +[2025-02-22 12:23:22,816 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0961 +[2025-02-22 12:23:22,921 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3891 +[2025-02-22 12:23:23,000 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1037 +[2025-02-22 12:23:23,133 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3281 +[2025-02-22 12:23:23,292 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5060 +[2025-02-22 12:23:23,383 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.5944 +[2025-02-22 12:23:23,436 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7142 +[2025-02-22 12:23:23,486 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1586 +[2025-02-22 12:23:23,634 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0387 +[2025-02-22 12:23:23,672 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6004 +[2025-02-22 12:23:23,719 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6638 +[2025-02-22 12:23:23,827 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4550 +[2025-02-22 12:23:24,042 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6332 +[2025-02-22 12:23:24,123 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2552 +[2025-02-22 12:23:24,286 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4981 +[2025-02-22 12:23:24,377 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6488 +[2025-02-22 12:23:35,236 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:23:35,236 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:23:35,236 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] cabinet : 0.1977 0.3912 0.6602 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] bed : 0.2422 0.4634 0.5593 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] chair : 0.7061 0.8699 0.9154 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] sofa : 0.3415 0.5685 0.7733 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] table : 0.4237 0.6719 0.7919 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] door : 0.1976 0.3920 0.5165 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] window : 0.1985 0.3924 0.6035 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] bookshelf : 0.2364 0.5173 0.7400 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] picture : 0.1954 0.2982 0.3865 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] counter : 0.0324 0.1204 0.5805 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] desk : 0.0784 0.2748 0.7203 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] curtain : 0.2724 0.4673 0.6725 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] refridgerator : 0.2568 0.3430 0.4211 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] shower curtain : 0.3842 0.5282 0.7387 +[2025-02-22 12:23:35,236 INFO evaluator.py line 547 2775932] toilet : 0.7858 0.9652 0.9828 +[2025-02-22 12:23:35,237 INFO evaluator.py line 547 2775932] sink : 0.1619 0.4664 0.8248 +[2025-02-22 12:23:35,237 INFO evaluator.py line 547 2775932] bathtub : 0.6223 0.7617 0.8567 +[2025-02-22 12:23:35,237 INFO evaluator.py line 547 2775932] otherfurniture : 0.2678 0.4478 0.5732 +[2025-02-22 12:23:35,237 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:23:35,237 INFO evaluator.py line 554 2775932] average : 0.3112 0.4966 0.6843 +[2025-02-22 12:23:35,237 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:23:35,237 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:23:35,269 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:23:35,273 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:23:43,791 INFO hook.py line 109 2775932] Train: [41/100][50/800] Data 0.003 (0.003) Batch 0.131 (0.142) Remain 01:53:45 loss: 0.2968 Lr: 4.20095e-03 +[2025-02-22 12:23:50,979 INFO hook.py line 109 2775932] Train: [41/100][100/800] Data 0.003 (0.003) Batch 0.146 (0.143) Remain 01:54:13 loss: -0.5451 Lr: 4.19538e-03 +[2025-02-22 12:23:58,335 INFO hook.py line 109 2775932] Train: [41/100][150/800] Data 0.003 (0.003) Batch 0.115 (0.144) Remain 01:55:11 loss: -0.1829 Lr: 4.18969e-03 +[2025-02-22 12:24:05,460 INFO hook.py line 109 2775932] Train: [41/100][200/800] Data 0.003 (0.003) Batch 0.131 (0.144) Remain 01:54:41 loss: -0.5177 Lr: 4.18400e-03 +[2025-02-22 12:24:12,619 INFO hook.py line 109 2775932] Train: [41/100][250/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 01:54:26 loss: -0.4671 Lr: 4.17830e-03 +[2025-02-22 12:24:19,865 INFO hook.py line 109 2775932] Train: [41/100][300/800] Data 0.003 (0.004) Batch 0.132 (0.144) Remain 01:54:28 loss: 0.4636 Lr: 4.17259e-03 +[2025-02-22 12:24:27,062 INFO hook.py line 109 2775932] Train: [41/100][350/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 01:54:20 loss: -0.4252 Lr: 4.16688e-03 +[2025-02-22 12:24:33,997 INFO hook.py line 109 2775932] Train: [41/100][400/800] Data 0.002 (0.003) Batch 0.140 (0.143) Remain 01:53:41 loss: -0.3694 Lr: 4.16117e-03 +[2025-02-22 12:24:41,096 INFO hook.py line 109 2775932] Train: [41/100][450/800] Data 0.003 (0.003) Batch 0.149 (0.143) Remain 01:53:27 loss: -0.2768 Lr: 4.15545e-03 +[2025-02-22 12:24:48,202 INFO hook.py line 109 2775932] Train: [41/100][500/800] Data 0.002 (0.003) Batch 0.139 (0.143) Remain 01:53:15 loss: -0.2616 Lr: 4.14972e-03 +[2025-02-22 12:24:55,280 INFO hook.py line 109 2775932] Train: [41/100][550/800] Data 0.003 (0.003) Batch 0.120 (0.143) Remain 01:53:01 loss: -0.2411 Lr: 4.14400e-03 +[2025-02-22 12:25:02,584 INFO hook.py line 109 2775932] Train: [41/100][600/800] Data 0.003 (0.003) Batch 0.144 (0.143) Remain 01:53:07 loss: -0.5149 Lr: 4.13826e-03 +[2025-02-22 12:25:09,681 INFO hook.py line 109 2775932] Train: [41/100][650/800] Data 0.003 (0.003) Batch 0.142 (0.143) Remain 01:52:55 loss: -0.4358 Lr: 4.13252e-03 +[2025-02-22 12:25:16,969 INFO hook.py line 109 2775932] Train: [41/100][700/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 01:52:57 loss: -0.3754 Lr: 4.12678e-03 +[2025-02-22 12:25:24,280 INFO hook.py line 109 2775932] Train: [41/100][750/800] Data 0.003 (0.003) Batch 0.137 (0.143) Remain 01:52:59 loss: -0.3435 Lr: 4.12103e-03 +[2025-02-22 12:25:31,268 INFO hook.py line 109 2775932] Train: [41/100][800/800] Data 0.002 (0.003) Batch 0.132 (0.143) Remain 01:52:41 loss: -0.2880 Lr: 4.11528e-03 +[2025-02-22 12:25:31,269 INFO misc.py line 135 2775932] Train result: loss: -0.4155 seg_loss: 0.2482 bias_l1_loss: 0.2625 bias_cosine_loss: -0.9262 +[2025-02-22 12:25:31,269 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:25:38,587 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6893 +[2025-02-22 12:25:38,933 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3378 +[2025-02-22 12:25:38,999 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5535 +[2025-02-22 12:25:39,200 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6289 +[2025-02-22 12:25:39,277 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6165 +[2025-02-22 12:25:39,337 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7696 +[2025-02-22 12:25:39,596 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5286 +[2025-02-22 12:25:39,625 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3457 +[2025-02-22 12:25:39,779 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2869 +[2025-02-22 12:25:39,839 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0452 +[2025-02-22 12:25:40,083 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0232 +[2025-02-22 12:25:40,198 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0333 +[2025-02-22 12:25:40,278 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4829 +[2025-02-22 12:25:40,388 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3273 +[2025-02-22 12:25:40,465 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4069 +[2025-02-22 12:25:40,555 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3430 +[2025-02-22 12:25:40,694 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4103 +[2025-02-22 12:25:40,787 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2495 +[2025-02-22 12:25:40,952 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2833 +[2025-02-22 12:25:41,021 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2251 +[2025-02-22 12:25:41,215 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6126 +[2025-02-22 12:25:41,391 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2404 +[2025-02-22 12:25:41,469 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1053 +[2025-02-22 12:25:41,524 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1142 +[2025-02-22 12:25:41,591 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3242 +[2025-02-22 12:25:41,652 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4985 +[2025-02-22 12:25:41,804 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3344 +[2025-02-22 12:25:41,899 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6376 +[2025-02-22 12:25:41,968 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6384 +[2025-02-22 12:25:42,041 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5981 +[2025-02-22 12:25:43,035 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4375 +[2025-02-22 12:25:43,169 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2620 +[2025-02-22 12:25:43,210 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6870 +[2025-02-22 12:25:43,310 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2083 +[2025-02-22 12:25:43,359 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3224 +[2025-02-22 12:25:43,481 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8672 +[2025-02-22 12:25:43,562 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5290 +[2025-02-22 12:25:43,701 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6453 +[2025-02-22 12:25:43,899 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2184 +[2025-02-22 12:25:44,140 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7737 +[2025-02-22 12:25:44,320 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4432 +[2025-02-22 12:25:44,372 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2797 +[2025-02-22 12:25:44,415 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6597 +[2025-02-22 12:25:44,672 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6184 +[2025-02-22 12:25:44,723 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5079 +[2025-02-22 12:25:44,769 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4827 +[2025-02-22 12:25:44,884 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0379 +[2025-02-22 12:25:45,002 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5009 +[2025-02-22 12:25:45,111 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0020 +[2025-02-22 12:25:45,204 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.1264 +[2025-02-22 12:25:45,287 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0938 +[2025-02-22 12:25:45,416 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2200 +[2025-02-22 12:25:45,480 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6171 +[2025-02-22 12:25:45,583 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8245 +[2025-02-22 12:25:45,672 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7925 +[2025-02-22 12:25:45,722 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6789 +[2025-02-22 12:25:45,849 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.3197 +[2025-02-22 12:25:45,892 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.1255 +[2025-02-22 12:25:46,122 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1845 +[2025-02-22 12:25:46,228 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0289 +[2025-02-22 12:25:46,313 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8331 +[2025-02-22 12:25:46,371 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5364 +[2025-02-22 12:25:46,542 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0683 +[2025-02-22 12:25:46,658 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5072 +[2025-02-22 12:25:46,756 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2933 +[2025-02-22 12:25:46,916 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3869 +[2025-02-22 12:25:47,104 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5848 +[2025-02-22 12:25:47,177 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0217 +[2025-02-22 12:25:47,232 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6676 +[2025-02-22 12:25:47,276 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2619 +[2025-02-22 12:25:47,429 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2256 +[2025-02-22 12:25:47,459 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5197 +[2025-02-22 12:25:47,513 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6530 +[2025-02-22 12:25:47,603 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8237 +[2025-02-22 12:25:47,789 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5130 +[2025-02-22 12:25:47,861 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2402 +[2025-02-22 12:25:48,018 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.2826 +[2025-02-22 12:25:48,100 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6522 +[2025-02-22 12:26:00,424 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:26:00,424 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:26:00,424 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] cabinet : 0.2525 0.5108 0.6956 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] bed : 0.3234 0.7057 0.8564 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] chair : 0.7106 0.8736 0.9269 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] sofa : 0.3467 0.6071 0.8344 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] table : 0.3279 0.5130 0.6440 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] door : 0.2220 0.4434 0.5946 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] window : 0.2201 0.4082 0.5705 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] bookshelf : 0.2557 0.5449 0.7050 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] picture : 0.1825 0.3055 0.4100 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] counter : 0.0292 0.1118 0.4693 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] desk : 0.0794 0.2816 0.7327 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] curtain : 0.1950 0.3452 0.5224 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] refridgerator : 0.2268 0.3289 0.4373 +[2025-02-22 12:26:00,424 INFO evaluator.py line 547 2775932] shower curtain : 0.4824 0.6749 0.7366 +[2025-02-22 12:26:00,425 INFO evaluator.py line 547 2775932] toilet : 0.7785 0.9825 0.9825 +[2025-02-22 12:26:00,425 INFO evaluator.py line 547 2775932] sink : 0.2620 0.5716 0.8584 +[2025-02-22 12:26:00,425 INFO evaluator.py line 547 2775932] bathtub : 0.6139 0.7379 0.8660 +[2025-02-22 12:26:00,425 INFO evaluator.py line 547 2775932] otherfurniture : 0.3173 0.4915 0.6388 +[2025-02-22 12:26:00,425 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:26:00,425 INFO evaluator.py line 554 2775932] average : 0.3237 0.5243 0.6934 +[2025-02-22 12:26:00,425 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:26:00,425 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:26:00,460 INFO misc.py line 164 2775932] Currently Best AP50: 0.5387 +[2025-02-22 12:26:00,464 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:26:09,525 INFO hook.py line 109 2775932] Train: [42/100][50/800] Data 0.003 (0.003) Batch 0.135 (0.150) Remain 01:57:46 loss: -0.3370 Lr: 4.10952e-03 +[2025-02-22 12:26:16,678 INFO hook.py line 109 2775932] Train: [42/100][100/800] Data 0.003 (0.003) Batch 0.152 (0.146) Remain 01:54:53 loss: -0.6109 Lr: 4.10376e-03 +[2025-02-22 12:26:23,884 INFO hook.py line 109 2775932] Train: [42/100][150/800] Data 0.007 (0.005) Batch 0.156 (0.146) Remain 01:54:10 loss: -0.5210 Lr: 4.09799e-03 +[2025-02-22 12:26:31,027 INFO hook.py line 109 2775932] Train: [42/100][200/800] Data 0.003 (0.004) Batch 0.135 (0.145) Remain 01:53:30 loss: -0.3906 Lr: 4.09222e-03 +[2025-02-22 12:26:38,391 INFO hook.py line 109 2775932] Train: [42/100][250/800] Data 0.003 (0.004) Batch 0.480 (0.145) Remain 01:53:45 loss: -0.4122 Lr: 4.08644e-03 +[2025-02-22 12:26:45,651 INFO hook.py line 109 2775932] Train: [42/100][300/800] Data 0.003 (0.004) Batch 0.118 (0.145) Remain 01:53:36 loss: -0.5862 Lr: 4.08066e-03 +[2025-02-22 12:26:52,834 INFO hook.py line 109 2775932] Train: [42/100][350/800] Data 0.002 (0.004) Batch 0.149 (0.145) Remain 01:53:18 loss: -0.1367 Lr: 4.07487e-03 +[2025-02-22 12:26:59,898 INFO hook.py line 109 2775932] Train: [42/100][400/800] Data 0.004 (0.004) Batch 0.138 (0.145) Remain 01:52:48 loss: -0.5403 Lr: 4.06908e-03 +[2025-02-22 12:27:07,002 INFO hook.py line 109 2775932] Train: [42/100][450/800] Data 0.003 (0.004) Batch 0.128 (0.144) Remain 01:52:27 loss: -0.5154 Lr: 4.06329e-03 +[2025-02-22 12:27:14,098 INFO hook.py line 109 2775932] Train: [42/100][500/800] Data 0.002 (0.004) Batch 0.140 (0.144) Remain 01:52:09 loss: -0.4234 Lr: 4.05749e-03 +[2025-02-22 12:27:21,207 INFO hook.py line 109 2775932] Train: [42/100][550/800] Data 0.003 (0.004) Batch 0.149 (0.144) Remain 01:51:53 loss: -0.0543 Lr: 4.05168e-03 +[2025-02-22 12:27:28,462 INFO hook.py line 109 2775932] Train: [42/100][600/800] Data 0.003 (0.004) Batch 0.255 (0.144) Remain 01:51:51 loss: -0.3413 Lr: 4.04587e-03 +[2025-02-22 12:27:35,546 INFO hook.py line 109 2775932] Train: [42/100][650/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 01:51:35 loss: -0.5098 Lr: 4.04006e-03 +[2025-02-22 12:27:42,742 INFO hook.py line 109 2775932] Train: [42/100][700/800] Data 0.003 (0.004) Batch 0.127 (0.144) Remain 01:51:28 loss: -0.5337 Lr: 4.03424e-03 +[2025-02-22 12:27:50,094 INFO hook.py line 109 2775932] Train: [42/100][750/800] Data 0.003 (0.004) Batch 0.156 (0.144) Remain 01:51:31 loss: 0.0576 Lr: 4.02842e-03 +[2025-02-22 12:27:56,908 INFO hook.py line 109 2775932] Train: [42/100][800/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 01:51:01 loss: -0.1681 Lr: 4.02259e-03 +[2025-02-22 12:27:56,909 INFO misc.py line 135 2775932] Train result: loss: -0.4070 seg_loss: 0.2519 bias_l1_loss: 0.2654 bias_cosine_loss: -0.9243 +[2025-02-22 12:27:56,909 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:28:04,159 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7730 +[2025-02-22 12:28:04,456 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2104 +[2025-02-22 12:28:04,546 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4917 +[2025-02-22 12:28:04,609 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5405 +[2025-02-22 12:28:04,678 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5953 +[2025-02-22 12:28:04,742 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5792 +[2025-02-22 12:28:05,005 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3826 +[2025-02-22 12:28:05,037 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4727 +[2025-02-22 12:28:05,170 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2362 +[2025-02-22 12:28:05,232 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0308 +[2025-02-22 12:28:05,489 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2910 +[2025-02-22 12:28:05,604 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1414 +[2025-02-22 12:28:05,679 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.3213 +[2025-02-22 12:28:05,773 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0329 +[2025-02-22 12:28:05,879 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.8181 +[2025-02-22 12:28:05,958 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.4003 +[2025-02-22 12:28:06,108 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4298 +[2025-02-22 12:28:06,212 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.0775 +[2025-02-22 12:28:06,381 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0322 +[2025-02-22 12:28:06,444 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3469 +[2025-02-22 12:28:06,591 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5005 +[2025-02-22 12:28:06,775 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.1560 +[2025-02-22 12:28:06,855 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0588 +[2025-02-22 12:28:06,913 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1195 +[2025-02-22 12:28:06,993 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3174 +[2025-02-22 12:28:07,061 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5457 +[2025-02-22 12:28:07,212 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2297 +[2025-02-22 12:28:07,312 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8825 +[2025-02-22 12:28:07,389 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6381 +[2025-02-22 12:28:07,457 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.3841 +[2025-02-22 12:28:08,322 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3758 +[2025-02-22 12:28:08,467 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.6447 +[2025-02-22 12:28:08,505 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7268 +[2025-02-22 12:28:08,607 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2853 +[2025-02-22 12:28:08,650 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6446 +[2025-02-22 12:28:08,762 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2479 +[2025-02-22 12:28:08,840 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5097 +[2025-02-22 12:28:08,960 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5634 +[2025-02-22 12:28:09,135 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0224 +[2025-02-22 12:28:09,337 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.4606 +[2025-02-22 12:28:09,481 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4499 +[2025-02-22 12:28:09,527 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0071 +[2025-02-22 12:28:09,567 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7830 +[2025-02-22 12:28:09,873 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6327 +[2025-02-22 12:28:09,918 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.2900 +[2025-02-22 12:28:09,965 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4568 +[2025-02-22 12:28:10,068 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4482 +[2025-02-22 12:28:10,190 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2936 +[2025-02-22 12:28:10,324 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2426 +[2025-02-22 12:28:10,417 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2017 +[2025-02-22 12:28:10,494 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3397 +[2025-02-22 12:28:10,652 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4330 +[2025-02-22 12:28:10,694 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6964 +[2025-02-22 12:28:10,799 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0870 +[2025-02-22 12:28:10,893 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8010 +[2025-02-22 12:28:10,942 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7303 +[2025-02-22 12:28:11,085 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1334 +[2025-02-22 12:28:11,130 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2942 +[2025-02-22 12:28:11,361 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3667 +[2025-02-22 12:28:11,477 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2241 +[2025-02-22 12:28:11,570 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.9631 +[2025-02-22 12:28:11,632 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4942 +[2025-02-22 12:28:11,810 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2488 +[2025-02-22 12:28:11,931 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5394 +[2025-02-22 12:28:12,002 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0306 +[2025-02-22 12:28:12,142 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2442 +[2025-02-22 12:28:12,344 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3232 +[2025-02-22 12:28:12,435 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0628 +[2025-02-22 12:28:12,492 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7722 +[2025-02-22 12:28:12,544 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1194 +[2025-02-22 12:28:12,698 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2226 +[2025-02-22 12:28:12,738 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4969 +[2025-02-22 12:28:12,786 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7425 +[2025-02-22 12:28:12,881 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2661 +[2025-02-22 12:28:13,089 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5858 +[2025-02-22 12:28:13,169 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0180 +[2025-02-22 12:28:13,331 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3845 +[2025-02-22 12:28:13,422 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6690 +[2025-02-22 12:28:25,397 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:28:25,398 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:28:25,398 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] cabinet : 0.2153 0.4433 0.6842 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] bed : 0.3549 0.7158 0.8364 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] chair : 0.7202 0.8761 0.9219 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] sofa : 0.3801 0.6809 0.8605 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] table : 0.3809 0.6462 0.7965 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] door : 0.2258 0.4531 0.6006 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] window : 0.1309 0.2534 0.4473 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] bookshelf : 0.1263 0.3491 0.6290 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] picture : 0.3336 0.5239 0.6310 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] counter : 0.0214 0.0799 0.3953 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] desk : 0.0584 0.1872 0.6300 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] curtain : 0.2304 0.4358 0.6256 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] refridgerator : 0.3689 0.5548 0.6242 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] shower curtain : 0.4774 0.7560 0.8495 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] toilet : 0.8379 0.9828 0.9828 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] sink : 0.2765 0.5319 0.8326 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] bathtub : 0.5771 0.7618 0.8646 +[2025-02-22 12:28:25,398 INFO evaluator.py line 547 2775932] otherfurniture : 0.4030 0.5883 0.7006 +[2025-02-22 12:28:25,398 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:28:25,398 INFO evaluator.py line 554 2775932] average : 0.3399 0.5456 0.7174 +[2025-02-22 12:28:25,398 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:28:25,457 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:28:25,499 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5456 +[2025-02-22 12:28:25,503 INFO misc.py line 164 2775932] Currently Best AP50: 0.5456 +[2025-02-22 12:28:25,503 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:28:34,480 INFO hook.py line 109 2775932] Train: [43/100][50/800] Data 0.003 (0.003) Batch 0.147 (0.146) Remain 01:52:28 loss: -0.4595 Lr: 4.01676e-03 +[2025-02-22 12:28:41,683 INFO hook.py line 109 2775932] Train: [43/100][100/800] Data 0.002 (0.003) Batch 0.131 (0.145) Remain 01:51:44 loss: -0.1406 Lr: 4.01093e-03 +[2025-02-22 12:28:48,804 INFO hook.py line 109 2775932] Train: [43/100][150/800] Data 0.002 (0.003) Batch 0.145 (0.144) Remain 01:50:59 loss: -0.5087 Lr: 4.00509e-03 +[2025-02-22 12:28:55,952 INFO hook.py line 109 2775932] Train: [43/100][200/800] Data 0.003 (0.003) Batch 0.133 (0.144) Remain 01:50:40 loss: -0.2945 Lr: 3.99924e-03 +[2025-02-22 12:29:03,436 INFO hook.py line 109 2775932] Train: [43/100][250/800] Data 0.002 (0.003) Batch 0.136 (0.145) Remain 01:51:28 loss: -0.4706 Lr: 3.99340e-03 +[2025-02-22 12:29:10,820 INFO hook.py line 109 2775932] Train: [43/100][300/800] Data 0.003 (0.003) Batch 0.153 (0.145) Remain 01:51:42 loss: -0.7826 Lr: 3.98754e-03 +[2025-02-22 12:29:18,176 INFO hook.py line 109 2775932] Train: [43/100][350/800] Data 0.004 (0.003) Batch 0.132 (0.146) Remain 01:51:47 loss: -0.4203 Lr: 3.98169e-03 +[2025-02-22 12:29:25,379 INFO hook.py line 109 2775932] Train: [43/100][400/800] Data 0.003 (0.003) Batch 0.131 (0.145) Remain 01:51:30 loss: -0.1901 Lr: 3.97583e-03 +[2025-02-22 12:29:32,525 INFO hook.py line 109 2775932] Train: [43/100][450/800] Data 0.004 (0.003) Batch 0.151 (0.145) Remain 01:51:10 loss: -0.4967 Lr: 3.96996e-03 +[2025-02-22 12:29:40,226 INFO hook.py line 109 2775932] Train: [43/100][500/800] Data 0.003 (0.004) Batch 0.161 (0.146) Remain 01:51:43 loss: -0.5133 Lr: 3.96409e-03 +[2025-02-22 12:29:47,321 INFO hook.py line 109 2775932] Train: [43/100][550/800] Data 0.003 (0.004) Batch 0.164 (0.146) Remain 01:51:19 loss: -0.5379 Lr: 3.95822e-03 +[2025-02-22 12:29:54,352 INFO hook.py line 109 2775932] Train: [43/100][600/800] Data 0.003 (0.004) Batch 0.146 (0.145) Remain 01:50:52 loss: -0.4903 Lr: 3.95234e-03 +[2025-02-22 12:30:01,635 INFO hook.py line 109 2775932] Train: [43/100][650/800] Data 0.003 (0.004) Batch 0.174 (0.145) Remain 01:50:46 loss: -0.6214 Lr: 3.94646e-03 +[2025-02-22 12:30:08,737 INFO hook.py line 109 2775932] Train: [43/100][700/800] Data 0.002 (0.004) Batch 0.142 (0.145) Remain 01:50:28 loss: -0.4745 Lr: 3.94057e-03 +[2025-02-22 12:30:15,860 INFO hook.py line 109 2775932] Train: [43/100][750/800] Data 0.003 (0.004) Batch 0.156 (0.145) Remain 01:50:13 loss: -0.4615 Lr: 3.93468e-03 +[2025-02-22 12:30:22,635 INFO hook.py line 109 2775932] Train: [43/100][800/800] Data 0.002 (0.004) Batch 0.120 (0.144) Remain 01:49:39 loss: -0.4337 Lr: 3.92879e-03 +[2025-02-22 12:30:22,636 INFO misc.py line 135 2775932] Train result: loss: -0.4138 seg_loss: 0.2504 bias_l1_loss: 0.2614 bias_cosine_loss: -0.9256 +[2025-02-22 12:30:22,637 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:30:30,004 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6514 +[2025-02-22 12:30:30,291 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5129 +[2025-02-22 12:30:30,361 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4318 +[2025-02-22 12:30:30,445 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5018 +[2025-02-22 12:30:30,530 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5910 +[2025-02-22 12:30:30,591 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8435 +[2025-02-22 12:30:30,879 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3611 +[2025-02-22 12:30:30,924 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5050 +[2025-02-22 12:30:31,089 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1618 +[2025-02-22 12:30:31,155 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3146 +[2025-02-22 12:30:31,407 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1047 +[2025-02-22 12:30:31,519 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1905 +[2025-02-22 12:30:31,598 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1241 +[2025-02-22 12:30:31,691 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2564 +[2025-02-22 12:30:31,776 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.9213 +[2025-02-22 12:30:31,855 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5883 +[2025-02-22 12:30:32,000 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4975 +[2025-02-22 12:30:32,099 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2145 +[2025-02-22 12:30:32,275 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1612 +[2025-02-22 12:30:32,355 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1338 +[2025-02-22 12:30:32,533 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6218 +[2025-02-22 12:30:32,749 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3023 +[2025-02-22 12:30:32,835 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0903 +[2025-02-22 12:30:32,905 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2623 +[2025-02-22 12:30:32,978 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3748 +[2025-02-22 12:30:33,049 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4691 +[2025-02-22 12:30:33,212 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1213 +[2025-02-22 12:30:33,342 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.3925 +[2025-02-22 12:30:33,440 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6729 +[2025-02-22 12:30:33,530 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6207 +[2025-02-22 12:30:34,533 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4433 +[2025-02-22 12:30:34,656 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1295 +[2025-02-22 12:30:34,710 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6805 +[2025-02-22 12:30:34,832 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2280 +[2025-02-22 12:30:34,870 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6582 +[2025-02-22 12:30:35,007 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9118 +[2025-02-22 12:30:35,086 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6094 +[2025-02-22 12:30:35,223 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6825 +[2025-02-22 12:30:35,383 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3256 +[2025-02-22 12:30:35,634 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6348 +[2025-02-22 12:30:35,803 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3779 +[2025-02-22 12:30:35,852 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0787 +[2025-02-22 12:30:35,893 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6499 +[2025-02-22 12:30:36,154 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5638 +[2025-02-22 12:30:36,196 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3579 +[2025-02-22 12:30:36,243 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5430 +[2025-02-22 12:30:36,341 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7036 +[2025-02-22 12:30:36,457 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3888 +[2025-02-22 12:30:36,557 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0405 +[2025-02-22 12:30:36,650 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2666 +[2025-02-22 12:30:36,728 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2800 +[2025-02-22 12:30:36,871 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4442 +[2025-02-22 12:30:36,911 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7484 +[2025-02-22 12:30:37,013 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1248 +[2025-02-22 12:30:37,116 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8266 +[2025-02-22 12:30:37,161 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7250 +[2025-02-22 12:30:37,290 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0315 +[2025-02-22 12:30:37,332 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4053 +[2025-02-22 12:30:37,558 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3674 +[2025-02-22 12:30:37,669 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0555 +[2025-02-22 12:30:37,740 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4705 +[2025-02-22 12:30:37,799 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5899 +[2025-02-22 12:30:37,952 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0597 +[2025-02-22 12:30:38,069 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5193 +[2025-02-22 12:30:38,168 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1296 +[2025-02-22 12:30:38,338 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0602 +[2025-02-22 12:30:38,530 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5464 +[2025-02-22 12:30:38,620 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2120 +[2025-02-22 12:30:38,677 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7379 +[2025-02-22 12:30:38,733 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2899 +[2025-02-22 12:30:38,879 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1273 +[2025-02-22 12:30:38,921 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5786 +[2025-02-22 12:30:38,976 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7616 +[2025-02-22 12:30:39,073 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4566 +[2025-02-22 12:30:39,276 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6616 +[2025-02-22 12:30:39,351 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0197 +[2025-02-22 12:30:39,547 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5286 +[2025-02-22 12:30:39,644 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6488 +[2025-02-22 12:30:51,836 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:30:51,836 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:30:51,836 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] cabinet : 0.1851 0.3755 0.6086 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] bed : 0.3365 0.6568 0.8325 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] chair : 0.7243 0.8868 0.9327 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] sofa : 0.3670 0.6966 0.8316 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] table : 0.3703 0.5604 0.6992 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] door : 0.1869 0.4077 0.5713 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] window : 0.2009 0.3691 0.5657 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] bookshelf : 0.2602 0.5685 0.7942 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] picture : 0.3407 0.5169 0.6242 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] counter : 0.0568 0.2136 0.6144 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] desk : 0.1195 0.3492 0.7372 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] curtain : 0.2513 0.4556 0.6051 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] refridgerator : 0.3958 0.5983 0.7134 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] shower curtain : 0.4221 0.6075 0.7284 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] toilet : 0.8142 0.9770 0.9934 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] sink : 0.2780 0.5378 0.8248 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] bathtub : 0.6544 0.7742 0.8710 +[2025-02-22 12:30:51,836 INFO evaluator.py line 547 2775932] otherfurniture : 0.3514 0.5191 0.6554 +[2025-02-22 12:30:51,836 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:30:51,836 INFO evaluator.py line 554 2775932] average : 0.3509 0.5595 0.7335 +[2025-02-22 12:30:51,836 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:30:51,837 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:30:51,876 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5595 +[2025-02-22 12:30:51,881 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:30:51,881 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:31:00,792 INFO hook.py line 109 2775932] Train: [44/100][50/800] Data 0.002 (0.003) Batch 0.133 (0.145) Remain 01:49:46 loss: -0.3841 Lr: 3.92289e-03 +[2025-02-22 12:31:07,779 INFO hook.py line 109 2775932] Train: [44/100][100/800] Data 0.002 (0.003) Batch 0.120 (0.142) Remain 01:47:45 loss: -0.5195 Lr: 3.91699e-03 +[2025-02-22 12:31:14,931 INFO hook.py line 109 2775932] Train: [44/100][150/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 01:47:52 loss: -0.6458 Lr: 3.91109e-03 +[2025-02-22 12:31:22,150 INFO hook.py line 109 2775932] Train: [44/100][200/800] Data 0.003 (0.004) Batch 0.141 (0.143) Remain 01:48:08 loss: -0.5128 Lr: 3.90518e-03 +[2025-02-22 12:31:29,457 INFO hook.py line 109 2775932] Train: [44/100][250/800] Data 0.003 (0.004) Batch 0.149 (0.144) Remain 01:48:30 loss: -0.4177 Lr: 3.89927e-03 +[2025-02-22 12:31:36,669 INFO hook.py line 109 2775932] Train: [44/100][300/800] Data 0.002 (0.004) Batch 0.133 (0.144) Remain 01:48:28 loss: -0.5825 Lr: 3.89335e-03 +[2025-02-22 12:31:43,782 INFO hook.py line 109 2775932] Train: [44/100][350/800] Data 0.003 (0.003) Batch 0.149 (0.143) Remain 01:48:12 loss: -0.3075 Lr: 3.88743e-03 +[2025-02-22 12:31:50,992 INFO hook.py line 109 2775932] Train: [44/100][400/800] Data 0.004 (0.003) Batch 0.137 (0.144) Remain 01:48:09 loss: -0.6156 Lr: 3.88150e-03 +[2025-02-22 12:31:57,953 INFO hook.py line 109 2775932] Train: [44/100][450/800] Data 0.003 (0.003) Batch 0.128 (0.143) Remain 01:47:39 loss: -0.0467 Lr: 3.87557e-03 +[2025-02-22 12:32:05,561 INFO hook.py line 109 2775932] Train: [44/100][500/800] Data 0.003 (0.003) Batch 0.121 (0.144) Remain 01:48:14 loss: -0.5295 Lr: 3.86964e-03 +[2025-02-22 12:32:12,857 INFO hook.py line 109 2775932] Train: [44/100][550/800] Data 0.004 (0.003) Batch 0.148 (0.144) Remain 01:48:14 loss: -0.5064 Lr: 3.86371e-03 +[2025-02-22 12:32:20,141 INFO hook.py line 109 2775932] Train: [44/100][600/800] Data 0.004 (0.003) Batch 0.143 (0.144) Remain 01:48:13 loss: -0.5267 Lr: 3.85777e-03 +[2025-02-22 12:32:27,463 INFO hook.py line 109 2775932] Train: [44/100][650/800] Data 0.005 (0.003) Batch 0.154 (0.144) Remain 01:48:13 loss: -0.4109 Lr: 3.85182e-03 +[2025-02-22 12:32:34,495 INFO hook.py line 109 2775932] Train: [44/100][700/800] Data 0.003 (0.003) Batch 0.137 (0.144) Remain 01:47:53 loss: -0.2264 Lr: 3.84588e-03 +[2025-02-22 12:32:41,751 INFO hook.py line 109 2775932] Train: [44/100][750/800] Data 0.003 (0.003) Batch 0.152 (0.144) Remain 01:47:49 loss: -0.5126 Lr: 3.83993e-03 +[2025-02-22 12:32:48,736 INFO hook.py line 109 2775932] Train: [44/100][800/800] Data 0.002 (0.003) Batch 0.122 (0.144) Remain 01:47:29 loss: -0.4200 Lr: 3.83397e-03 +[2025-02-22 12:32:48,737 INFO misc.py line 135 2775932] Train result: loss: -0.4139 seg_loss: 0.2498 bias_l1_loss: 0.2618 bias_cosine_loss: -0.9255 +[2025-02-22 12:32:48,738 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:32:55,680 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7621 +[2025-02-22 12:32:56,479 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3519 +[2025-02-22 12:32:56,554 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4843 +[2025-02-22 12:32:56,669 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5985 +[2025-02-22 12:32:57,143 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6254 +[2025-02-22 12:32:57,219 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7782 +[2025-02-22 12:32:57,497 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4876 +[2025-02-22 12:32:57,548 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4112 +[2025-02-22 12:32:57,698 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0517 +[2025-02-22 12:32:57,776 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1835 +[2025-02-22 12:32:58,026 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1278 +[2025-02-22 12:32:58,143 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2764 +[2025-02-22 12:32:58,218 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.6618 +[2025-02-22 12:32:58,307 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2665 +[2025-02-22 12:32:58,392 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2190 +[2025-02-22 12:32:58,459 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5417 +[2025-02-22 12:32:58,605 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3292 +[2025-02-22 12:32:58,692 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1442 +[2025-02-22 12:32:58,955 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0373 +[2025-02-22 12:32:59,052 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3796 +[2025-02-22 12:32:59,216 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5565 +[2025-02-22 12:32:59,386 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2227 +[2025-02-22 12:32:59,453 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.3970 +[2025-02-22 12:32:59,519 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2843 +[2025-02-22 12:32:59,588 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2427 +[2025-02-22 12:32:59,641 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4540 +[2025-02-22 12:32:59,756 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1738 +[2025-02-22 12:32:59,858 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6549 +[2025-02-22 12:32:59,948 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6300 +[2025-02-22 12:33:00,024 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5635 +[2025-02-22 12:33:00,909 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.2289 +[2025-02-22 12:33:01,049 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7150 +[2025-02-22 12:33:01,099 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6986 +[2025-02-22 12:33:01,212 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0265 +[2025-02-22 12:33:01,251 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4974 +[2025-02-22 12:33:01,374 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8874 +[2025-02-22 12:33:01,443 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5670 +[2025-02-22 12:33:01,585 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6646 +[2025-02-22 12:33:01,763 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1608 +[2025-02-22 12:33:01,967 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6420 +[2025-02-22 12:33:02,143 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5528 +[2025-02-22 12:33:02,197 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0671 +[2025-02-22 12:33:02,248 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7260 +[2025-02-22 12:33:02,497 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5663 +[2025-02-22 12:33:02,540 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4581 +[2025-02-22 12:33:02,591 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5476 +[2025-02-22 12:33:02,747 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7892 +[2025-02-22 12:33:02,868 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2526 +[2025-02-22 12:33:03,013 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1890 +[2025-02-22 12:33:03,117 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0946 +[2025-02-22 12:33:03,193 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1642 +[2025-02-22 12:33:03,385 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3440 +[2025-02-22 12:33:03,430 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5323 +[2025-02-22 12:33:03,534 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.6005 +[2025-02-22 12:33:03,654 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8238 +[2025-02-22 12:33:03,710 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6503 +[2025-02-22 12:33:03,870 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1553 +[2025-02-22 12:33:03,923 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2714 +[2025-02-22 12:33:04,153 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.1284 +[2025-02-22 12:33:04,295 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1227 +[2025-02-22 12:33:04,384 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.9421 +[2025-02-22 12:33:04,470 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5530 +[2025-02-22 12:33:04,640 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1839 +[2025-02-22 12:33:04,757 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3125 +[2025-02-22 12:33:04,830 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1218 +[2025-02-22 12:33:04,954 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2940 +[2025-02-22 12:33:05,115 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.3776 +[2025-02-22 12:33:05,209 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0329 +[2025-02-22 12:33:05,263 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8477 +[2025-02-22 12:33:05,313 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1114 +[2025-02-22 12:33:05,466 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0688 +[2025-02-22 12:33:05,503 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4375 +[2025-02-22 12:33:05,559 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7032 +[2025-02-22 12:33:05,650 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7180 +[2025-02-22 12:33:05,875 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5905 +[2025-02-22 12:33:05,955 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1746 +[2025-02-22 12:33:06,114 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4631 +[2025-02-22 12:33:06,212 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6119 +[2025-02-22 12:33:15,665 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:33:15,665 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:33:15,665 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] cabinet : 0.1846 0.3661 0.6111 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] bed : 0.3312 0.7006 0.8390 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] chair : 0.7278 0.8838 0.9290 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] sofa : 0.4572 0.7618 0.8582 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] table : 0.3584 0.5667 0.7204 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] door : 0.2220 0.4247 0.5594 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] window : 0.2025 0.3557 0.5595 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] bookshelf : 0.1634 0.4124 0.6874 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] picture : 0.2701 0.3723 0.4753 +[2025-02-22 12:33:15,665 INFO evaluator.py line 547 2775932] counter : 0.0249 0.1420 0.6132 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] desk : 0.1233 0.3465 0.8186 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] curtain : 0.1694 0.3082 0.4100 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] refridgerator : 0.1453 0.2632 0.2963 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] shower curtain : 0.4962 0.6318 0.7488 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] toilet : 0.7789 0.9282 0.9796 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] sink : 0.2604 0.4516 0.7893 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] bathtub : 0.6474 0.7742 0.8710 +[2025-02-22 12:33:15,666 INFO evaluator.py line 547 2775932] otherfurniture : 0.3093 0.4782 0.5930 +[2025-02-22 12:33:15,666 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:33:15,666 INFO evaluator.py line 554 2775932] average : 0.3262 0.5093 0.6866 +[2025-02-22 12:33:15,666 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:33:15,666 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:33:15,697 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:33:15,702 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:33:24,300 INFO hook.py line 109 2775932] Train: [45/100][50/800] Data 0.003 (0.006) Batch 0.149 (0.151) Remain 01:52:53 loss: -0.3924 Lr: 3.82814e-03 +[2025-02-22 12:33:31,510 INFO hook.py line 109 2775932] Train: [45/100][100/800] Data 0.003 (0.007) Batch 0.135 (0.148) Remain 01:50:01 loss: -0.4069 Lr: 3.82217e-03 +[2025-02-22 12:33:38,567 INFO hook.py line 109 2775932] Train: [45/100][150/800] Data 0.004 (0.005) Batch 0.145 (0.145) Remain 01:48:14 loss: -0.6420 Lr: 3.81621e-03 +[2025-02-22 12:33:45,628 INFO hook.py line 109 2775932] Train: [45/100][200/800] Data 0.003 (0.005) Batch 0.138 (0.144) Remain 01:47:19 loss: -0.5128 Lr: 3.81024e-03 +[2025-02-22 12:33:53,043 INFO hook.py line 109 2775932] Train: [45/100][250/800] Data 0.003 (0.004) Batch 0.130 (0.145) Remain 01:47:47 loss: -0.4999 Lr: 3.80427e-03 +[2025-02-22 12:34:00,139 INFO hook.py line 109 2775932] Train: [45/100][300/800] Data 0.003 (0.004) Batch 0.143 (0.145) Remain 01:47:15 loss: -0.3875 Lr: 3.79830e-03 +[2025-02-22 12:34:07,353 INFO hook.py line 109 2775932] Train: [45/100][350/800] Data 0.003 (0.004) Batch 0.143 (0.145) Remain 01:47:06 loss: -0.4157 Lr: 3.79232e-03 +[2025-02-22 12:34:14,289 INFO hook.py line 109 2775932] Train: [45/100][400/800] Data 0.003 (0.004) Batch 0.144 (0.144) Remain 01:46:26 loss: -0.4857 Lr: 3.78634e-03 +[2025-02-22 12:34:21,245 INFO hook.py line 109 2775932] Train: [45/100][450/800] Data 0.002 (0.004) Batch 0.135 (0.143) Remain 01:45:55 loss: -0.4092 Lr: 3.78035e-03 +[2025-02-22 12:34:28,153 INFO hook.py line 109 2775932] Train: [45/100][500/800] Data 0.004 (0.004) Batch 0.139 (0.143) Remain 01:45:25 loss: -0.4735 Lr: 3.77436e-03 +[2025-02-22 12:34:35,227 INFO hook.py line 109 2775932] Train: [45/100][550/800] Data 0.002 (0.004) Batch 0.125 (0.143) Remain 01:45:13 loss: -0.3702 Lr: 3.76837e-03 +[2025-02-22 12:34:42,825 INFO hook.py line 109 2775932] Train: [45/100][600/800] Data 0.002 (0.004) Batch 0.127 (0.143) Remain 01:45:40 loss: -0.3629 Lr: 3.76238e-03 +[2025-02-22 12:34:49,875 INFO hook.py line 109 2775932] Train: [45/100][650/800] Data 0.004 (0.004) Batch 0.147 (0.143) Remain 01:45:24 loss: -0.2689 Lr: 3.75638e-03 +[2025-02-22 12:34:56,965 INFO hook.py line 109 2775932] Train: [45/100][700/800] Data 0.003 (0.004) Batch 0.140 (0.143) Remain 01:45:12 loss: -0.5805 Lr: 3.75038e-03 +[2025-02-22 12:35:04,112 INFO hook.py line 109 2775932] Train: [45/100][750/800] Data 0.002 (0.004) Batch 0.149 (0.143) Remain 01:45:05 loss: -0.4423 Lr: 3.74437e-03 +[2025-02-22 12:35:11,093 INFO hook.py line 109 2775932] Train: [45/100][800/800] Data 0.002 (0.003) Batch 0.098 (0.143) Remain 01:44:48 loss: -0.5412 Lr: 3.73837e-03 +[2025-02-22 12:35:11,094 INFO misc.py line 135 2775932] Train result: loss: -0.4387 seg_loss: 0.2363 bias_l1_loss: 0.2530 bias_cosine_loss: -0.9281 +[2025-02-22 12:35:11,094 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:35:18,018 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7220 +[2025-02-22 12:35:18,502 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3758 +[2025-02-22 12:35:18,578 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4981 +[2025-02-22 12:35:18,645 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5302 +[2025-02-22 12:35:18,712 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6829 +[2025-02-22 12:35:18,775 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0154 +[2025-02-22 12:35:19,061 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.3755 +[2025-02-22 12:35:19,092 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4716 +[2025-02-22 12:35:19,265 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0737 +[2025-02-22 12:35:19,323 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0436 +[2025-02-22 12:35:19,569 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1681 +[2025-02-22 12:35:19,686 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0807 +[2025-02-22 12:35:19,769 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4533 +[2025-02-22 12:35:19,871 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7606 +[2025-02-22 12:35:19,962 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1620 +[2025-02-22 12:35:20,040 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3409 +[2025-02-22 12:35:20,222 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2934 +[2025-02-22 12:35:20,330 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2326 +[2025-02-22 12:35:20,496 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.3486 +[2025-02-22 12:35:20,563 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1790 +[2025-02-22 12:35:20,733 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6336 +[2025-02-22 12:35:20,968 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2253 +[2025-02-22 12:35:21,051 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0596 +[2025-02-22 12:35:21,116 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0808 +[2025-02-22 12:35:21,206 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2552 +[2025-02-22 12:35:21,270 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4663 +[2025-02-22 12:35:21,448 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2098 +[2025-02-22 12:35:21,538 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7904 +[2025-02-22 12:35:21,605 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5984 +[2025-02-22 12:35:21,685 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6279 +[2025-02-22 12:35:22,678 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4373 +[2025-02-22 12:35:22,809 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1673 +[2025-02-22 12:35:22,855 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7005 +[2025-02-22 12:35:22,983 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0584 +[2025-02-22 12:35:23,023 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6555 +[2025-02-22 12:35:23,157 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0286 +[2025-02-22 12:35:23,248 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4311 +[2025-02-22 12:35:23,388 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5394 +[2025-02-22 12:35:23,564 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1762 +[2025-02-22 12:35:23,798 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9995 +[2025-02-22 12:35:23,963 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4041 +[2025-02-22 12:35:24,017 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.0863 +[2025-02-22 12:35:24,061 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6601 +[2025-02-22 12:35:24,340 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5464 +[2025-02-22 12:35:24,383 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5723 +[2025-02-22 12:35:24,429 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4802 +[2025-02-22 12:35:24,537 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5644 +[2025-02-22 12:35:24,670 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4077 +[2025-02-22 12:35:24,778 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1793 +[2025-02-22 12:35:24,876 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2127 +[2025-02-22 12:35:24,943 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3049 +[2025-02-22 12:35:25,078 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2624 +[2025-02-22 12:35:25,132 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6679 +[2025-02-22 12:35:25,229 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2773 +[2025-02-22 12:35:25,319 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7445 +[2025-02-22 12:35:25,363 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7255 +[2025-02-22 12:35:25,477 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1157 +[2025-02-22 12:35:25,532 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2693 +[2025-02-22 12:35:25,741 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3818 +[2025-02-22 12:35:25,870 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1847 +[2025-02-22 12:35:25,936 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8775 +[2025-02-22 12:35:25,991 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4642 +[2025-02-22 12:35:26,160 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1506 +[2025-02-22 12:35:26,293 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6671 +[2025-02-22 12:35:26,376 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1638 +[2025-02-22 12:35:26,503 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1118 +[2025-02-22 12:35:26,695 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5334 +[2025-02-22 12:35:26,792 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0235 +[2025-02-22 12:35:26,852 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6165 +[2025-02-22 12:35:26,904 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0343 +[2025-02-22 12:35:27,069 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2956 +[2025-02-22 12:35:27,108 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4741 +[2025-02-22 12:35:27,159 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7002 +[2025-02-22 12:35:27,265 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2304 +[2025-02-22 12:35:27,480 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4986 +[2025-02-22 12:35:27,563 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0595 +[2025-02-22 12:35:27,740 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4804 +[2025-02-22 12:35:27,839 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6159 +[2025-02-22 12:35:41,185 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:35:41,185 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:35:41,185 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] cabinet : 0.2297 0.4307 0.6420 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] bed : 0.3620 0.7261 0.8259 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] chair : 0.7017 0.8556 0.9073 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] sofa : 0.3990 0.6752 0.8373 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] table : 0.3843 0.6029 0.7253 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] door : 0.2201 0.4492 0.6276 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] window : 0.2097 0.4086 0.6028 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] bookshelf : 0.2040 0.4468 0.6596 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] picture : 0.2828 0.4395 0.5590 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] counter : 0.0486 0.1810 0.5686 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] desk : 0.1199 0.3052 0.7822 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] curtain : 0.2467 0.4003 0.5379 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] refridgerator : 0.4100 0.6232 0.6494 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] shower curtain : 0.4062 0.5112 0.6023 +[2025-02-22 12:35:41,185 INFO evaluator.py line 547 2775932] toilet : 0.8629 0.9979 0.9979 +[2025-02-22 12:35:41,186 INFO evaluator.py line 547 2775932] sink : 0.3400 0.6304 0.8640 +[2025-02-22 12:35:41,186 INFO evaluator.py line 547 2775932] bathtub : 0.6113 0.7917 0.8686 +[2025-02-22 12:35:41,186 INFO evaluator.py line 547 2775932] otherfurniture : 0.3716 0.5599 0.6727 +[2025-02-22 12:35:41,186 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:35:41,186 INFO evaluator.py line 554 2775932] average : 0.3561 0.5575 0.7184 +[2025-02-22 12:35:41,186 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:35:41,186 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:35:41,226 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:35:41,230 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:35:49,678 INFO hook.py line 109 2775932] Train: [46/100][50/800] Data 0.003 (0.003) Batch 0.146 (0.143) Remain 01:44:28 loss: -0.6338 Lr: 3.73235e-03 +[2025-02-22 12:35:56,865 INFO hook.py line 109 2775932] Train: [46/100][100/800] Data 0.003 (0.003) Batch 0.129 (0.143) Remain 01:44:46 loss: -0.2797 Lr: 3.72634e-03 +[2025-02-22 12:36:03,902 INFO hook.py line 109 2775932] Train: [46/100][150/800] Data 0.003 (0.003) Batch 0.149 (0.142) Remain 01:44:02 loss: -0.3893 Lr: 3.72032e-03 +[2025-02-22 12:36:10,982 INFO hook.py line 109 2775932] Train: [46/100][200/800] Data 0.003 (0.003) Batch 0.154 (0.142) Remain 01:43:47 loss: -0.5108 Lr: 3.71430e-03 +[2025-02-22 12:36:17,875 INFO hook.py line 109 2775932] Train: [46/100][250/800] Data 0.002 (0.003) Batch 0.130 (0.141) Remain 01:43:01 loss: -0.4672 Lr: 3.70828e-03 +[2025-02-22 12:36:25,304 INFO hook.py line 109 2775932] Train: [46/100][300/800] Data 0.003 (0.004) Batch 0.128 (0.143) Remain 01:43:48 loss: -0.5199 Lr: 3.70225e-03 +[2025-02-22 12:36:32,349 INFO hook.py line 109 2775932] Train: [46/100][350/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 01:43:30 loss: -0.2879 Lr: 3.69622e-03 +[2025-02-22 12:36:39,608 INFO hook.py line 109 2775932] Train: [46/100][400/800] Data 0.003 (0.003) Batch 0.176 (0.143) Remain 01:43:39 loss: -0.4176 Lr: 3.69019e-03 +[2025-02-22 12:36:46,608 INFO hook.py line 109 2775932] Train: [46/100][450/800] Data 0.003 (0.003) Batch 0.159 (0.142) Remain 01:43:19 loss: 0.0723 Lr: 3.68416e-03 +[2025-02-22 12:36:53,813 INFO hook.py line 109 2775932] Train: [46/100][500/800] Data 0.002 (0.003) Batch 0.225 (0.143) Remain 01:43:20 loss: -0.5277 Lr: 3.67812e-03 +[2025-02-22 12:37:01,121 INFO hook.py line 109 2775932] Train: [46/100][550/800] Data 0.003 (0.003) Batch 0.162 (0.143) Remain 01:43:27 loss: -0.5676 Lr: 3.67208e-03 +[2025-02-22 12:37:08,363 INFO hook.py line 109 2775932] Train: [46/100][600/800] Data 0.002 (0.003) Batch 0.132 (0.143) Remain 01:43:27 loss: -0.1279 Lr: 3.66603e-03 +[2025-02-22 12:37:15,704 INFO hook.py line 109 2775932] Train: [46/100][650/800] Data 0.002 (0.003) Batch 0.139 (0.143) Remain 01:43:32 loss: -0.5841 Lr: 3.65999e-03 +[2025-02-22 12:37:22,810 INFO hook.py line 109 2775932] Train: [46/100][700/800] Data 0.003 (0.003) Batch 0.142 (0.143) Remain 01:43:22 loss: -0.4969 Lr: 3.65394e-03 +[2025-02-22 12:37:29,925 INFO hook.py line 109 2775932] Train: [46/100][750/800] Data 0.002 (0.003) Batch 0.115 (0.143) Remain 01:43:12 loss: -0.5933 Lr: 3.64789e-03 +[2025-02-22 12:37:37,013 INFO hook.py line 109 2775932] Train: [46/100][800/800] Data 0.002 (0.003) Batch 0.127 (0.143) Remain 01:43:01 loss: -0.5521 Lr: 3.64183e-03 +[2025-02-22 12:37:37,013 INFO misc.py line 135 2775932] Train result: loss: -0.4440 seg_loss: 0.2367 bias_l1_loss: 0.2499 bias_cosine_loss: -0.9306 +[2025-02-22 12:37:37,014 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:37:44,399 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7479 +[2025-02-22 12:37:44,857 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.2166 +[2025-02-22 12:37:44,923 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4361 +[2025-02-22 12:37:44,994 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6788 +[2025-02-22 12:37:45,062 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6339 +[2025-02-22 12:37:45,119 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0676 +[2025-02-22 12:37:45,380 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4792 +[2025-02-22 12:37:45,408 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4343 +[2025-02-22 12:37:45,538 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0524 +[2025-02-22 12:37:45,602 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2463 +[2025-02-22 12:37:45,864 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3051 +[2025-02-22 12:37:45,975 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1807 +[2025-02-22 12:37:46,053 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.2512 +[2025-02-22 12:37:46,139 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0980 +[2025-02-22 12:37:46,221 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2110 +[2025-02-22 12:37:46,297 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6210 +[2025-02-22 12:37:46,447 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4773 +[2025-02-22 12:37:46,545 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4561 +[2025-02-22 12:37:46,718 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2034 +[2025-02-22 12:37:46,804 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0422 +[2025-02-22 12:37:46,957 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6394 +[2025-02-22 12:37:47,145 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1808 +[2025-02-22 12:37:47,224 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0141 +[2025-02-22 12:37:47,285 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0061 +[2025-02-22 12:37:47,358 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3442 +[2025-02-22 12:37:47,433 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4724 +[2025-02-22 12:37:47,612 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0626 +[2025-02-22 12:37:47,731 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6719 +[2025-02-22 12:37:47,808 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6112 +[2025-02-22 12:37:47,875 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6428 +[2025-02-22 12:37:48,612 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4312 +[2025-02-22 12:37:48,744 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1325 +[2025-02-22 12:37:48,785 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7355 +[2025-02-22 12:37:48,890 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1035 +[2025-02-22 12:37:48,935 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6495 +[2025-02-22 12:37:49,074 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.7949 +[2025-02-22 12:37:49,145 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6246 +[2025-02-22 12:37:49,270 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6071 +[2025-02-22 12:37:49,421 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3872 +[2025-02-22 12:37:49,613 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6221 +[2025-02-22 12:37:49,776 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4379 +[2025-02-22 12:37:49,820 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3391 +[2025-02-22 12:37:49,856 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6950 +[2025-02-22 12:37:50,112 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6280 +[2025-02-22 12:37:50,149 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5071 +[2025-02-22 12:37:50,194 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5198 +[2025-02-22 12:37:50,287 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3020 +[2025-02-22 12:37:50,394 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0959 +[2025-02-22 12:37:50,486 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2316 +[2025-02-22 12:37:50,566 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2901 +[2025-02-22 12:37:50,642 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2410 +[2025-02-22 12:37:50,764 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4585 +[2025-02-22 12:37:50,800 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7471 +[2025-02-22 12:37:50,895 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0604 +[2025-02-22 12:37:50,992 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8074 +[2025-02-22 12:37:51,036 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7491 +[2025-02-22 12:37:51,149 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0120 +[2025-02-22 12:37:51,196 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4803 +[2025-02-22 12:37:51,389 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2510 +[2025-02-22 12:37:51,509 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1976 +[2025-02-22 12:37:51,582 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5211 +[2025-02-22 12:37:51,638 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4172 +[2025-02-22 12:37:51,804 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2102 +[2025-02-22 12:37:51,935 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4116 +[2025-02-22 12:37:52,015 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1154 +[2025-02-22 12:37:52,141 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0787 +[2025-02-22 12:37:52,323 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5140 +[2025-02-22 12:37:52,414 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1725 +[2025-02-22 12:37:52,485 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7172 +[2025-02-22 12:37:52,535 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1081 +[2025-02-22 12:37:52,707 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2186 +[2025-02-22 12:37:52,744 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3832 +[2025-02-22 12:37:52,806 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7284 +[2025-02-22 12:37:52,915 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.8281 +[2025-02-22 12:37:53,128 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5481 +[2025-02-22 12:37:53,204 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2826 +[2025-02-22 12:37:53,392 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4384 +[2025-02-22 12:37:53,484 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5361 +[2025-02-22 12:38:05,202 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:38:05,203 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:38:05,203 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] cabinet : 0.1677 0.3712 0.6450 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] bed : 0.3414 0.7144 0.8830 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] chair : 0.7456 0.8968 0.9387 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] sofa : 0.3134 0.5416 0.8009 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] table : 0.3760 0.5893 0.7337 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] door : 0.2084 0.4193 0.5737 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] window : 0.1603 0.3158 0.5450 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] bookshelf : 0.1881 0.4293 0.6403 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] picture : 0.2427 0.3745 0.5011 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] counter : 0.0288 0.1279 0.6578 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] desk : 0.1236 0.3733 0.8112 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] curtain : 0.2869 0.4888 0.6141 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] refridgerator : 0.2609 0.3636 0.4656 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] shower curtain : 0.4767 0.6184 0.6424 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] toilet : 0.8533 0.9985 0.9985 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] sink : 0.3323 0.6108 0.8382 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] bathtub : 0.6461 0.8065 0.8710 +[2025-02-22 12:38:05,203 INFO evaluator.py line 547 2775932] otherfurniture : 0.3715 0.5541 0.6563 +[2025-02-22 12:38:05,203 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:38:05,203 INFO evaluator.py line 554 2775932] average : 0.3402 0.5330 0.7120 +[2025-02-22 12:38:05,203 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:38:05,203 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:38:05,240 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:38:05,245 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:38:13,423 INFO hook.py line 109 2775932] Train: [47/100][50/800] Data 0.003 (0.003) Batch 0.115 (0.141) Remain 01:41:40 loss: -0.5537 Lr: 3.63577e-03 +[2025-02-22 12:38:20,632 INFO hook.py line 109 2775932] Train: [47/100][100/800] Data 0.002 (0.004) Batch 0.145 (0.143) Remain 01:42:35 loss: -0.2713 Lr: 3.62971e-03 +[2025-02-22 12:38:27,931 INFO hook.py line 109 2775932] Train: [47/100][150/800] Data 0.002 (0.005) Batch 0.132 (0.144) Remain 01:43:14 loss: -0.4639 Lr: 3.62365e-03 +[2025-02-22 12:38:35,140 INFO hook.py line 109 2775932] Train: [47/100][200/800] Data 0.003 (0.004) Batch 0.146 (0.144) Remain 01:43:10 loss: -0.4794 Lr: 3.61758e-03 +[2025-02-22 12:38:42,245 INFO hook.py line 109 2775932] Train: [47/100][250/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 01:42:46 loss: -0.4676 Lr: 3.61151e-03 +[2025-02-22 12:38:49,357 INFO hook.py line 109 2775932] Train: [47/100][300/800] Data 0.003 (0.004) Batch 0.144 (0.143) Remain 01:42:30 loss: -0.3920 Lr: 3.60544e-03 +[2025-02-22 12:38:56,469 INFO hook.py line 109 2775932] Train: [47/100][350/800] Data 0.003 (0.004) Batch 0.137 (0.143) Remain 01:42:15 loss: -0.6218 Lr: 3.59937e-03 +[2025-02-22 12:39:03,593 INFO hook.py line 109 2775932] Train: [47/100][400/800] Data 0.003 (0.004) Batch 0.128 (0.143) Remain 01:42:04 loss: -0.4086 Lr: 3.59329e-03 +[2025-02-22 12:39:10,737 INFO hook.py line 109 2775932] Train: [47/100][450/800] Data 0.005 (0.004) Batch 0.130 (0.143) Remain 01:41:56 loss: -0.5511 Lr: 3.58721e-03 +[2025-02-22 12:39:17,991 INFO hook.py line 109 2775932] Train: [47/100][500/800] Data 0.002 (0.004) Batch 0.117 (0.143) Remain 01:41:57 loss: -0.6106 Lr: 3.58113e-03 +[2025-02-22 12:39:25,225 INFO hook.py line 109 2775932] Train: [47/100][550/800] Data 0.003 (0.004) Batch 0.139 (0.143) Remain 01:41:56 loss: -0.1369 Lr: 3.57505e-03 +[2025-02-22 12:39:32,275 INFO hook.py line 109 2775932] Train: [47/100][600/800] Data 0.004 (0.003) Batch 0.163 (0.143) Remain 01:41:40 loss: -0.5123 Lr: 3.56896e-03 +[2025-02-22 12:39:39,405 INFO hook.py line 109 2775932] Train: [47/100][650/800] Data 0.003 (0.003) Batch 0.153 (0.143) Remain 01:41:31 loss: -0.3107 Lr: 3.56300e-03 +[2025-02-22 12:39:46,792 INFO hook.py line 109 2775932] Train: [47/100][700/800] Data 0.004 (0.003) Batch 0.158 (0.143) Remain 01:41:38 loss: -0.3978 Lr: 3.55691e-03 +[2025-02-22 12:39:54,066 INFO hook.py line 109 2775932] Train: [47/100][750/800] Data 0.003 (0.003) Batch 0.130 (0.144) Remain 01:41:36 loss: -0.3611 Lr: 3.55081e-03 +[2025-02-22 12:40:00,979 INFO hook.py line 109 2775932] Train: [47/100][800/800] Data 0.002 (0.003) Batch 0.110 (0.143) Remain 01:41:15 loss: -0.4744 Lr: 3.54472e-03 +[2025-02-22 12:40:00,980 INFO misc.py line 135 2775932] Train result: loss: -0.4493 seg_loss: 0.2279 bias_l1_loss: 0.2518 bias_cosine_loss: -0.9289 +[2025-02-22 12:40:00,980 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:40:08,128 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.6886 +[2025-02-22 12:40:08,537 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3346 +[2025-02-22 12:40:08,621 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4433 +[2025-02-22 12:40:08,704 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4939 +[2025-02-22 12:40:08,778 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6166 +[2025-02-22 12:40:08,834 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.6943 +[2025-02-22 12:40:09,134 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5266 +[2025-02-22 12:40:09,168 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4708 +[2025-02-22 12:40:09,358 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0682 +[2025-02-22 12:40:09,438 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0326 +[2025-02-22 12:40:09,704 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1005 +[2025-02-22 12:40:09,820 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1230 +[2025-02-22 12:40:09,897 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0502 +[2025-02-22 12:40:10,003 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1508 +[2025-02-22 12:40:10,094 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3980 +[2025-02-22 12:40:10,175 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5608 +[2025-02-22 12:40:10,344 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.2378 +[2025-02-22 12:40:10,452 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.2498 +[2025-02-22 12:40:10,639 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0549 +[2025-02-22 12:40:10,726 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1452 +[2025-02-22 12:40:10,922 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5716 +[2025-02-22 12:40:11,138 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2553 +[2025-02-22 12:40:11,224 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0068 +[2025-02-22 12:40:11,293 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1707 +[2025-02-22 12:40:11,392 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0917 +[2025-02-22 12:40:11,464 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5485 +[2025-02-22 12:40:11,649 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3301 +[2025-02-22 12:40:11,755 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.2679 +[2025-02-22 12:40:11,841 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5079 +[2025-02-22 12:40:11,927 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6131 +[2025-02-22 12:40:12,675 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4419 +[2025-02-22 12:40:12,841 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4881 +[2025-02-22 12:40:12,891 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6942 +[2025-02-22 12:40:12,991 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3180 +[2025-02-22 12:40:13,034 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.7151 +[2025-02-22 12:40:13,161 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0569 +[2025-02-22 12:40:13,237 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6216 +[2025-02-22 12:40:13,386 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7067 +[2025-02-22 12:40:13,559 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4345 +[2025-02-22 12:40:13,824 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.4771 +[2025-02-22 12:40:14,024 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.8541 +[2025-02-22 12:40:14,074 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3020 +[2025-02-22 12:40:14,114 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.5339 +[2025-02-22 12:40:14,395 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4900 +[2025-02-22 12:40:14,437 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4027 +[2025-02-22 12:40:14,483 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4488 +[2025-02-22 12:40:14,583 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1960 +[2025-02-22 12:40:14,723 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3240 +[2025-02-22 12:40:14,833 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2892 +[2025-02-22 12:40:14,943 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0769 +[2025-02-22 12:40:15,023 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2913 +[2025-02-22 12:40:15,172 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2706 +[2025-02-22 12:40:15,214 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6835 +[2025-02-22 12:40:15,335 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0922 +[2025-02-22 12:40:15,431 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8230 +[2025-02-22 12:40:15,480 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7693 +[2025-02-22 12:40:15,635 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0954 +[2025-02-22 12:40:15,683 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3458 +[2025-02-22 12:40:15,911 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2421 +[2025-02-22 12:40:16,021 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2279 +[2025-02-22 12:40:16,103 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.5216 +[2025-02-22 12:40:16,163 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6628 +[2025-02-22 12:40:16,322 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1282 +[2025-02-22 12:40:16,435 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3365 +[2025-02-22 12:40:16,521 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3433 +[2025-02-22 12:40:16,665 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0228 +[2025-02-22 12:40:16,849 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4741 +[2025-02-22 12:40:16,942 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0885 +[2025-02-22 12:40:17,002 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.5814 +[2025-02-22 12:40:17,052 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2589 +[2025-02-22 12:40:17,220 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0263 +[2025-02-22 12:40:17,258 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5155 +[2025-02-22 12:40:17,307 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7100 +[2025-02-22 12:40:17,418 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.0650 +[2025-02-22 12:40:17,643 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6375 +[2025-02-22 12:40:17,731 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.4915 +[2025-02-22 12:40:17,919 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.1830 +[2025-02-22 12:40:18,014 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6840 +[2025-02-22 12:40:30,226 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:40:30,226 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:40:30,226 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] cabinet : 0.2283 0.4460 0.7056 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] bed : 0.2879 0.5814 0.7486 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] chair : 0.7040 0.8449 0.8979 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] sofa : 0.3365 0.6297 0.7661 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] table : 0.3705 0.5781 0.7288 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] door : 0.2612 0.4921 0.6219 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] window : 0.2178 0.3872 0.5664 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] bookshelf : 0.1991 0.4361 0.6776 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] picture : 0.2922 0.4420 0.5176 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] counter : 0.0508 0.2170 0.5624 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] desk : 0.1209 0.3596 0.7367 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] curtain : 0.2530 0.4477 0.5435 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] refridgerator : 0.2780 0.4117 0.4997 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] shower curtain : 0.3802 0.5617 0.6252 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] toilet : 0.8217 0.9476 0.9815 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] sink : 0.2976 0.5645 0.8280 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] bathtub : 0.5129 0.7290 0.8185 +[2025-02-22 12:40:30,226 INFO evaluator.py line 547 2775932] otherfurniture : 0.3490 0.5267 0.6514 +[2025-02-22 12:40:30,226 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:40:30,226 INFO evaluator.py line 554 2775932] average : 0.3312 0.5335 0.6932 +[2025-02-22 12:40:30,226 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:40:30,227 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:40:30,259 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:40:30,263 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:40:38,724 INFO hook.py line 109 2775932] Train: [48/100][50/800] Data 0.003 (0.003) Batch 0.127 (0.143) Remain 01:41:05 loss: -0.5006 Lr: 3.53862e-03 +[2025-02-22 12:40:45,914 INFO hook.py line 109 2775932] Train: [48/100][100/800] Data 0.002 (0.003) Batch 0.158 (0.144) Remain 01:41:10 loss: -0.6441 Lr: 3.53252e-03 +[2025-02-22 12:40:53,163 INFO hook.py line 109 2775932] Train: [48/100][150/800] Data 0.003 (0.003) Batch 0.116 (0.144) Remain 01:41:24 loss: -0.4005 Lr: 3.52642e-03 +[2025-02-22 12:41:00,236 INFO hook.py line 109 2775932] Train: [48/100][200/800] Data 0.003 (0.003) Batch 0.131 (0.143) Remain 01:40:49 loss: -0.5607 Lr: 3.52031e-03 +[2025-02-22 12:41:07,305 INFO hook.py line 109 2775932] Train: [48/100][250/800] Data 0.003 (0.003) Batch 0.151 (0.143) Remain 01:40:25 loss: -0.5418 Lr: 3.51420e-03 +[2025-02-22 12:41:14,573 INFO hook.py line 109 2775932] Train: [48/100][300/800] Data 0.003 (0.004) Batch 0.144 (0.143) Remain 01:40:35 loss: -0.3836 Lr: 3.50809e-03 +[2025-02-22 12:41:22,087 INFO hook.py line 109 2775932] Train: [48/100][350/800] Data 0.003 (0.004) Batch 0.144 (0.144) Remain 01:41:10 loss: -0.5572 Lr: 3.50198e-03 +[2025-02-22 12:41:29,226 INFO hook.py line 109 2775932] Train: [48/100][400/800] Data 0.003 (0.004) Batch 0.145 (0.144) Remain 01:40:54 loss: -0.4878 Lr: 3.49587e-03 +[2025-02-22 12:41:36,430 INFO hook.py line 109 2775932] Train: [48/100][450/800] Data 0.002 (0.004) Batch 0.175 (0.144) Remain 01:40:47 loss: -0.5821 Lr: 3.48975e-03 +[2025-02-22 12:41:43,607 INFO hook.py line 109 2775932] Train: [48/100][500/800] Data 0.003 (0.004) Batch 0.122 (0.144) Remain 01:40:37 loss: -0.5871 Lr: 3.48364e-03 +[2025-02-22 12:41:50,858 INFO hook.py line 109 2775932] Train: [48/100][550/800] Data 0.003 (0.004) Batch 0.115 (0.144) Remain 01:40:33 loss: -0.4778 Lr: 3.47752e-03 +[2025-02-22 12:41:58,051 INFO hook.py line 109 2775932] Train: [48/100][600/800] Data 0.002 (0.004) Batch 0.162 (0.144) Remain 01:40:25 loss: -0.3860 Lr: 3.47139e-03 +[2025-02-22 12:42:05,557 INFO hook.py line 109 2775932] Train: [48/100][650/800] Data 0.003 (0.004) Batch 0.148 (0.145) Remain 01:40:37 loss: -0.5658 Lr: 3.46527e-03 +[2025-02-22 12:42:12,719 INFO hook.py line 109 2775932] Train: [48/100][700/800] Data 0.003 (0.003) Batch 0.132 (0.145) Remain 01:40:26 loss: -0.3943 Lr: 3.45914e-03 +[2025-02-22 12:42:20,077 INFO hook.py line 109 2775932] Train: [48/100][750/800] Data 0.003 (0.003) Batch 0.146 (0.145) Remain 01:40:26 loss: -0.3899 Lr: 3.45302e-03 +[2025-02-22 12:42:26,774 INFO hook.py line 109 2775932] Train: [48/100][800/800] Data 0.002 (0.003) Batch 0.134 (0.144) Remain 01:39:51 loss: -0.5002 Lr: 3.44689e-03 +[2025-02-22 12:42:26,776 INFO misc.py line 135 2775932] Train result: loss: -0.4531 seg_loss: 0.2283 bias_l1_loss: 0.2484 bias_cosine_loss: -0.9299 +[2025-02-22 12:42:26,776 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:42:33,648 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7687 +[2025-02-22 12:42:34,374 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4748 +[2025-02-22 12:42:34,467 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4190 +[2025-02-22 12:42:34,561 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6105 +[2025-02-22 12:42:34,955 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6210 +[2025-02-22 12:42:35,012 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.2026 +[2025-02-22 12:42:35,310 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5413 +[2025-02-22 12:42:35,342 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5131 +[2025-02-22 12:42:35,474 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1603 +[2025-02-22 12:42:35,532 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0042 +[2025-02-22 12:42:35,785 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0381 +[2025-02-22 12:42:35,927 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.3023 +[2025-02-22 12:42:36,010 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1808 +[2025-02-22 12:42:36,117 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3630 +[2025-02-22 12:42:36,212 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2620 +[2025-02-22 12:42:36,292 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5455 +[2025-02-22 12:42:36,422 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3966 +[2025-02-22 12:42:36,522 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1912 +[2025-02-22 12:42:36,662 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.3447 +[2025-02-22 12:42:36,720 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0240 +[2025-02-22 12:42:36,889 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6201 +[2025-02-22 12:42:37,055 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0803 +[2025-02-22 12:42:37,125 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0939 +[2025-02-22 12:42:37,189 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0331 +[2025-02-22 12:42:37,266 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3232 +[2025-02-22 12:42:37,333 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5536 +[2025-02-22 12:42:37,475 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0837 +[2025-02-22 12:42:37,559 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5351 +[2025-02-22 12:42:37,641 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6145 +[2025-02-22 12:42:37,722 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6204 +[2025-02-22 12:42:38,512 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4756 +[2025-02-22 12:42:38,645 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0221 +[2025-02-22 12:42:38,693 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6317 +[2025-02-22 12:42:38,802 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2905 +[2025-02-22 12:42:38,850 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6335 +[2025-02-22 12:42:38,977 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.3049 +[2025-02-22 12:42:39,050 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5628 +[2025-02-22 12:42:39,191 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6590 +[2025-02-22 12:42:39,405 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0912 +[2025-02-22 12:42:39,615 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8267 +[2025-02-22 12:42:39,791 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3749 +[2025-02-22 12:42:39,849 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1564 +[2025-02-22 12:42:39,896 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6983 +[2025-02-22 12:42:40,168 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6457 +[2025-02-22 12:42:40,233 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5120 +[2025-02-22 12:42:40,280 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5808 +[2025-02-22 12:42:40,391 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2465 +[2025-02-22 12:42:40,512 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3096 +[2025-02-22 12:42:40,625 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1588 +[2025-02-22 12:42:40,715 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0293 +[2025-02-22 12:42:40,790 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.6198 +[2025-02-22 12:42:40,927 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2030 +[2025-02-22 12:42:40,968 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6387 +[2025-02-22 12:42:41,128 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0032 +[2025-02-22 12:42:41,225 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8425 +[2025-02-22 12:42:41,277 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6900 +[2025-02-22 12:42:41,549 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0412 +[2025-02-22 12:42:41,592 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4638 +[2025-02-22 12:42:41,813 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2907 +[2025-02-22 12:42:41,923 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0458 +[2025-02-22 12:42:41,992 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5587 +[2025-02-22 12:42:42,066 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5101 +[2025-02-22 12:42:42,239 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2519 +[2025-02-22 12:42:42,399 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3384 +[2025-02-22 12:42:42,489 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0574 +[2025-02-22 12:42:42,715 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1614 +[2025-02-22 12:42:42,888 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6051 +[2025-02-22 12:42:42,989 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2080 +[2025-02-22 12:42:43,045 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7931 +[2025-02-22 12:42:43,095 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1357 +[2025-02-22 12:42:43,233 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2857 +[2025-02-22 12:42:43,315 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3041 +[2025-02-22 12:42:43,372 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5003 +[2025-02-22 12:42:43,491 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4019 +[2025-02-22 12:42:43,690 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5208 +[2025-02-22 12:42:43,772 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1789 +[2025-02-22 12:42:43,931 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4465 +[2025-02-22 12:42:44,026 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6643 +[2025-02-22 12:42:55,783 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:42:55,783 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:42:55,783 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] cabinet : 0.2666 0.4933 0.7279 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] bed : 0.3351 0.6735 0.8322 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] chair : 0.7059 0.8633 0.9050 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] sofa : 0.3234 0.5628 0.8003 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] table : 0.3886 0.6207 0.7507 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] door : 0.2382 0.4441 0.5768 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] window : 0.1981 0.3831 0.5540 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] bookshelf : 0.1643 0.4559 0.7100 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] picture : 0.3123 0.4900 0.5692 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] counter : 0.0489 0.1934 0.6226 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] desk : 0.0916 0.2650 0.6435 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] curtain : 0.1671 0.3271 0.5677 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] refridgerator : 0.3611 0.4784 0.5945 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] shower curtain : 0.4810 0.6718 0.7042 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] toilet : 0.8123 0.9646 0.9818 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] sink : 0.3354 0.5999 0.8736 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] bathtub : 0.6135 0.7742 0.8710 +[2025-02-22 12:42:55,783 INFO evaluator.py line 547 2775932] otherfurniture : 0.3415 0.4973 0.6382 +[2025-02-22 12:42:55,783 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:42:55,783 INFO evaluator.py line 554 2775932] average : 0.3436 0.5421 0.7180 +[2025-02-22 12:42:55,783 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:42:55,783 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:42:55,815 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:42:55,820 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:43:04,755 INFO hook.py line 109 2775932] Train: [49/100][50/800] Data 0.004 (0.003) Batch 0.130 (0.145) Remain 01:40:12 loss: -0.3195 Lr: 3.44075e-03 +[2025-02-22 12:43:12,011 INFO hook.py line 109 2775932] Train: [49/100][100/800] Data 0.004 (0.003) Batch 0.142 (0.145) Remain 01:40:13 loss: -0.4251 Lr: 3.43462e-03 +[2025-02-22 12:43:19,267 INFO hook.py line 109 2775932] Train: [49/100][150/800] Data 0.003 (0.003) Batch 0.126 (0.145) Remain 01:40:09 loss: -0.4219 Lr: 3.42848e-03 +[2025-02-22 12:43:26,677 INFO hook.py line 109 2775932] Train: [49/100][200/800] Data 0.003 (0.004) Batch 0.131 (0.146) Remain 01:40:36 loss: -0.4892 Lr: 3.42235e-03 +[2025-02-22 12:43:34,164 INFO hook.py line 109 2775932] Train: [49/100][250/800] Data 0.003 (0.004) Batch 0.131 (0.147) Remain 01:41:01 loss: -0.3924 Lr: 3.41621e-03 +[2025-02-22 12:43:41,540 INFO hook.py line 109 2775932] Train: [49/100][300/800] Data 0.004 (0.004) Batch 0.150 (0.147) Remain 01:41:00 loss: -0.4478 Lr: 3.41007e-03 +[2025-02-22 12:43:48,594 INFO hook.py line 109 2775932] Train: [49/100][350/800] Data 0.004 (0.004) Batch 0.128 (0.146) Remain 01:40:19 loss: -0.5284 Lr: 3.40392e-03 +[2025-02-22 12:43:55,706 INFO hook.py line 109 2775932] Train: [49/100][400/800] Data 0.002 (0.004) Batch 0.137 (0.145) Remain 01:39:53 loss: -0.5826 Lr: 3.39778e-03 +[2025-02-22 12:44:02,924 INFO hook.py line 109 2775932] Train: [49/100][450/800] Data 0.002 (0.004) Batch 0.144 (0.145) Remain 01:39:40 loss: -0.6936 Lr: 3.39163e-03 +[2025-02-22 12:44:10,078 INFO hook.py line 109 2775932] Train: [49/100][500/800] Data 0.003 (0.004) Batch 0.161 (0.145) Remain 01:39:24 loss: -0.3324 Lr: 3.38549e-03 +[2025-02-22 12:44:17,465 INFO hook.py line 109 2775932] Train: [49/100][550/800] Data 0.003 (0.004) Batch 0.143 (0.145) Remain 01:39:26 loss: -0.3448 Lr: 3.37934e-03 +[2025-02-22 12:44:25,083 INFO hook.py line 109 2775932] Train: [49/100][600/800] Data 0.003 (0.004) Batch 0.135 (0.146) Remain 01:39:43 loss: -0.3814 Lr: 3.37319e-03 +[2025-02-22 12:44:32,479 INFO hook.py line 109 2775932] Train: [49/100][650/800] Data 0.002 (0.004) Batch 0.166 (0.146) Remain 01:39:42 loss: -0.2489 Lr: 3.36703e-03 +[2025-02-22 12:44:39,512 INFO hook.py line 109 2775932] Train: [49/100][700/800] Data 0.002 (0.004) Batch 0.170 (0.146) Remain 01:39:19 loss: -0.7495 Lr: 3.36088e-03 +[2025-02-22 12:44:46,929 INFO hook.py line 109 2775932] Train: [49/100][750/800] Data 0.003 (0.004) Batch 0.146 (0.146) Remain 01:39:19 loss: -0.4820 Lr: 3.35472e-03 +[2025-02-22 12:44:53,685 INFO hook.py line 109 2775932] Train: [49/100][800/800] Data 0.001 (0.004) Batch 0.112 (0.145) Remain 01:38:44 loss: -0.2619 Lr: 3.34857e-03 +[2025-02-22 12:44:53,685 INFO misc.py line 135 2775932] Train result: loss: -0.4598 seg_loss: 0.2251 bias_l1_loss: 0.2462 bias_cosine_loss: -0.9310 +[2025-02-22 12:44:53,685 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:45:00,725 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7307 +[2025-02-22 12:45:01,067 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3685 +[2025-02-22 12:45:01,555 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4485 +[2025-02-22 12:45:01,621 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5941 +[2025-02-22 12:45:01,692 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6393 +[2025-02-22 12:45:01,751 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9591 +[2025-02-22 12:45:02,014 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4845 +[2025-02-22 12:45:02,046 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4491 +[2025-02-22 12:45:02,213 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2736 +[2025-02-22 12:45:02,282 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1526 +[2025-02-22 12:45:02,538 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0450 +[2025-02-22 12:45:02,636 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2115 +[2025-02-22 12:45:02,711 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4237 +[2025-02-22 12:45:02,836 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.4262 +[2025-02-22 12:45:02,930 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2535 +[2025-02-22 12:45:03,020 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5214 +[2025-02-22 12:45:03,192 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4886 +[2025-02-22 12:45:03,295 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4463 +[2025-02-22 12:45:03,436 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1785 +[2025-02-22 12:45:03,514 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1292 +[2025-02-22 12:45:03,667 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5971 +[2025-02-22 12:45:03,833 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1691 +[2025-02-22 12:45:03,921 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1484 +[2025-02-22 12:45:03,983 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0850 +[2025-02-22 12:45:04,059 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4146 +[2025-02-22 12:45:04,121 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.3736 +[2025-02-22 12:45:04,265 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.8794 +[2025-02-22 12:45:04,492 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7222 +[2025-02-22 12:45:04,561 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5729 +[2025-02-22 12:45:04,637 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.4384 +[2025-02-22 12:45:05,354 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3960 +[2025-02-22 12:45:05,468 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2008 +[2025-02-22 12:45:05,507 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6031 +[2025-02-22 12:45:05,596 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1682 +[2025-02-22 12:45:05,634 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5579 +[2025-02-22 12:45:05,736 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0304 +[2025-02-22 12:45:05,802 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4879 +[2025-02-22 12:45:05,933 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6721 +[2025-02-22 12:45:06,086 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.2505 +[2025-02-22 12:45:06,302 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7602 +[2025-02-22 12:45:06,450 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6002 +[2025-02-22 12:45:06,495 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.0465 +[2025-02-22 12:45:06,532 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7171 +[2025-02-22 12:45:06,761 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6211 +[2025-02-22 12:45:06,799 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5118 +[2025-02-22 12:45:06,834 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4322 +[2025-02-22 12:45:06,922 INFO evaluator.py line 595 2775932] Test: [47/78] Loss -0.1311 +[2025-02-22 12:45:07,048 INFO evaluator.py line 595 2775932] Test: [48/78] Loss 0.0677 +[2025-02-22 12:45:07,144 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2026 +[2025-02-22 12:45:07,220 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1689 +[2025-02-22 12:45:07,290 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.4092 +[2025-02-22 12:45:07,406 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2574 +[2025-02-22 12:45:07,438 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6296 +[2025-02-22 12:45:07,562 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0204 +[2025-02-22 12:45:07,681 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8046 +[2025-02-22 12:45:07,757 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5834 +[2025-02-22 12:45:07,915 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0068 +[2025-02-22 12:45:07,974 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3188 +[2025-02-22 12:45:08,184 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4005 +[2025-02-22 12:45:08,293 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1775 +[2025-02-22 12:45:08,353 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.8926 +[2025-02-22 12:45:08,405 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.0676 +[2025-02-22 12:45:08,538 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0164 +[2025-02-22 12:45:08,635 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7611 +[2025-02-22 12:45:08,693 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3469 +[2025-02-22 12:45:08,808 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.2098 +[2025-02-22 12:45:08,979 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4693 +[2025-02-22 12:45:09,055 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2818 +[2025-02-22 12:45:09,101 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6538 +[2025-02-22 12:45:09,147 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2586 +[2025-02-22 12:45:09,286 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3489 +[2025-02-22 12:45:09,316 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4992 +[2025-02-22 12:45:09,370 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.5063 +[2025-02-22 12:45:09,485 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4085 +[2025-02-22 12:45:09,664 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5769 +[2025-02-22 12:45:09,741 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0787 +[2025-02-22 12:45:09,892 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3435 +[2025-02-22 12:45:09,980 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5649 +[2025-02-22 12:45:21,801 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:45:21,801 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:45:21,801 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] cabinet : 0.2775 0.5043 0.7245 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] bed : 0.3477 0.7111 0.8370 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] chair : 0.7283 0.8833 0.9288 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] sofa : 0.3583 0.6183 0.8267 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] table : 0.4091 0.6551 0.7846 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] door : 0.2356 0.4445 0.5850 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] window : 0.1231 0.2297 0.3953 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] bookshelf : 0.1846 0.4916 0.6690 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] picture : 0.2655 0.3962 0.4635 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] counter : 0.0311 0.1283 0.5362 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] desk : 0.0970 0.2692 0.7289 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] curtain : 0.2360 0.3825 0.5966 +[2025-02-22 12:45:21,801 INFO evaluator.py line 547 2775932] refridgerator : 0.2592 0.3266 0.4621 +[2025-02-22 12:45:21,802 INFO evaluator.py line 547 2775932] shower curtain : 0.4285 0.5782 0.5782 +[2025-02-22 12:45:21,802 INFO evaluator.py line 547 2775932] toilet : 0.8485 0.9988 0.9988 +[2025-02-22 12:45:21,802 INFO evaluator.py line 547 2775932] sink : 0.3456 0.6101 0.8469 +[2025-02-22 12:45:21,802 INFO evaluator.py line 547 2775932] bathtub : 0.6214 0.8027 0.8686 +[2025-02-22 12:45:21,802 INFO evaluator.py line 547 2775932] otherfurniture : 0.3363 0.5199 0.6647 +[2025-02-22 12:45:21,802 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:45:21,802 INFO evaluator.py line 554 2775932] average : 0.3407 0.5306 0.6942 +[2025-02-22 12:45:21,802 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:45:21,802 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:45:21,840 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:45:21,845 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:45:30,928 INFO hook.py line 109 2775932] Train: [50/100][50/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 01:37:27 loss: -0.4719 Lr: 3.34241e-03 +[2025-02-22 12:45:38,281 INFO hook.py line 109 2775932] Train: [50/100][100/800] Data 0.002 (0.005) Batch 0.155 (0.145) Remain 01:38:35 loss: -0.6028 Lr: 3.33625e-03 +[2025-02-22 12:45:46,212 INFO hook.py line 109 2775932] Train: [50/100][150/800] Data 0.004 (0.004) Batch 0.121 (0.150) Remain 01:41:31 loss: -0.5991 Lr: 3.33009e-03 +[2025-02-22 12:45:53,395 INFO hook.py line 109 2775932] Train: [50/100][200/800] Data 0.003 (0.004) Batch 0.154 (0.148) Remain 01:40:20 loss: -0.5177 Lr: 3.32392e-03 +[2025-02-22 12:46:00,290 INFO hook.py line 109 2775932] Train: [50/100][250/800] Data 0.003 (0.004) Batch 0.122 (0.146) Remain 01:38:47 loss: -0.5831 Lr: 3.31776e-03 +[2025-02-22 12:46:07,714 INFO hook.py line 109 2775932] Train: [50/100][300/800] Data 0.003 (0.004) Batch 0.138 (0.147) Remain 01:38:55 loss: -0.5270 Lr: 3.31159e-03 +[2025-02-22 12:46:14,843 INFO hook.py line 109 2775932] Train: [50/100][350/800] Data 0.003 (0.004) Batch 0.170 (0.146) Remain 01:38:25 loss: -0.7000 Lr: 3.30543e-03 +[2025-02-22 12:46:21,837 INFO hook.py line 109 2775932] Train: [50/100][400/800] Data 0.003 (0.004) Batch 0.150 (0.145) Remain 01:37:46 loss: -0.3354 Lr: 3.29926e-03 +[2025-02-22 12:46:28,954 INFO hook.py line 109 2775932] Train: [50/100][450/800] Data 0.003 (0.003) Batch 0.127 (0.145) Remain 01:37:26 loss: -0.5962 Lr: 3.29309e-03 +[2025-02-22 12:46:36,074 INFO hook.py line 109 2775932] Train: [50/100][500/800] Data 0.002 (0.003) Batch 0.131 (0.145) Remain 01:37:09 loss: 0.6983 Lr: 3.28692e-03 +[2025-02-22 12:46:43,124 INFO hook.py line 109 2775932] Train: [50/100][550/800] Data 0.002 (0.003) Batch 0.130 (0.144) Remain 01:36:48 loss: -0.6408 Lr: 3.28074e-03 +[2025-02-22 12:46:50,274 INFO hook.py line 109 2775932] Train: [50/100][600/800] Data 0.002 (0.003) Batch 0.175 (0.144) Remain 01:36:36 loss: -0.5757 Lr: 3.27457e-03 +[2025-02-22 12:46:57,700 INFO hook.py line 109 2775932] Train: [50/100][650/800] Data 0.002 (0.003) Batch 0.136 (0.145) Remain 01:36:43 loss: -0.5992 Lr: 3.26852e-03 +[2025-02-22 12:47:05,071 INFO hook.py line 109 2775932] Train: [50/100][700/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 01:36:44 loss: -0.1035 Lr: 3.26234e-03 +[2025-02-22 12:47:12,291 INFO hook.py line 109 2775932] Train: [50/100][750/800] Data 0.003 (0.004) Batch 0.150 (0.145) Remain 01:36:35 loss: -0.4067 Lr: 3.25617e-03 +[2025-02-22 12:47:19,245 INFO hook.py line 109 2775932] Train: [50/100][800/800] Data 0.002 (0.004) Batch 0.105 (0.144) Remain 01:36:14 loss: -0.5471 Lr: 3.24999e-03 +[2025-02-22 12:47:19,246 INFO misc.py line 135 2775932] Train result: loss: -0.4799 seg_loss: 0.2122 bias_l1_loss: 0.2420 bias_cosine_loss: -0.9340 +[2025-02-22 12:47:19,247 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:47:26,332 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7290 +[2025-02-22 12:47:26,944 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3383 +[2025-02-22 12:47:27,235 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4508 +[2025-02-22 12:47:27,328 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5417 +[2025-02-22 12:47:27,400 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5787 +[2025-02-22 12:47:27,455 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8178 +[2025-02-22 12:47:27,726 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4155 +[2025-02-22 12:47:27,776 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5294 +[2025-02-22 12:47:27,911 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3850 +[2025-02-22 12:47:27,979 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0932 +[2025-02-22 12:47:28,239 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0078 +[2025-02-22 12:47:28,353 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1174 +[2025-02-22 12:47:28,428 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0690 +[2025-02-22 12:47:28,536 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9283 +[2025-02-22 12:47:28,616 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2051 +[2025-02-22 12:47:28,693 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.3757 +[2025-02-22 12:47:28,834 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5492 +[2025-02-22 12:47:28,951 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.5144 +[2025-02-22 12:47:29,134 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1963 +[2025-02-22 12:47:29,211 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2246 +[2025-02-22 12:47:29,389 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5361 +[2025-02-22 12:47:29,600 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1516 +[2025-02-22 12:47:29,687 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0510 +[2025-02-22 12:47:29,756 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1059 +[2025-02-22 12:47:29,833 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0733 +[2025-02-22 12:47:29,894 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4827 +[2025-02-22 12:47:30,050 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3289 +[2025-02-22 12:47:30,144 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6239 +[2025-02-22 12:47:30,224 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5841 +[2025-02-22 12:47:30,332 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5416 +[2025-02-22 12:47:31,030 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3890 +[2025-02-22 12:47:31,153 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4368 +[2025-02-22 12:47:31,191 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7026 +[2025-02-22 12:47:31,284 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3875 +[2025-02-22 12:47:31,325 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6270 +[2025-02-22 12:47:31,438 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.4013 +[2025-02-22 12:47:31,495 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5487 +[2025-02-22 12:47:31,637 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6251 +[2025-02-22 12:47:31,824 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1611 +[2025-02-22 12:47:32,033 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8233 +[2025-02-22 12:47:32,201 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3712 +[2025-02-22 12:47:32,275 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1012 +[2025-02-22 12:47:32,322 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7115 +[2025-02-22 12:47:32,598 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6041 +[2025-02-22 12:47:32,656 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4742 +[2025-02-22 12:47:32,698 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.2958 +[2025-02-22 12:47:32,794 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5951 +[2025-02-22 12:47:32,924 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3657 +[2025-02-22 12:47:33,043 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1523 +[2025-02-22 12:47:33,142 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1069 +[2025-02-22 12:47:33,219 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1543 +[2025-02-22 12:47:33,352 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1769 +[2025-02-22 12:47:33,394 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6973 +[2025-02-22 12:47:33,541 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.4152 +[2025-02-22 12:47:33,639 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7775 +[2025-02-22 12:47:33,689 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7818 +[2025-02-22 12:47:33,824 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.1140 +[2025-02-22 12:47:33,874 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3562 +[2025-02-22 12:47:34,109 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3544 +[2025-02-22 12:47:34,211 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2371 +[2025-02-22 12:47:34,286 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7407 +[2025-02-22 12:47:34,345 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4179 +[2025-02-22 12:47:34,508 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1187 +[2025-02-22 12:47:34,619 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3351 +[2025-02-22 12:47:34,714 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3454 +[2025-02-22 12:47:34,851 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.1453 +[2025-02-22 12:47:35,035 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.2401 +[2025-02-22 12:47:35,137 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1471 +[2025-02-22 12:47:35,204 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7148 +[2025-02-22 12:47:35,281 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0375 +[2025-02-22 12:47:35,428 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1359 +[2025-02-22 12:47:35,472 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6203 +[2025-02-22 12:47:35,534 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6895 +[2025-02-22 12:47:35,642 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6904 +[2025-02-22 12:47:35,864 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6688 +[2025-02-22 12:47:35,958 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2745 +[2025-02-22 12:47:36,120 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4713 +[2025-02-22 12:47:36,246 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.7025 +[2025-02-22 12:47:49,422 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:47:49,423 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:47:49,423 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] cabinet : 0.2327 0.4743 0.7089 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] bed : 0.3560 0.7234 0.8365 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] chair : 0.7306 0.8838 0.9307 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] sofa : 0.4585 0.7735 0.8586 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] table : 0.4020 0.6402 0.7926 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] door : 0.2123 0.4116 0.5485 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] window : 0.1972 0.3538 0.5534 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] bookshelf : 0.1931 0.4779 0.6806 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] picture : 0.3016 0.4595 0.5271 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] counter : 0.0106 0.0483 0.2840 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] desk : 0.0774 0.2727 0.6684 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] curtain : 0.1898 0.3409 0.4455 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] refridgerator : 0.3340 0.4630 0.5658 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] shower curtain : 0.4343 0.6073 0.7355 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] toilet : 0.8376 1.0000 1.0000 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] sink : 0.2929 0.5433 0.7469 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] bathtub : 0.5748 0.7137 0.8515 +[2025-02-22 12:47:49,423 INFO evaluator.py line 547 2775932] otherfurniture : 0.3635 0.5418 0.6832 +[2025-02-22 12:47:49,423 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:47:49,423 INFO evaluator.py line 554 2775932] average : 0.3444 0.5405 0.6899 +[2025-02-22 12:47:49,423 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:47:49,423 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:47:49,462 INFO misc.py line 164 2775932] Currently Best AP50: 0.5595 +[2025-02-22 12:47:49,467 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:47:58,012 INFO hook.py line 109 2775932] Train: [51/100][50/800] Data 0.003 (0.003) Batch 0.138 (0.145) Remain 01:36:13 loss: -0.3474 Lr: 3.24381e-03 +[2025-02-22 12:48:05,161 INFO hook.py line 109 2775932] Train: [51/100][100/800] Data 0.003 (0.003) Batch 0.161 (0.144) Remain 01:35:34 loss: -0.3400 Lr: 3.23763e-03 +[2025-02-22 12:48:12,155 INFO hook.py line 109 2775932] Train: [51/100][150/800] Data 0.002 (0.003) Batch 0.138 (0.142) Remain 01:34:35 loss: -0.3615 Lr: 3.23145e-03 +[2025-02-22 12:48:19,280 INFO hook.py line 109 2775932] Train: [51/100][200/800] Data 0.003 (0.003) Batch 0.129 (0.142) Remain 01:34:28 loss: -0.5725 Lr: 3.22527e-03 +[2025-02-22 12:48:26,445 INFO hook.py line 109 2775932] Train: [51/100][250/800] Data 0.004 (0.003) Batch 0.148 (0.143) Remain 01:34:28 loss: -0.6238 Lr: 3.21909e-03 +[2025-02-22 12:48:33,643 INFO hook.py line 109 2775932] Train: [51/100][300/800] Data 0.002 (0.003) Batch 0.140 (0.143) Remain 01:34:30 loss: -0.5315 Lr: 3.21290e-03 +[2025-02-22 12:48:40,827 INFO hook.py line 109 2775932] Train: [51/100][350/800] Data 0.003 (0.003) Batch 0.138 (0.143) Remain 01:34:28 loss: -0.4969 Lr: 3.20672e-03 +[2025-02-22 12:48:47,979 INFO hook.py line 109 2775932] Train: [51/100][400/800] Data 0.003 (0.003) Batch 0.141 (0.143) Remain 01:34:21 loss: -0.3047 Lr: 3.20053e-03 +[2025-02-22 12:48:55,192 INFO hook.py line 109 2775932] Train: [51/100][450/800] Data 0.002 (0.003) Batch 0.135 (0.143) Remain 01:34:20 loss: -0.6025 Lr: 3.19435e-03 +[2025-02-22 12:49:02,299 INFO hook.py line 109 2775932] Train: [51/100][500/800] Data 0.003 (0.003) Batch 0.182 (0.143) Remain 01:34:09 loss: -0.2973 Lr: 3.18816e-03 +[2025-02-22 12:49:09,450 INFO hook.py line 109 2775932] Train: [51/100][550/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 01:34:01 loss: -0.6052 Lr: 3.18197e-03 +[2025-02-22 12:49:16,567 INFO hook.py line 109 2775932] Train: [51/100][600/800] Data 0.003 (0.003) Batch 0.145 (0.143) Remain 01:33:52 loss: -0.6179 Lr: 3.17578e-03 +[2025-02-22 12:49:24,029 INFO hook.py line 109 2775932] Train: [51/100][650/800] Data 0.003 (0.003) Batch 0.157 (0.143) Remain 01:34:04 loss: -0.6454 Lr: 3.16959e-03 +[2025-02-22 12:49:31,060 INFO hook.py line 109 2775932] Train: [51/100][700/800] Data 0.003 (0.003) Batch 0.157 (0.143) Remain 01:33:49 loss: -0.5546 Lr: 3.16340e-03 +[2025-02-22 12:49:38,307 INFO hook.py line 109 2775932] Train: [51/100][750/800] Data 0.002 (0.003) Batch 0.135 (0.143) Remain 01:33:46 loss: -0.6531 Lr: 3.15721e-03 +[2025-02-22 12:49:45,329 INFO hook.py line 109 2775932] Train: [51/100][800/800] Data 0.002 (0.003) Batch 0.239 (0.143) Remain 01:33:32 loss: -0.2856 Lr: 3.15102e-03 +[2025-02-22 12:49:45,330 INFO misc.py line 135 2775932] Train result: loss: -0.4725 seg_loss: 0.2209 bias_l1_loss: 0.2399 bias_cosine_loss: -0.9333 +[2025-02-22 12:49:45,330 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:49:52,710 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7594 +[2025-02-22 12:49:52,929 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5251 +[2025-02-22 12:49:53,009 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5200 +[2025-02-22 12:49:53,082 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6251 +[2025-02-22 12:49:53,150 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6600 +[2025-02-22 12:49:53,616 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.6685 +[2025-02-22 12:49:53,881 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5798 +[2025-02-22 12:49:53,914 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5404 +[2025-02-22 12:49:54,044 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0144 +[2025-02-22 12:49:54,100 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1246 +[2025-02-22 12:49:54,366 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0292 +[2025-02-22 12:49:54,470 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0145 +[2025-02-22 12:49:54,555 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.4587 +[2025-02-22 12:49:54,656 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.6491 +[2025-02-22 12:49:54,734 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1296 +[2025-02-22 12:49:54,799 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5530 +[2025-02-22 12:49:54,954 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4926 +[2025-02-22 12:49:55,051 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1526 +[2025-02-22 12:49:55,203 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0535 +[2025-02-22 12:49:55,266 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0594 +[2025-02-22 12:49:55,421 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6193 +[2025-02-22 12:49:55,584 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0335 +[2025-02-22 12:49:55,655 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2960 +[2025-02-22 12:49:55,710 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2584 +[2025-02-22 12:49:55,773 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4663 +[2025-02-22 12:49:55,835 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5499 +[2025-02-22 12:49:55,994 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3806 +[2025-02-22 12:49:56,114 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 1.0515 +[2025-02-22 12:49:56,219 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6654 +[2025-02-22 12:49:56,317 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6186 +[2025-02-22 12:49:57,112 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5299 +[2025-02-22 12:49:57,247 INFO evaluator.py line 595 2775932] Test: [32/78] Loss -0.1031 +[2025-02-22 12:49:57,291 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7163 +[2025-02-22 12:49:57,391 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.1011 +[2025-02-22 12:49:57,431 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.7020 +[2025-02-22 12:49:57,545 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1105 +[2025-02-22 12:49:57,610 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6309 +[2025-02-22 12:49:57,747 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5565 +[2025-02-22 12:49:57,932 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.1277 +[2025-02-22 12:49:58,165 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6300 +[2025-02-22 12:49:58,331 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4207 +[2025-02-22 12:49:58,397 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3665 +[2025-02-22 12:49:58,444 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.6956 +[2025-02-22 12:49:58,724 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5113 +[2025-02-22 12:49:58,769 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6188 +[2025-02-22 12:49:58,821 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5945 +[2025-02-22 12:49:58,927 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7326 +[2025-02-22 12:49:59,047 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2659 +[2025-02-22 12:49:59,151 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2550 +[2025-02-22 12:49:59,252 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1948 +[2025-02-22 12:49:59,339 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0082 +[2025-02-22 12:49:59,475 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2759 +[2025-02-22 12:49:59,516 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6868 +[2025-02-22 12:49:59,634 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3364 +[2025-02-22 12:49:59,729 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7675 +[2025-02-22 12:49:59,778 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7498 +[2025-02-22 12:49:59,906 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2810 +[2025-02-22 12:49:59,952 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4351 +[2025-02-22 12:50:00,195 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3146 +[2025-02-22 12:50:00,290 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0735 +[2025-02-22 12:50:00,361 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7053 +[2025-02-22 12:50:00,417 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6635 +[2025-02-22 12:50:00,564 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1838 +[2025-02-22 12:50:00,673 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4802 +[2025-02-22 12:50:00,751 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3162 +[2025-02-22 12:50:00,887 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3445 +[2025-02-22 12:50:01,052 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6313 +[2025-02-22 12:50:01,153 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0236 +[2025-02-22 12:50:01,221 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7612 +[2025-02-22 12:50:01,271 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1180 +[2025-02-22 12:50:01,435 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2062 +[2025-02-22 12:50:01,472 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4740 +[2025-02-22 12:50:01,524 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7099 +[2025-02-22 12:50:01,623 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2552 +[2025-02-22 12:50:01,835 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3688 +[2025-02-22 12:50:01,919 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2179 +[2025-02-22 12:50:02,093 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4823 +[2025-02-22 12:50:02,179 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4290 +[2025-02-22 12:50:12,840 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:50:12,840 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:50:12,840 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] cabinet : 0.2294 0.4556 0.6676 +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] bed : 0.3244 0.7034 0.8472 +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] chair : 0.7216 0.8781 0.9273 +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] sofa : 0.4084 0.7123 0.8354 +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] table : 0.3817 0.6062 0.7369 +[2025-02-22 12:50:12,840 INFO evaluator.py line 547 2775932] door : 0.2468 0.4695 0.6127 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] window : 0.2109 0.3876 0.5885 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] bookshelf : 0.2207 0.5027 0.6979 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] picture : 0.2461 0.3767 0.4547 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] counter : 0.0409 0.1457 0.5666 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] desk : 0.0685 0.2709 0.7691 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] curtain : 0.2304 0.4028 0.5456 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] refridgerator : 0.3514 0.5325 0.5741 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] shower curtain : 0.5059 0.6987 0.7603 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] toilet : 0.8735 0.9825 0.9986 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] sink : 0.3144 0.6445 0.9002 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] bathtub : 0.6615 0.8065 0.8710 +[2025-02-22 12:50:12,841 INFO evaluator.py line 547 2775932] otherfurniture : 0.3196 0.5007 0.6383 +[2025-02-22 12:50:12,841 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:50:12,841 INFO evaluator.py line 554 2775932] average : 0.3531 0.5598 0.7218 +[2025-02-22 12:50:12,841 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:50:12,841 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:50:12,879 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5598 +[2025-02-22 12:50:12,884 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 12:50:12,884 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:50:22,116 INFO hook.py line 109 2775932] Train: [52/100][50/800] Data 0.003 (0.004) Batch 0.146 (0.146) Remain 01:35:32 loss: -0.5953 Lr: 3.14483e-03 +[2025-02-22 12:50:29,401 INFO hook.py line 109 2775932] Train: [52/100][100/800] Data 0.003 (0.004) Batch 0.128 (0.146) Remain 01:35:10 loss: -0.5572 Lr: 3.13863e-03 +[2025-02-22 12:50:36,841 INFO hook.py line 109 2775932] Train: [52/100][150/800] Data 0.003 (0.005) Batch 0.128 (0.147) Remain 01:35:39 loss: -0.2242 Lr: 3.13244e-03 +[2025-02-22 12:50:44,122 INFO hook.py line 109 2775932] Train: [52/100][200/800] Data 0.003 (0.004) Batch 0.124 (0.147) Remain 01:35:19 loss: -0.6084 Lr: 3.12624e-03 +[2025-02-22 12:50:51,076 INFO hook.py line 109 2775932] Train: [52/100][250/800] Data 0.004 (0.004) Batch 0.140 (0.145) Remain 01:34:11 loss: -0.3339 Lr: 3.12005e-03 +[2025-02-22 12:50:58,473 INFO hook.py line 109 2775932] Train: [52/100][300/800] Data 0.003 (0.004) Batch 0.152 (0.146) Remain 01:34:23 loss: -0.5427 Lr: 3.11385e-03 +[2025-02-22 12:51:05,569 INFO hook.py line 109 2775932] Train: [52/100][350/800] Data 0.003 (0.004) Batch 0.138 (0.145) Remain 01:33:55 loss: -0.4130 Lr: 3.10766e-03 +[2025-02-22 12:51:12,892 INFO hook.py line 109 2775932] Train: [52/100][400/800] Data 0.002 (0.004) Batch 0.130 (0.145) Remain 01:33:55 loss: -0.3705 Lr: 3.10146e-03 +[2025-02-22 12:51:20,169 INFO hook.py line 109 2775932] Train: [52/100][450/800] Data 0.003 (0.004) Batch 0.131 (0.145) Remain 01:33:49 loss: -0.5215 Lr: 3.09527e-03 +[2025-02-22 12:51:27,250 INFO hook.py line 109 2775932] Train: [52/100][500/800] Data 0.002 (0.004) Batch 0.132 (0.145) Remain 01:33:27 loss: -0.4461 Lr: 3.08907e-03 +[2025-02-22 12:51:34,372 INFO hook.py line 109 2775932] Train: [52/100][550/800] Data 0.003 (0.004) Batch 0.163 (0.145) Remain 01:33:11 loss: -0.4470 Lr: 3.08287e-03 +[2025-02-22 12:51:41,527 INFO hook.py line 109 2775932] Train: [52/100][600/800] Data 0.002 (0.004) Batch 0.165 (0.145) Remain 01:32:59 loss: -0.5320 Lr: 3.07667e-03 +[2025-02-22 12:51:48,701 INFO hook.py line 109 2775932] Train: [52/100][650/800] Data 0.004 (0.004) Batch 0.126 (0.144) Remain 01:32:48 loss: -0.5880 Lr: 3.07048e-03 +[2025-02-22 12:51:55,979 INFO hook.py line 109 2775932] Train: [52/100][700/800] Data 0.003 (0.004) Batch 0.146 (0.145) Remain 01:32:44 loss: -0.5817 Lr: 3.06428e-03 +[2025-02-22 12:52:03,205 INFO hook.py line 109 2775932] Train: [52/100][750/800] Data 0.003 (0.004) Batch 0.164 (0.145) Remain 01:32:37 loss: -0.1519 Lr: 3.05808e-03 +[2025-02-22 12:52:10,004 INFO hook.py line 109 2775932] Train: [52/100][800/800] Data 0.003 (0.004) Batch 0.128 (0.144) Remain 01:32:09 loss: -0.5279 Lr: 3.05188e-03 +[2025-02-22 12:52:10,004 INFO misc.py line 135 2775932] Train result: loss: -0.4846 seg_loss: 0.2127 bias_l1_loss: 0.2371 bias_cosine_loss: -0.9344 +[2025-02-22 12:52:10,005 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:52:17,184 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7433 +[2025-02-22 12:52:17,488 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3618 +[2025-02-22 12:52:17,998 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5245 +[2025-02-22 12:52:18,083 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5124 +[2025-02-22 12:52:18,145 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7004 +[2025-02-22 12:52:18,218 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7979 +[2025-02-22 12:52:18,520 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4080 +[2025-02-22 12:52:18,554 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5013 +[2025-02-22 12:52:18,700 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2930 +[2025-02-22 12:52:18,761 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0705 +[2025-02-22 12:52:19,050 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0093 +[2025-02-22 12:52:19,158 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1837 +[2025-02-22 12:52:19,245 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.6207 +[2025-02-22 12:52:19,356 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2702 +[2025-02-22 12:52:19,446 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2514 +[2025-02-22 12:52:19,529 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6360 +[2025-02-22 12:52:19,684 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5540 +[2025-02-22 12:52:19,794 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3817 +[2025-02-22 12:52:19,958 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1631 +[2025-02-22 12:52:20,021 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2769 +[2025-02-22 12:52:20,185 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5495 +[2025-02-22 12:52:20,363 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.0447 +[2025-02-22 12:52:20,462 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0049 +[2025-02-22 12:52:20,532 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1316 +[2025-02-22 12:52:20,600 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4910 +[2025-02-22 12:52:20,661 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5631 +[2025-02-22 12:52:20,808 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2197 +[2025-02-22 12:52:20,920 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.8517 +[2025-02-22 12:52:21,005 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.4433 +[2025-02-22 12:52:21,078 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6336 +[2025-02-22 12:52:21,983 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4909 +[2025-02-22 12:52:22,134 INFO evaluator.py line 595 2775932] Test: [32/78] Loss -0.0404 +[2025-02-22 12:52:22,182 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7273 +[2025-02-22 12:52:22,285 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3675 +[2025-02-22 12:52:22,330 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.7255 +[2025-02-22 12:52:22,462 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0324 +[2025-02-22 12:52:22,539 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5676 +[2025-02-22 12:52:22,694 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7147 +[2025-02-22 12:52:22,883 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4607 +[2025-02-22 12:52:23,156 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6125 +[2025-02-22 12:52:23,355 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5084 +[2025-02-22 12:52:23,406 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1117 +[2025-02-22 12:52:23,452 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7034 +[2025-02-22 12:52:23,738 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6406 +[2025-02-22 12:52:23,784 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3604 +[2025-02-22 12:52:23,831 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4347 +[2025-02-22 12:52:23,957 INFO evaluator.py line 595 2775932] Test: [47/78] Loss -0.0707 +[2025-02-22 12:52:24,114 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1889 +[2025-02-22 12:52:24,237 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0422 +[2025-02-22 12:52:24,339 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1230 +[2025-02-22 12:52:24,419 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2119 +[2025-02-22 12:52:24,565 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3931 +[2025-02-22 12:52:24,604 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7756 +[2025-02-22 12:52:24,730 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9313 +[2025-02-22 12:52:24,857 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8152 +[2025-02-22 12:52:24,923 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7774 +[2025-02-22 12:52:25,058 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2233 +[2025-02-22 12:52:25,106 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4337 +[2025-02-22 12:52:25,350 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2807 +[2025-02-22 12:52:25,461 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2342 +[2025-02-22 12:52:25,550 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.1999 +[2025-02-22 12:52:25,609 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6366 +[2025-02-22 12:52:25,773 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2523 +[2025-02-22 12:52:25,889 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7129 +[2025-02-22 12:52:25,967 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0207 +[2025-02-22 12:52:26,097 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0000 +[2025-02-22 12:52:26,292 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6916 +[2025-02-22 12:52:26,388 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1578 +[2025-02-22 12:52:26,446 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7655 +[2025-02-22 12:52:26,499 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1439 +[2025-02-22 12:52:26,654 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1935 +[2025-02-22 12:52:26,692 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6329 +[2025-02-22 12:52:26,757 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7507 +[2025-02-22 12:52:26,868 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.0882 +[2025-02-22 12:52:27,087 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5851 +[2025-02-22 12:52:27,171 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0612 +[2025-02-22 12:52:27,372 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3013 +[2025-02-22 12:52:27,467 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6988 +[2025-02-22 12:52:39,736 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:52:39,737 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:52:39,737 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] cabinet : 0.2474 0.4820 0.6926 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] bed : 0.3531 0.7113 0.8091 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] chair : 0.7093 0.8818 0.9294 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] sofa : 0.3215 0.6100 0.8105 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] table : 0.4094 0.6501 0.7846 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] door : 0.2387 0.4608 0.6068 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] window : 0.1937 0.3347 0.4978 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] bookshelf : 0.1835 0.4289 0.6715 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] picture : 0.1955 0.2796 0.3372 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] counter : 0.0264 0.1171 0.4619 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] desk : 0.0743 0.2518 0.6505 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] curtain : 0.2977 0.4794 0.6620 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] refridgerator : 0.2952 0.3953 0.5062 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] shower curtain : 0.4355 0.6863 0.8353 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] toilet : 0.8665 0.9994 0.9994 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] sink : 0.3009 0.5615 0.7916 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] bathtub : 0.5845 0.7204 0.8507 +[2025-02-22 12:52:39,737 INFO evaluator.py line 547 2775932] otherfurniture : 0.3666 0.5554 0.6621 +[2025-02-22 12:52:39,737 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:52:39,737 INFO evaluator.py line 554 2775932] average : 0.3389 0.5337 0.6977 +[2025-02-22 12:52:39,737 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:52:39,737 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:52:39,774 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 12:52:39,774 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:52:49,165 INFO hook.py line 109 2775932] Train: [53/100][50/800] Data 0.003 (0.016) Batch 0.153 (0.160) Remain 01:41:57 loss: -0.5643 Lr: 3.04568e-03 +[2025-02-22 12:52:56,512 INFO hook.py line 109 2775932] Train: [53/100][100/800] Data 0.003 (0.009) Batch 0.175 (0.153) Remain 01:37:41 loss: -0.5507 Lr: 3.03948e-03 +[2025-02-22 12:53:03,703 INFO hook.py line 109 2775932] Train: [53/100][150/800] Data 0.002 (0.007) Batch 0.163 (0.150) Remain 01:35:33 loss: -0.5100 Lr: 3.03328e-03 +[2025-02-22 12:53:10,870 INFO hook.py line 109 2775932] Train: [53/100][200/800] Data 0.002 (0.006) Batch 0.160 (0.148) Remain 01:34:22 loss: -0.6495 Lr: 3.02708e-03 +[2025-02-22 12:53:17,896 INFO hook.py line 109 2775932] Train: [53/100][250/800] Data 0.003 (0.005) Batch 0.141 (0.147) Remain 01:33:15 loss: -0.5691 Lr: 3.02088e-03 +[2025-02-22 12:53:25,192 INFO hook.py line 109 2775932] Train: [53/100][300/800] Data 0.003 (0.005) Batch 0.139 (0.147) Remain 01:33:03 loss: -0.4617 Lr: 3.01468e-03 +[2025-02-22 12:53:32,674 INFO hook.py line 109 2775932] Train: [53/100][350/800] Data 0.002 (0.005) Batch 0.137 (0.147) Remain 01:33:13 loss: -0.4176 Lr: 3.00848e-03 +[2025-02-22 12:53:39,861 INFO hook.py line 109 2775932] Train: [53/100][400/800] Data 0.002 (0.005) Batch 0.157 (0.147) Remain 01:32:50 loss: -0.5499 Lr: 3.00228e-03 +[2025-02-22 12:53:47,052 INFO hook.py line 109 2775932] Train: [53/100][450/800] Data 0.003 (0.005) Batch 0.132 (0.146) Remain 01:32:30 loss: -0.3353 Lr: 2.99608e-03 +[2025-02-22 12:53:54,099 INFO hook.py line 109 2775932] Train: [53/100][500/800] Data 0.002 (0.005) Batch 0.122 (0.146) Remain 01:32:03 loss: -0.4626 Lr: 2.98988e-03 +[2025-02-22 12:54:01,378 INFO hook.py line 109 2775932] Train: [53/100][550/800] Data 0.002 (0.005) Batch 0.130 (0.146) Remain 01:31:55 loss: -0.2494 Lr: 2.98368e-03 +[2025-02-22 12:54:08,611 INFO hook.py line 109 2775932] Train: [53/100][600/800] Data 0.003 (0.004) Batch 0.132 (0.146) Remain 01:31:44 loss: -0.4402 Lr: 2.97748e-03 +[2025-02-22 12:54:15,922 INFO hook.py line 109 2775932] Train: [53/100][650/800] Data 0.003 (0.004) Batch 0.137 (0.146) Remain 01:31:39 loss: -0.6260 Lr: 2.97128e-03 +[2025-02-22 12:54:23,125 INFO hook.py line 109 2775932] Train: [53/100][700/800] Data 0.002 (0.004) Batch 0.132 (0.146) Remain 01:31:27 loss: -0.6047 Lr: 2.96509e-03 +[2025-02-22 12:54:30,301 INFO hook.py line 109 2775932] Train: [53/100][750/800] Data 0.003 (0.004) Batch 0.154 (0.145) Remain 01:31:15 loss: -0.4791 Lr: 2.95889e-03 +[2025-02-22 12:54:37,179 INFO hook.py line 109 2775932] Train: [53/100][800/800] Data 0.002 (0.004) Batch 0.120 (0.145) Remain 01:30:49 loss: -0.4896 Lr: 2.95269e-03 +[2025-02-22 12:54:37,180 INFO misc.py line 135 2775932] Train result: loss: -0.4926 seg_loss: 0.2061 bias_l1_loss: 0.2367 bias_cosine_loss: -0.9354 +[2025-02-22 12:54:37,181 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:54:44,322 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7529 +[2025-02-22 12:54:44,824 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.1349 +[2025-02-22 12:54:44,911 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5207 +[2025-02-22 12:54:44,991 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4254 +[2025-02-22 12:54:45,051 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6102 +[2025-02-22 12:54:45,137 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8148 +[2025-02-22 12:54:45,395 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4661 +[2025-02-22 12:54:45,439 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6216 +[2025-02-22 12:54:45,623 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3259 +[2025-02-22 12:54:45,681 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0340 +[2025-02-22 12:54:45,963 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2123 +[2025-02-22 12:54:46,072 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1604 +[2025-02-22 12:54:46,156 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0577 +[2025-02-22 12:54:46,240 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1083 +[2025-02-22 12:54:46,321 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.1044 +[2025-02-22 12:54:46,412 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6093 +[2025-02-22 12:54:46,577 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5246 +[2025-02-22 12:54:46,683 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3758 +[2025-02-22 12:54:46,826 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2722 +[2025-02-22 12:54:46,891 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0673 +[2025-02-22 12:54:47,053 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6537 +[2025-02-22 12:54:47,257 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4422 +[2025-02-22 12:54:47,345 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1728 +[2025-02-22 12:54:47,412 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1835 +[2025-02-22 12:54:47,476 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3548 +[2025-02-22 12:54:47,536 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5446 +[2025-02-22 12:54:47,677 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.1443 +[2025-02-22 12:54:47,776 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7477 +[2025-02-22 12:54:47,852 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6917 +[2025-02-22 12:54:47,920 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6960 +[2025-02-22 12:54:48,607 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4182 +[2025-02-22 12:54:48,723 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0393 +[2025-02-22 12:54:48,757 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6224 +[2025-02-22 12:54:48,856 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2986 +[2025-02-22 12:54:48,905 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5519 +[2025-02-22 12:54:49,030 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.2322 +[2025-02-22 12:54:49,108 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6957 +[2025-02-22 12:54:49,242 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6941 +[2025-02-22 12:54:49,431 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1033 +[2025-02-22 12:54:49,622 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0610 +[2025-02-22 12:54:49,791 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5582 +[2025-02-22 12:54:49,842 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2730 +[2025-02-22 12:54:49,904 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7292 +[2025-02-22 12:54:50,219 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6392 +[2025-02-22 12:54:50,258 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3333 +[2025-02-22 12:54:50,304 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5005 +[2025-02-22 12:54:50,384 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0990 +[2025-02-22 12:54:50,500 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2059 +[2025-02-22 12:54:50,604 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1067 +[2025-02-22 12:54:50,697 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1348 +[2025-02-22 12:54:50,787 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2000 +[2025-02-22 12:54:50,925 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3290 +[2025-02-22 12:54:50,968 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5439 +[2025-02-22 12:54:51,101 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3201 +[2025-02-22 12:54:51,193 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8426 +[2025-02-22 12:54:51,241 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7098 +[2025-02-22 12:54:51,373 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1639 +[2025-02-22 12:54:51,421 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4619 +[2025-02-22 12:54:51,649 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2825 +[2025-02-22 12:54:51,761 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1308 +[2025-02-22 12:54:51,832 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.7056 +[2025-02-22 12:54:51,887 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4026 +[2025-02-22 12:54:52,025 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1667 +[2025-02-22 12:54:52,126 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4037 +[2025-02-22 12:54:52,193 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.3042 +[2025-02-22 12:54:52,350 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2670 +[2025-02-22 12:54:52,521 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6437 +[2025-02-22 12:54:52,610 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1774 +[2025-02-22 12:54:52,669 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8157 +[2025-02-22 12:54:52,719 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2523 +[2025-02-22 12:54:52,864 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1338 +[2025-02-22 12:54:52,898 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6494 +[2025-02-22 12:54:52,952 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7940 +[2025-02-22 12:54:53,060 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2847 +[2025-02-22 12:54:53,268 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6560 +[2025-02-22 12:54:53,347 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1575 +[2025-02-22 12:54:53,534 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3733 +[2025-02-22 12:54:53,630 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6125 +[2025-02-22 12:55:04,391 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:55:04,391 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:55:04,391 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] cabinet : 0.2366 0.4707 0.6600 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] bed : 0.3435 0.6821 0.8371 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] chair : 0.7359 0.9023 0.9429 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] sofa : 0.3460 0.6020 0.8326 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] table : 0.4298 0.6648 0.7928 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] door : 0.2387 0.4479 0.5529 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] window : 0.1699 0.2886 0.4261 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] bookshelf : 0.2430 0.5620 0.7584 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] picture : 0.3065 0.4530 0.5339 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] counter : 0.0318 0.1089 0.5869 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] desk : 0.0989 0.3543 0.7898 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] curtain : 0.2356 0.3856 0.5715 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] refridgerator : 0.3971 0.5541 0.6131 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] shower curtain : 0.4468 0.5937 0.6964 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] toilet : 0.8291 0.9896 0.9896 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] sink : 0.2955 0.6099 0.8530 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] bathtub : 0.5817 0.7222 0.8686 +[2025-02-22 12:55:04,391 INFO evaluator.py line 547 2775932] otherfurniture : 0.3413 0.5075 0.6266 +[2025-02-22 12:55:04,391 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:55:04,391 INFO evaluator.py line 554 2775932] average : 0.3504 0.5500 0.7185 +[2025-02-22 12:55:04,391 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:55:04,391 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:55:04,423 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 12:55:04,428 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:55:13,070 INFO hook.py line 109 2775932] Train: [54/100][50/800] Data 0.002 (0.003) Batch 0.159 (0.142) Remain 01:28:39 loss: -0.3319 Lr: 2.94649e-03 +[2025-02-22 12:55:20,478 INFO hook.py line 109 2775932] Train: [54/100][100/800] Data 0.003 (0.003) Batch 0.124 (0.145) Remain 01:30:37 loss: -0.5317 Lr: 2.94029e-03 +[2025-02-22 12:55:27,551 INFO hook.py line 109 2775932] Train: [54/100][150/800] Data 0.004 (0.003) Batch 0.140 (0.144) Remain 01:29:45 loss: -0.5018 Lr: 2.93409e-03 +[2025-02-22 12:55:34,775 INFO hook.py line 109 2775932] Train: [54/100][200/800] Data 0.003 (0.004) Batch 0.148 (0.144) Remain 01:29:44 loss: -0.6102 Lr: 2.92789e-03 +[2025-02-22 12:55:41,945 INFO hook.py line 109 2775932] Train: [54/100][250/800] Data 0.003 (0.004) Batch 0.134 (0.144) Remain 01:29:32 loss: -0.3443 Lr: 2.92169e-03 +[2025-02-22 12:55:49,249 INFO hook.py line 109 2775932] Train: [54/100][300/800] Data 0.004 (0.004) Batch 0.142 (0.144) Remain 01:29:39 loss: -0.6754 Lr: 2.91550e-03 +[2025-02-22 12:55:56,337 INFO hook.py line 109 2775932] Train: [54/100][350/800] Data 0.002 (0.003) Batch 0.117 (0.144) Remain 01:29:19 loss: -0.5376 Lr: 2.90930e-03 +[2025-02-22 12:56:03,780 INFO hook.py line 109 2775932] Train: [54/100][400/800] Data 0.004 (0.003) Batch 0.146 (0.145) Remain 01:29:35 loss: -0.3920 Lr: 2.90310e-03 +[2025-02-22 12:56:11,162 INFO hook.py line 109 2775932] Train: [54/100][450/800] Data 0.003 (0.003) Batch 0.166 (0.145) Remain 01:29:41 loss: -0.5854 Lr: 2.89691e-03 +[2025-02-22 12:56:18,467 INFO hook.py line 109 2775932] Train: [54/100][500/800] Data 0.003 (0.003) Batch 0.134 (0.145) Remain 01:29:38 loss: -0.2197 Lr: 2.89071e-03 +[2025-02-22 12:56:25,550 INFO hook.py line 109 2775932] Train: [54/100][550/800] Data 0.004 (0.003) Batch 0.146 (0.145) Remain 01:29:20 loss: -0.6544 Lr: 2.88451e-03 +[2025-02-22 12:56:32,620 INFO hook.py line 109 2775932] Train: [54/100][600/800] Data 0.002 (0.003) Batch 0.147 (0.144) Remain 01:29:02 loss: -0.6256 Lr: 2.87832e-03 +[2025-02-22 12:56:39,877 INFO hook.py line 109 2775932] Train: [54/100][650/800] Data 0.002 (0.003) Batch 0.158 (0.144) Remain 01:28:57 loss: -0.4207 Lr: 2.87213e-03 +[2025-02-22 12:56:47,144 INFO hook.py line 109 2775932] Train: [54/100][700/800] Data 0.003 (0.003) Batch 0.171 (0.145) Remain 01:28:52 loss: -0.5199 Lr: 2.86593e-03 +[2025-02-22 12:56:54,156 INFO hook.py line 109 2775932] Train: [54/100][750/800] Data 0.004 (0.003) Batch 0.134 (0.144) Remain 01:28:35 loss: -0.7099 Lr: 2.85974e-03 +[2025-02-22 12:57:01,146 INFO hook.py line 109 2775932] Train: [54/100][800/800] Data 0.003 (0.003) Batch 0.131 (0.144) Remain 01:28:17 loss: -0.5396 Lr: 2.85355e-03 +[2025-02-22 12:57:01,147 INFO misc.py line 135 2775932] Train result: loss: -0.4997 seg_loss: 0.2042 bias_l1_loss: 0.2331 bias_cosine_loss: -0.9369 +[2025-02-22 12:57:01,148 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:57:08,461 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7597 +[2025-02-22 12:57:09,042 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4381 +[2025-02-22 12:57:09,113 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5278 +[2025-02-22 12:57:09,209 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5321 +[2025-02-22 12:57:09,298 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5494 +[2025-02-22 12:57:09,361 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0220 +[2025-02-22 12:57:09,701 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5279 +[2025-02-22 12:57:09,732 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5841 +[2025-02-22 12:57:09,895 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0288 +[2025-02-22 12:57:09,968 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0249 +[2025-02-22 12:57:10,244 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1964 +[2025-02-22 12:57:10,365 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0139 +[2025-02-22 12:57:10,441 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.3428 +[2025-02-22 12:57:10,543 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.7873 +[2025-02-22 12:57:10,624 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.1032 +[2025-02-22 12:57:10,703 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6058 +[2025-02-22 12:57:10,844 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3975 +[2025-02-22 12:57:10,946 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2953 +[2025-02-22 12:57:11,121 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0019 +[2025-02-22 12:57:11,183 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0187 +[2025-02-22 12:57:11,358 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5636 +[2025-02-22 12:57:11,565 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.0074 +[2025-02-22 12:57:11,647 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1635 +[2025-02-22 12:57:11,705 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1629 +[2025-02-22 12:57:11,793 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2342 +[2025-02-22 12:57:11,872 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4103 +[2025-02-22 12:57:12,014 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2219 +[2025-02-22 12:57:12,111 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5353 +[2025-02-22 12:57:12,182 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5030 +[2025-02-22 12:57:12,256 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6023 +[2025-02-22 12:57:13,045 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5466 +[2025-02-22 12:57:13,162 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1854 +[2025-02-22 12:57:13,209 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6379 +[2025-02-22 12:57:13,308 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2443 +[2025-02-22 12:57:13,344 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5208 +[2025-02-22 12:57:13,472 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1692 +[2025-02-22 12:57:13,542 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5372 +[2025-02-22 12:57:13,657 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6072 +[2025-02-22 12:57:13,819 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1298 +[2025-02-22 12:57:14,025 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5622 +[2025-02-22 12:57:14,181 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.2949 +[2025-02-22 12:57:14,230 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.3520 +[2025-02-22 12:57:14,265 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7054 +[2025-02-22 12:57:14,555 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5267 +[2025-02-22 12:57:14,607 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4458 +[2025-02-22 12:57:14,665 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5226 +[2025-02-22 12:57:14,776 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5148 +[2025-02-22 12:57:14,905 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2370 +[2025-02-22 12:57:15,017 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3467 +[2025-02-22 12:57:15,117 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0307 +[2025-02-22 12:57:15,197 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1660 +[2025-02-22 12:57:15,344 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3718 +[2025-02-22 12:57:15,389 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5730 +[2025-02-22 12:57:15,509 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8404 +[2025-02-22 12:57:15,616 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7447 +[2025-02-22 12:57:15,673 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7323 +[2025-02-22 12:57:15,823 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0433 +[2025-02-22 12:57:15,873 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4409 +[2025-02-22 12:57:16,125 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2061 +[2025-02-22 12:57:16,240 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0603 +[2025-02-22 12:57:16,332 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6138 +[2025-02-22 12:57:16,394 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4667 +[2025-02-22 12:57:16,571 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0423 +[2025-02-22 12:57:16,686 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6369 +[2025-02-22 12:57:16,750 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0518 +[2025-02-22 12:57:16,898 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1792 +[2025-02-22 12:57:17,087 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6425 +[2025-02-22 12:57:17,175 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0826 +[2025-02-22 12:57:17,238 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7009 +[2025-02-22 12:57:17,305 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3400 +[2025-02-22 12:57:17,495 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1695 +[2025-02-22 12:57:17,534 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6151 +[2025-02-22 12:57:17,587 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7583 +[2025-02-22 12:57:17,698 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.1118 +[2025-02-22 12:57:17,919 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6399 +[2025-02-22 12:57:18,002 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2003 +[2025-02-22 12:57:18,192 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5398 +[2025-02-22 12:57:18,296 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6925 +[2025-02-22 12:57:33,184 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:57:33,185 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:57:33,185 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] cabinet : 0.2494 0.4809 0.6974 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] bed : 0.3614 0.7505 0.8605 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] chair : 0.7403 0.9003 0.9338 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] sofa : 0.3324 0.5488 0.7987 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] table : 0.4068 0.6390 0.8076 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] door : 0.2502 0.4852 0.6330 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] window : 0.2409 0.4409 0.6410 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] bookshelf : 0.2224 0.5539 0.7993 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] picture : 0.3496 0.5316 0.6625 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] counter : 0.0247 0.0792 0.4727 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] desk : 0.0694 0.2603 0.7174 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] curtain : 0.2740 0.4127 0.5987 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] refridgerator : 0.3697 0.4949 0.5232 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] shower curtain : 0.4469 0.6072 0.7184 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] toilet : 0.8186 0.9920 0.9920 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] sink : 0.2050 0.5330 0.8579 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] bathtub : 0.5333 0.6926 0.8343 +[2025-02-22 12:57:33,185 INFO evaluator.py line 547 2775932] otherfurniture : 0.3837 0.5744 0.6967 +[2025-02-22 12:57:33,185 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:57:33,185 INFO evaluator.py line 554 2775932] average : 0.3488 0.5543 0.7359 +[2025-02-22 12:57:33,185 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:57:33,185 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:57:33,242 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 12:57:33,248 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 12:57:41,919 INFO hook.py line 109 2775932] Train: [55/100][50/800] Data 0.003 (0.007) Batch 0.155 (0.151) Remain 01:32:33 loss: -0.7042 Lr: 2.84735e-03 +[2025-02-22 12:57:49,193 INFO hook.py line 109 2775932] Train: [55/100][100/800] Data 0.003 (0.005) Batch 0.148 (0.148) Remain 01:30:39 loss: -0.5444 Lr: 2.84116e-03 +[2025-02-22 12:57:56,223 INFO hook.py line 109 2775932] Train: [55/100][150/800] Data 0.002 (0.004) Batch 0.140 (0.146) Remain 01:28:57 loss: -0.6568 Lr: 2.83497e-03 +[2025-02-22 12:58:03,347 INFO hook.py line 109 2775932] Train: [55/100][200/800] Data 0.002 (0.004) Batch 0.131 (0.145) Remain 01:28:20 loss: -0.6842 Lr: 2.82878e-03 +[2025-02-22 12:58:10,865 INFO hook.py line 109 2775932] Train: [55/100][250/800] Data 0.004 (0.004) Batch 0.154 (0.146) Remain 01:28:54 loss: -0.7012 Lr: 2.82259e-03 +[2025-02-22 12:58:17,981 INFO hook.py line 109 2775932] Train: [55/100][300/800] Data 0.003 (0.004) Batch 0.154 (0.145) Remain 01:28:24 loss: -0.5820 Lr: 2.81640e-03 +[2025-02-22 12:58:25,412 INFO hook.py line 109 2775932] Train: [55/100][350/800] Data 0.003 (0.005) Batch 0.132 (0.146) Remain 01:28:34 loss: -0.6435 Lr: 2.81021e-03 +[2025-02-22 12:58:32,517 INFO hook.py line 109 2775932] Train: [55/100][400/800] Data 0.004 (0.005) Batch 0.160 (0.145) Remain 01:28:10 loss: -0.4218 Lr: 2.80403e-03 +[2025-02-22 12:58:39,753 INFO hook.py line 109 2775932] Train: [55/100][450/800] Data 0.003 (0.004) Batch 0.138 (0.145) Remain 01:28:00 loss: -0.6090 Lr: 2.79784e-03 +[2025-02-22 12:58:46,839 INFO hook.py line 109 2775932] Train: [55/100][500/800] Data 0.003 (0.004) Batch 0.139 (0.145) Remain 01:27:40 loss: -0.4095 Lr: 2.79166e-03 +[2025-02-22 12:58:54,005 INFO hook.py line 109 2775932] Train: [55/100][550/800] Data 0.003 (0.004) Batch 0.145 (0.145) Remain 01:27:27 loss: -0.5123 Lr: 2.78547e-03 +[2025-02-22 12:59:01,079 INFO hook.py line 109 2775932] Train: [55/100][600/800] Data 0.002 (0.004) Batch 0.168 (0.144) Remain 01:27:10 loss: -0.2855 Lr: 2.77929e-03 +[2025-02-22 12:59:08,244 INFO hook.py line 109 2775932] Train: [55/100][650/800] Data 0.003 (0.004) Batch 0.136 (0.144) Remain 01:27:00 loss: -0.6025 Lr: 2.77323e-03 +[2025-02-22 12:59:15,276 INFO hook.py line 109 2775932] Train: [55/100][700/800] Data 0.004 (0.004) Batch 0.139 (0.144) Remain 01:26:43 loss: -0.5393 Lr: 2.76705e-03 +[2025-02-22 12:59:22,590 INFO hook.py line 109 2775932] Train: [55/100][750/800] Data 0.003 (0.004) Batch 0.172 (0.144) Remain 01:26:40 loss: 0.0741 Lr: 2.76087e-03 +[2025-02-22 12:59:29,715 INFO hook.py line 109 2775932] Train: [55/100][800/800] Data 0.003 (0.004) Batch 0.122 (0.144) Remain 01:26:29 loss: -0.5487 Lr: 2.75469e-03 +[2025-02-22 12:59:29,716 INFO misc.py line 135 2775932] Train result: loss: -0.5097 seg_loss: 0.1998 bias_l1_loss: 0.2286 bias_cosine_loss: -0.9381 +[2025-02-22 12:59:29,716 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 12:59:36,797 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7616 +[2025-02-22 12:59:37,101 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4971 +[2025-02-22 12:59:37,175 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5326 +[2025-02-22 12:59:37,563 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5937 +[2025-02-22 12:59:37,651 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6420 +[2025-02-22 12:59:37,731 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8041 +[2025-02-22 12:59:38,014 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5326 +[2025-02-22 12:59:38,047 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6024 +[2025-02-22 12:59:38,188 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0862 +[2025-02-22 12:59:38,249 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3678 +[2025-02-22 12:59:38,492 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0052 +[2025-02-22 12:59:38,606 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1181 +[2025-02-22 12:59:38,675 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.7239 +[2025-02-22 12:59:38,761 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8810 +[2025-02-22 12:59:38,846 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0127 +[2025-02-22 12:59:38,923 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5614 +[2025-02-22 12:59:39,053 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5528 +[2025-02-22 12:59:39,153 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4207 +[2025-02-22 12:59:39,334 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0606 +[2025-02-22 12:59:39,412 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2242 +[2025-02-22 12:59:39,564 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6604 +[2025-02-22 12:59:39,745 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0984 +[2025-02-22 12:59:39,822 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1022 +[2025-02-22 12:59:39,877 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0631 +[2025-02-22 12:59:39,941 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3282 +[2025-02-22 12:59:40,009 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5331 +[2025-02-22 12:59:40,147 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2059 +[2025-02-22 12:59:40,233 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6329 +[2025-02-22 12:59:40,307 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6616 +[2025-02-22 12:59:40,372 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5512 +[2025-02-22 12:59:41,053 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4572 +[2025-02-22 12:59:41,173 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1377 +[2025-02-22 12:59:41,219 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5189 +[2025-02-22 12:59:41,328 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3805 +[2025-02-22 12:59:41,368 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5248 +[2025-02-22 12:59:41,482 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1155 +[2025-02-22 12:59:41,561 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6436 +[2025-02-22 12:59:41,704 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7073 +[2025-02-22 12:59:41,871 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6409 +[2025-02-22 12:59:42,084 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7993 +[2025-02-22 12:59:42,252 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3216 +[2025-02-22 12:59:42,314 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1233 +[2025-02-22 12:59:42,381 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7344 +[2025-02-22 12:59:42,674 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6229 +[2025-02-22 12:59:42,726 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4581 +[2025-02-22 12:59:42,771 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.6131 +[2025-02-22 12:59:42,876 INFO evaluator.py line 595 2775932] Test: [47/78] Loss -0.0320 +[2025-02-22 12:59:42,996 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2027 +[2025-02-22 12:59:43,102 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0330 +[2025-02-22 12:59:43,206 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0532 +[2025-02-22 12:59:43,296 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1008 +[2025-02-22 12:59:43,438 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4461 +[2025-02-22 12:59:43,485 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5702 +[2025-02-22 12:59:43,601 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2592 +[2025-02-22 12:59:43,701 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8174 +[2025-02-22 12:59:43,757 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6195 +[2025-02-22 12:59:43,880 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2800 +[2025-02-22 12:59:43,933 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4446 +[2025-02-22 12:59:44,168 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2284 +[2025-02-22 12:59:44,269 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0288 +[2025-02-22 12:59:44,342 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6495 +[2025-02-22 12:59:44,399 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6644 +[2025-02-22 12:59:44,559 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1401 +[2025-02-22 12:59:44,667 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3091 +[2025-02-22 12:59:44,749 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1894 +[2025-02-22 12:59:44,874 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.4139 +[2025-02-22 12:59:45,040 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5122 +[2025-02-22 12:59:45,158 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1247 +[2025-02-22 12:59:45,206 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8330 +[2025-02-22 12:59:45,252 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3310 +[2025-02-22 12:59:45,392 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0202 +[2025-02-22 12:59:45,429 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5564 +[2025-02-22 12:59:45,484 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6643 +[2025-02-22 12:59:45,590 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.1357 +[2025-02-22 12:59:45,785 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5533 +[2025-02-22 12:59:45,862 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1668 +[2025-02-22 12:59:46,015 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4326 +[2025-02-22 12:59:46,101 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4690 +[2025-02-22 12:59:57,380 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 12:59:57,380 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 12:59:57,380 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] cabinet : 0.2490 0.4774 0.6860 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] bed : 0.3496 0.7201 0.8264 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] chair : 0.7236 0.8821 0.9253 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] sofa : 0.3410 0.5632 0.7989 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] table : 0.4438 0.6494 0.7823 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] door : 0.2168 0.4463 0.6051 +[2025-02-22 12:59:57,380 INFO evaluator.py line 547 2775932] window : 0.1779 0.3256 0.5520 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] bookshelf : 0.2312 0.5225 0.7435 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] picture : 0.3219 0.4826 0.5669 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] counter : 0.0354 0.1424 0.6671 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] desk : 0.1166 0.3718 0.8056 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] curtain : 0.2244 0.3620 0.5849 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] refridgerator : 0.2876 0.3791 0.4352 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] shower curtain : 0.5486 0.7234 0.8246 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] toilet : 0.6710 0.8214 0.8434 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] sink : 0.2749 0.5781 0.8572 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] bathtub : 0.6418 0.8375 0.8710 +[2025-02-22 12:59:57,381 INFO evaluator.py line 547 2775932] otherfurniture : 0.3411 0.5078 0.6209 +[2025-02-22 12:59:57,381 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 12:59:57,381 INFO evaluator.py line 554 2775932] average : 0.3442 0.5440 0.7220 +[2025-02-22 12:59:57,381 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 12:59:57,381 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 12:59:57,422 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 12:59:57,428 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:00:05,821 INFO hook.py line 109 2775932] Train: [56/100][50/800] Data 0.002 (0.003) Batch 0.132 (0.143) Remain 01:25:48 loss: -0.4244 Lr: 2.74851e-03 +[2025-02-22 13:00:13,290 INFO hook.py line 109 2775932] Train: [56/100][100/800] Data 0.003 (0.004) Batch 0.124 (0.146) Remain 01:27:35 loss: -0.6436 Lr: 2.74233e-03 +[2025-02-22 13:00:20,318 INFO hook.py line 109 2775932] Train: [56/100][150/800] Data 0.004 (0.003) Batch 0.128 (0.144) Remain 01:26:17 loss: -0.6781 Lr: 2.73616e-03 +[2025-02-22 13:00:27,272 INFO hook.py line 109 2775932] Train: [56/100][200/800] Data 0.004 (0.003) Batch 0.136 (0.143) Remain 01:25:21 loss: -0.5031 Lr: 2.72998e-03 +[2025-02-22 13:00:34,628 INFO hook.py line 109 2775932] Train: [56/100][250/800] Data 0.003 (0.004) Batch 0.131 (0.144) Remain 01:25:43 loss: -0.6391 Lr: 2.72381e-03 +[2025-02-22 13:00:41,772 INFO hook.py line 109 2775932] Train: [56/100][300/800] Data 0.003 (0.004) Batch 0.152 (0.144) Remain 01:25:30 loss: -0.6866 Lr: 2.71763e-03 +[2025-02-22 13:00:49,133 INFO hook.py line 109 2775932] Train: [56/100][350/800] Data 0.002 (0.004) Batch 0.142 (0.144) Remain 01:25:41 loss: -0.6578 Lr: 2.71146e-03 +[2025-02-22 13:00:56,160 INFO hook.py line 109 2775932] Train: [56/100][400/800] Data 0.003 (0.004) Batch 0.134 (0.144) Remain 01:25:17 loss: -0.6993 Lr: 2.70529e-03 +[2025-02-22 13:01:03,218 INFO hook.py line 109 2775932] Train: [56/100][450/800] Data 0.002 (0.004) Batch 0.127 (0.143) Remain 01:25:00 loss: -0.5287 Lr: 2.69912e-03 +[2025-02-22 13:01:10,495 INFO hook.py line 109 2775932] Train: [56/100][500/800] Data 0.003 (0.003) Batch 0.137 (0.144) Remain 01:25:00 loss: -0.4679 Lr: 2.69295e-03 +[2025-02-22 13:01:17,815 INFO hook.py line 109 2775932] Train: [56/100][550/800] Data 0.003 (0.003) Batch 0.148 (0.144) Remain 01:25:01 loss: -0.6168 Lr: 2.68679e-03 +[2025-02-22 13:01:25,238 INFO hook.py line 109 2775932] Train: [56/100][600/800] Data 0.002 (0.003) Batch 0.246 (0.144) Remain 01:25:08 loss: -0.5277 Lr: 2.68062e-03 +[2025-02-22 13:01:32,243 INFO hook.py line 109 2775932] Train: [56/100][650/800] Data 0.003 (0.003) Batch 0.139 (0.144) Remain 01:24:49 loss: -0.5312 Lr: 2.67446e-03 +[2025-02-22 13:01:39,430 INFO hook.py line 109 2775932] Train: [56/100][700/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 01:24:41 loss: -0.6279 Lr: 2.66830e-03 +[2025-02-22 13:01:46,548 INFO hook.py line 109 2775932] Train: [56/100][750/800] Data 0.003 (0.003) Batch 0.130 (0.144) Remain 01:24:30 loss: -0.6273 Lr: 2.66213e-03 +[2025-02-22 13:01:53,781 INFO hook.py line 109 2775932] Train: [56/100][800/800] Data 0.002 (0.003) Batch 0.129 (0.144) Remain 01:24:25 loss: -0.6403 Lr: 2.65597e-03 +[2025-02-22 13:01:53,782 INFO misc.py line 135 2775932] Train result: loss: -0.5167 seg_loss: 0.1945 bias_l1_loss: 0.2281 bias_cosine_loss: -0.9393 +[2025-02-22 13:01:53,782 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:02:01,084 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7806 +[2025-02-22 13:02:01,974 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5092 +[2025-02-22 13:02:02,056 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5095 +[2025-02-22 13:02:02,124 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5041 +[2025-02-22 13:02:02,181 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6621 +[2025-02-22 13:02:02,242 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0264 +[2025-02-22 13:02:02,494 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4236 +[2025-02-22 13:02:02,529 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5882 +[2025-02-22 13:02:02,673 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2573 +[2025-02-22 13:02:02,729 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0882 +[2025-02-22 13:02:02,965 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2130 +[2025-02-22 13:02:03,074 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.5466 +[2025-02-22 13:02:03,145 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.2251 +[2025-02-22 13:02:03,242 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9099 +[2025-02-22 13:02:03,331 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0447 +[2025-02-22 13:02:03,413 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6327 +[2025-02-22 13:02:03,546 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5856 +[2025-02-22 13:02:03,641 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3089 +[2025-02-22 13:02:03,783 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1817 +[2025-02-22 13:02:03,851 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0717 +[2025-02-22 13:02:04,018 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6593 +[2025-02-22 13:02:04,198 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1595 +[2025-02-22 13:02:04,275 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2072 +[2025-02-22 13:02:04,333 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0344 +[2025-02-22 13:02:04,397 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3131 +[2025-02-22 13:02:04,457 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5614 +[2025-02-22 13:02:04,579 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.3285 +[2025-02-22 13:02:04,667 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6376 +[2025-02-22 13:02:04,738 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6183 +[2025-02-22 13:02:04,803 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5646 +[2025-02-22 13:02:05,559 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5144 +[2025-02-22 13:02:05,670 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0554 +[2025-02-22 13:02:05,707 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6758 +[2025-02-22 13:02:05,795 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.5647 +[2025-02-22 13:02:05,844 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4709 +[2025-02-22 13:02:05,953 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9294 +[2025-02-22 13:02:06,021 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4449 +[2025-02-22 13:02:06,150 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6661 +[2025-02-22 13:02:06,302 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7318 +[2025-02-22 13:02:06,507 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7154 +[2025-02-22 13:02:06,645 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5186 +[2025-02-22 13:02:06,692 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4281 +[2025-02-22 13:02:06,727 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7027 +[2025-02-22 13:02:06,969 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7100 +[2025-02-22 13:02:07,008 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4772 +[2025-02-22 13:02:07,045 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5611 +[2025-02-22 13:02:07,132 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5031 +[2025-02-22 13:02:07,248 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2584 +[2025-02-22 13:02:07,353 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.4240 +[2025-02-22 13:02:07,441 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3204 +[2025-02-22 13:02:07,507 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2525 +[2025-02-22 13:02:07,626 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3989 +[2025-02-22 13:02:07,662 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5222 +[2025-02-22 13:02:07,767 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.7171 +[2025-02-22 13:02:07,866 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7947 +[2025-02-22 13:02:08,060 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7292 +[2025-02-22 13:02:08,196 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.3017 +[2025-02-22 13:02:08,242 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3336 +[2025-02-22 13:02:08,486 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2481 +[2025-02-22 13:02:08,589 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0743 +[2025-02-22 13:02:08,673 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5230 +[2025-02-22 13:02:08,726 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3997 +[2025-02-22 13:02:08,877 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2515 +[2025-02-22 13:02:08,989 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4361 +[2025-02-22 13:02:09,066 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0352 +[2025-02-22 13:02:09,203 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2184 +[2025-02-22 13:02:09,375 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6031 +[2025-02-22 13:02:09,467 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1036 +[2025-02-22 13:02:09,525 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7274 +[2025-02-22 13:02:09,580 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0421 +[2025-02-22 13:02:09,733 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0932 +[2025-02-22 13:02:09,776 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6188 +[2025-02-22 13:02:09,827 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7813 +[2025-02-22 13:02:09,929 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 4.1237 +[2025-02-22 13:02:10,144 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6870 +[2025-02-22 13:02:10,223 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1763 +[2025-02-22 13:02:10,375 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4752 +[2025-02-22 13:02:10,474 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6766 +[2025-02-22 13:02:21,254 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:02:21,254 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:02:21,254 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] cabinet : 0.2543 0.4763 0.7085 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] bed : 0.3507 0.7065 0.8488 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] chair : 0.7204 0.8784 0.9222 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] sofa : 0.3684 0.5959 0.8504 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] table : 0.3919 0.6669 0.8027 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] door : 0.2187 0.4177 0.5730 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] window : 0.2189 0.3975 0.5884 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] bookshelf : 0.2469 0.5261 0.7188 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] picture : 0.3083 0.4638 0.5431 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] counter : 0.0398 0.1556 0.6062 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] desk : 0.0752 0.2511 0.6789 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] curtain : 0.2475 0.4320 0.5671 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] refridgerator : 0.3576 0.4814 0.5252 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] shower curtain : 0.4603 0.6257 0.6927 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] toilet : 0.8240 1.0000 1.0000 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] sink : 0.3438 0.5993 0.8358 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] bathtub : 0.6426 0.7972 0.8710 +[2025-02-22 13:02:21,254 INFO evaluator.py line 547 2775932] otherfurniture : 0.3804 0.5722 0.6969 +[2025-02-22 13:02:21,254 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:02:21,254 INFO evaluator.py line 554 2775932] average : 0.3583 0.5580 0.7239 +[2025-02-22 13:02:21,254 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:02:21,255 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:02:21,289 INFO misc.py line 164 2775932] Currently Best AP50: 0.5598 +[2025-02-22 13:02:21,295 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:02:29,880 INFO hook.py line 109 2775932] Train: [57/100][50/800] Data 0.003 (0.003) Batch 0.129 (0.142) Remain 01:23:08 loss: -0.4697 Lr: 2.64982e-03 +[2025-02-22 13:02:36,954 INFO hook.py line 109 2775932] Train: [57/100][100/800] Data 0.003 (0.003) Batch 0.132 (0.142) Remain 01:22:53 loss: -0.7349 Lr: 2.64366e-03 +[2025-02-22 13:02:44,450 INFO hook.py line 109 2775932] Train: [57/100][150/800] Data 0.002 (0.004) Batch 0.140 (0.144) Remain 01:24:24 loss: -0.6124 Lr: 2.63750e-03 +[2025-02-22 13:02:51,559 INFO hook.py line 109 2775932] Train: [57/100][200/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 01:23:56 loss: -0.4019 Lr: 2.63135e-03 +[2025-02-22 13:02:58,780 INFO hook.py line 109 2775932] Train: [57/100][250/800] Data 0.002 (0.004) Batch 0.241 (0.144) Remain 01:23:53 loss: -0.5228 Lr: 2.62520e-03 +[2025-02-22 13:03:05,853 INFO hook.py line 109 2775932] Train: [57/100][300/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 01:23:30 loss: -0.2749 Lr: 2.61905e-03 +[2025-02-22 13:03:13,077 INFO hook.py line 109 2775932] Train: [57/100][350/800] Data 0.003 (0.003) Batch 0.132 (0.144) Remain 01:23:28 loss: -0.5586 Lr: 2.61290e-03 +[2025-02-22 13:03:20,182 INFO hook.py line 109 2775932] Train: [57/100][400/800] Data 0.002 (0.003) Batch 0.145 (0.144) Remain 01:23:13 loss: -0.5557 Lr: 2.60675e-03 +[2025-02-22 13:03:27,279 INFO hook.py line 109 2775932] Train: [57/100][450/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 01:23:00 loss: -0.5173 Lr: 2.60061e-03 +[2025-02-22 13:03:34,385 INFO hook.py line 109 2775932] Train: [57/100][500/800] Data 0.002 (0.003) Batch 0.139 (0.143) Remain 01:22:49 loss: -0.6399 Lr: 2.59446e-03 +[2025-02-22 13:03:41,430 INFO hook.py line 109 2775932] Train: [57/100][550/800] Data 0.003 (0.003) Batch 0.140 (0.143) Remain 01:22:34 loss: -0.3628 Lr: 2.58832e-03 +[2025-02-22 13:03:48,670 INFO hook.py line 109 2775932] Train: [57/100][600/800] Data 0.002 (0.003) Batch 0.143 (0.143) Remain 01:22:32 loss: -0.4947 Lr: 2.58218e-03 +[2025-02-22 13:03:55,781 INFO hook.py line 109 2775932] Train: [57/100][650/800] Data 0.003 (0.003) Batch 0.141 (0.143) Remain 01:22:23 loss: -0.6677 Lr: 2.57604e-03 +[2025-02-22 13:04:03,235 INFO hook.py line 109 2775932] Train: [57/100][700/800] Data 0.004 (0.003) Batch 0.146 (0.144) Remain 01:22:30 loss: -0.5239 Lr: 2.56991e-03 +[2025-02-22 13:04:10,261 INFO hook.py line 109 2775932] Train: [57/100][750/800] Data 0.002 (0.003) Batch 0.146 (0.143) Remain 01:22:16 loss: -0.4981 Lr: 2.56377e-03 +[2025-02-22 13:04:17,409 INFO hook.py line 109 2775932] Train: [57/100][800/800] Data 0.002 (0.004) Batch 0.105 (0.143) Remain 01:22:08 loss: -0.5765 Lr: 2.55776e-03 +[2025-02-22 13:04:17,410 INFO misc.py line 135 2775932] Train result: loss: -0.5242 seg_loss: 0.1918 bias_l1_loss: 0.2242 bias_cosine_loss: -0.9401 +[2025-02-22 13:04:17,410 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:04:24,626 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7706 +[2025-02-22 13:04:25,605 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4755 +[2025-02-22 13:04:25,677 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5120 +[2025-02-22 13:04:25,766 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6470 +[2025-02-22 13:04:25,824 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5703 +[2025-02-22 13:04:25,888 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9854 +[2025-02-22 13:04:26,221 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4268 +[2025-02-22 13:04:26,263 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4483 +[2025-02-22 13:04:26,405 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1129 +[2025-02-22 13:04:26,463 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1647 +[2025-02-22 13:04:26,740 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0030 +[2025-02-22 13:04:26,859 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.4257 +[2025-02-22 13:04:26,933 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.0760 +[2025-02-22 13:04:27,025 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3625 +[2025-02-22 13:04:27,116 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3753 +[2025-02-22 13:04:27,194 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6209 +[2025-02-22 13:04:27,333 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5493 +[2025-02-22 13:04:27,446 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2737 +[2025-02-22 13:04:27,607 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.3912 +[2025-02-22 13:04:27,668 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2071 +[2025-02-22 13:04:27,832 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6684 +[2025-02-22 13:04:28,015 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.0808 +[2025-02-22 13:04:28,210 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1970 +[2025-02-22 13:04:28,264 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1635 +[2025-02-22 13:04:28,327 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1646 +[2025-02-22 13:04:28,387 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5838 +[2025-02-22 13:04:28,527 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2399 +[2025-02-22 13:04:28,625 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6125 +[2025-02-22 13:04:28,692 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6753 +[2025-02-22 13:04:28,751 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6008 +[2025-02-22 13:04:29,519 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5390 +[2025-02-22 13:04:29,677 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3665 +[2025-02-22 13:04:29,724 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7013 +[2025-02-22 13:04:29,841 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3456 +[2025-02-22 13:04:29,891 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5573 +[2025-02-22 13:04:30,016 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9948 +[2025-02-22 13:04:30,089 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6050 +[2025-02-22 13:04:30,234 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.5979 +[2025-02-22 13:04:30,426 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.2498 +[2025-02-22 13:04:30,679 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0018 +[2025-02-22 13:04:30,856 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.2872 +[2025-02-22 13:04:30,910 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3492 +[2025-02-22 13:04:30,951 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7438 +[2025-02-22 13:04:31,232 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5964 +[2025-02-22 13:04:31,275 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3698 +[2025-02-22 13:04:31,318 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4844 +[2025-02-22 13:04:31,425 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.6250 +[2025-02-22 13:04:31,566 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2407 +[2025-02-22 13:04:31,683 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1355 +[2025-02-22 13:04:31,785 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0930 +[2025-02-22 13:04:31,887 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.0543 +[2025-02-22 13:04:32,035 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2658 +[2025-02-22 13:04:32,080 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4993 +[2025-02-22 13:04:32,208 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1751 +[2025-02-22 13:04:32,306 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8523 +[2025-02-22 13:04:32,355 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7266 +[2025-02-22 13:04:32,501 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1972 +[2025-02-22 13:04:32,547 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3982 +[2025-02-22 13:04:32,781 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3179 +[2025-02-22 13:04:32,902 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0441 +[2025-02-22 13:04:32,990 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5806 +[2025-02-22 13:04:33,050 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6052 +[2025-02-22 13:04:33,227 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.4183 +[2025-02-22 13:04:33,345 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.6947 +[2025-02-22 13:04:33,432 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2368 +[2025-02-22 13:04:33,584 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1408 +[2025-02-22 13:04:33,767 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4001 +[2025-02-22 13:04:33,884 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1055 +[2025-02-22 13:04:33,938 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6772 +[2025-02-22 13:04:33,992 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2393 +[2025-02-22 13:04:34,165 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3606 +[2025-02-22 13:04:34,205 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4853 +[2025-02-22 13:04:34,263 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7995 +[2025-02-22 13:04:34,382 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3747 +[2025-02-22 13:04:34,603 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6092 +[2025-02-22 13:04:34,696 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0256 +[2025-02-22 13:04:34,922 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3916 +[2025-02-22 13:04:35,024 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6515 +[2025-02-22 13:04:46,206 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:04:46,206 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:04:46,206 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] cabinet : 0.2405 0.4462 0.6533 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] bed : 0.3604 0.6831 0.8240 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] chair : 0.7414 0.9003 0.9396 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] sofa : 0.4047 0.6700 0.8339 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] table : 0.3973 0.6249 0.7676 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] door : 0.2200 0.4303 0.5659 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] window : 0.1746 0.3371 0.5535 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] bookshelf : 0.2028 0.5067 0.7146 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] picture : 0.2666 0.3917 0.4535 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] counter : 0.0775 0.2432 0.6689 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] desk : 0.1169 0.3243 0.7854 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] curtain : 0.2172 0.3779 0.5774 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] refridgerator : 0.4363 0.6154 0.6715 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] shower curtain : 0.3983 0.6044 0.7973 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] toilet : 0.7566 0.9477 0.9477 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] sink : 0.3298 0.5758 0.8391 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] bathtub : 0.6431 0.8387 0.8710 +[2025-02-22 13:04:46,206 INFO evaluator.py line 547 2775932] otherfurniture : 0.3966 0.5850 0.6967 +[2025-02-22 13:04:46,206 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:04:46,207 INFO evaluator.py line 554 2775932] average : 0.3545 0.5613 0.7312 +[2025-02-22 13:04:46,207 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:04:46,207 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:04:46,242 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5613 +[2025-02-22 13:04:46,247 INFO misc.py line 164 2775932] Currently Best AP50: 0.5613 +[2025-02-22 13:04:46,247 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:04:56,127 INFO hook.py line 109 2775932] Train: [58/100][50/800] Data 0.002 (0.008) Batch 0.146 (0.155) Remain 01:28:28 loss: -0.6014 Lr: 2.55163e-03 +[2025-02-22 13:05:03,442 INFO hook.py line 109 2775932] Train: [58/100][100/800] Data 0.003 (0.006) Batch 0.153 (0.150) Remain 01:25:54 loss: -0.7300 Lr: 2.54550e-03 +[2025-02-22 13:05:10,674 INFO hook.py line 109 2775932] Train: [58/100][150/800] Data 0.003 (0.005) Batch 0.119 (0.148) Remain 01:24:41 loss: -0.5824 Lr: 2.53937e-03 +[2025-02-22 13:05:17,922 INFO hook.py line 109 2775932] Train: [58/100][200/800] Data 0.003 (0.004) Batch 0.138 (0.148) Remain 01:24:04 loss: -0.5820 Lr: 2.53325e-03 +[2025-02-22 13:05:25,215 INFO hook.py line 109 2775932] Train: [58/100][250/800] Data 0.002 (0.004) Batch 0.140 (0.147) Remain 01:23:45 loss: -0.5820 Lr: 2.52712e-03 +[2025-02-22 13:05:32,356 INFO hook.py line 109 2775932] Train: [58/100][300/800] Data 0.003 (0.004) Batch 0.124 (0.146) Remain 01:23:13 loss: -0.5626 Lr: 2.52100e-03 +[2025-02-22 13:05:39,686 INFO hook.py line 109 2775932] Train: [58/100][350/800] Data 0.003 (0.004) Batch 0.155 (0.146) Remain 01:23:06 loss: -0.4569 Lr: 2.51488e-03 +[2025-02-22 13:05:47,016 INFO hook.py line 109 2775932] Train: [58/100][400/800] Data 0.003 (0.004) Batch 0.151 (0.146) Remain 01:23:00 loss: -0.5543 Lr: 2.50877e-03 +[2025-02-22 13:05:54,159 INFO hook.py line 109 2775932] Train: [58/100][450/800] Data 0.004 (0.004) Batch 0.154 (0.146) Remain 01:22:39 loss: -0.5288 Lr: 2.50265e-03 +[2025-02-22 13:06:01,613 INFO hook.py line 109 2775932] Train: [58/100][500/800] Data 0.004 (0.004) Batch 0.138 (0.146) Remain 01:22:42 loss: -0.5156 Lr: 2.49654e-03 +[2025-02-22 13:06:08,915 INFO hook.py line 109 2775932] Train: [58/100][550/800] Data 0.003 (0.004) Batch 0.147 (0.146) Remain 01:22:33 loss: -0.5232 Lr: 2.49043e-03 +[2025-02-22 13:06:16,106 INFO hook.py line 109 2775932] Train: [58/100][600/800] Data 0.003 (0.004) Batch 0.149 (0.146) Remain 01:22:19 loss: -0.4503 Lr: 2.48432e-03 +[2025-02-22 13:06:23,249 INFO hook.py line 109 2775932] Train: [58/100][650/800] Data 0.005 (0.004) Batch 0.138 (0.146) Remain 01:22:03 loss: -0.6297 Lr: 2.47821e-03 +[2025-02-22 13:06:30,436 INFO hook.py line 109 2775932] Train: [58/100][700/800] Data 0.003 (0.004) Batch 0.129 (0.146) Remain 01:21:50 loss: -0.0809 Lr: 2.47211e-03 +[2025-02-22 13:06:37,807 INFO hook.py line 109 2775932] Train: [58/100][750/800] Data 0.003 (0.004) Batch 0.153 (0.146) Remain 01:21:47 loss: -0.6997 Lr: 2.46601e-03 +[2025-02-22 13:06:44,592 INFO hook.py line 109 2775932] Train: [58/100][800/800] Data 0.002 (0.004) Batch 0.116 (0.145) Remain 01:21:18 loss: -0.5207 Lr: 2.45991e-03 +[2025-02-22 13:06:44,592 INFO misc.py line 135 2775932] Train result: loss: -0.5315 seg_loss: 0.1882 bias_l1_loss: 0.2211 bias_cosine_loss: -0.9408 +[2025-02-22 13:06:44,593 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:06:51,683 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7647 +[2025-02-22 13:06:52,061 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3722 +[2025-02-22 13:06:52,219 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5290 +[2025-02-22 13:06:52,749 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4550 +[2025-02-22 13:06:52,817 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.4771 +[2025-02-22 13:06:52,889 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.5166 +[2025-02-22 13:06:53,186 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4309 +[2025-02-22 13:06:53,220 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3671 +[2025-02-22 13:06:53,384 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.1107 +[2025-02-22 13:06:53,453 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1097 +[2025-02-22 13:06:53,748 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1748 +[2025-02-22 13:06:53,866 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.2904 +[2025-02-22 13:06:53,949 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 1.1368 +[2025-02-22 13:06:54,056 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0101 +[2025-02-22 13:06:54,149 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6115 +[2025-02-22 13:06:54,248 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6216 +[2025-02-22 13:06:54,390 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.3749 +[2025-02-22 13:06:54,488 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2956 +[2025-02-22 13:06:54,651 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1311 +[2025-02-22 13:06:54,719 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0218 +[2025-02-22 13:06:54,888 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6627 +[2025-02-22 13:06:55,080 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3043 +[2025-02-22 13:06:55,169 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1564 +[2025-02-22 13:06:55,225 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.2454 +[2025-02-22 13:06:55,300 INFO evaluator.py line 595 2775932] Test: [25/78] Loss 0.0131 +[2025-02-22 13:06:55,363 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4487 +[2025-02-22 13:06:55,509 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1490 +[2025-02-22 13:06:55,618 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6660 +[2025-02-22 13:06:55,703 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6785 +[2025-02-22 13:06:55,783 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6312 +[2025-02-22 13:06:56,477 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.3955 +[2025-02-22 13:06:56,614 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0780 +[2025-02-22 13:06:56,654 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7061 +[2025-02-22 13:06:56,751 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3282 +[2025-02-22 13:06:56,789 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6601 +[2025-02-22 13:06:56,915 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1646 +[2025-02-22 13:06:56,995 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6913 +[2025-02-22 13:06:57,162 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6844 +[2025-02-22 13:06:57,355 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.0201 +[2025-02-22 13:06:57,599 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7991 +[2025-02-22 13:06:57,792 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5084 +[2025-02-22 13:06:57,849 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3463 +[2025-02-22 13:06:57,897 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7346 +[2025-02-22 13:06:58,199 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.4692 +[2025-02-22 13:06:58,246 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5540 +[2025-02-22 13:06:58,291 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4660 +[2025-02-22 13:06:58,399 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3910 +[2025-02-22 13:06:58,543 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3236 +[2025-02-22 13:06:58,659 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3423 +[2025-02-22 13:06:58,774 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2557 +[2025-02-22 13:06:58,858 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1593 +[2025-02-22 13:06:59,028 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3779 +[2025-02-22 13:06:59,075 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6651 +[2025-02-22 13:06:59,223 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.4613 +[2025-02-22 13:06:59,339 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8056 +[2025-02-22 13:06:59,396 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6439 +[2025-02-22 13:06:59,562 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0334 +[2025-02-22 13:06:59,613 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4687 +[2025-02-22 13:06:59,923 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3203 +[2025-02-22 13:07:00,045 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.3047 +[2025-02-22 13:07:00,125 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6478 +[2025-02-22 13:07:00,186 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5915 +[2025-02-22 13:07:00,355 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3860 +[2025-02-22 13:07:00,464 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4213 +[2025-02-22 13:07:00,539 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0711 +[2025-02-22 13:07:00,682 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0721 +[2025-02-22 13:07:00,881 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6496 +[2025-02-22 13:07:01,001 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0243 +[2025-02-22 13:07:01,071 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6839 +[2025-02-22 13:07:01,136 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.1141 +[2025-02-22 13:07:01,321 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.1336 +[2025-02-22 13:07:01,366 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5609 +[2025-02-22 13:07:01,429 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6587 +[2025-02-22 13:07:01,558 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5225 +[2025-02-22 13:07:01,804 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.4882 +[2025-02-22 13:07:01,936 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.3963 +[2025-02-22 13:07:02,119 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3184 +[2025-02-22 13:07:02,220 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5560 +[2025-02-22 13:07:15,423 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:07:15,423 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:07:15,423 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] cabinet : 0.2159 0.4237 0.6205 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] bed : 0.3170 0.5915 0.7748 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] chair : 0.7144 0.8711 0.9173 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] sofa : 0.3548 0.6137 0.8314 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] table : 0.3989 0.5928 0.7129 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] door : 0.2367 0.4665 0.6166 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] window : 0.2146 0.4130 0.6601 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] bookshelf : 0.2157 0.5670 0.7860 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] picture : 0.3075 0.4609 0.5406 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] counter : 0.0248 0.0696 0.5103 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] desk : 0.1228 0.3216 0.8029 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] curtain : 0.2453 0.4435 0.6074 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] refridgerator : 0.3488 0.5014 0.5552 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] shower curtain : 0.4443 0.6090 0.7519 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] toilet : 0.8343 0.9655 1.0000 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] sink : 0.2741 0.5739 0.8336 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] bathtub : 0.6404 0.7653 0.8673 +[2025-02-22 13:07:15,423 INFO evaluator.py line 547 2775932] otherfurniture : 0.3936 0.5738 0.6930 +[2025-02-22 13:07:15,423 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:07:15,423 INFO evaluator.py line 554 2775932] average : 0.3502 0.5458 0.7268 +[2025-02-22 13:07:15,423 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:07:15,424 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:07:15,466 INFO misc.py line 164 2775932] Currently Best AP50: 0.5613 +[2025-02-22 13:07:15,472 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:07:24,273 INFO hook.py line 109 2775932] Train: [59/100][50/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 01:19:17 loss: -0.3557 Lr: 2.45381e-03 +[2025-02-22 13:07:31,510 INFO hook.py line 109 2775932] Train: [59/100][100/800] Data 0.003 (0.003) Batch 0.138 (0.143) Remain 01:20:00 loss: -0.5669 Lr: 2.44772e-03 +[2025-02-22 13:07:38,734 INFO hook.py line 109 2775932] Train: [59/100][150/800] Data 0.003 (0.003) Batch 0.123 (0.144) Remain 01:20:06 loss: -0.6346 Lr: 2.44162e-03 +[2025-02-22 13:07:46,218 INFO hook.py line 109 2775932] Train: [59/100][200/800] Data 0.003 (0.004) Batch 0.162 (0.145) Remain 01:20:50 loss: -0.4315 Lr: 2.43553e-03 +[2025-02-22 13:07:53,252 INFO hook.py line 109 2775932] Train: [59/100][250/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 01:20:12 loss: -0.4649 Lr: 2.42945e-03 +[2025-02-22 13:08:00,400 INFO hook.py line 109 2775932] Train: [59/100][300/800] Data 0.003 (0.004) Batch 0.140 (0.144) Remain 01:19:57 loss: -0.7724 Lr: 2.42336e-03 +[2025-02-22 13:08:07,569 INFO hook.py line 109 2775932] Train: [59/100][350/800] Data 0.002 (0.004) Batch 0.152 (0.144) Remain 01:19:47 loss: -0.6336 Lr: 2.41728e-03 +[2025-02-22 13:08:14,919 INFO hook.py line 109 2775932] Train: [59/100][400/800] Data 0.004 (0.004) Batch 0.145 (0.144) Remain 01:19:52 loss: -0.5870 Lr: 2.41120e-03 +[2025-02-22 13:08:22,065 INFO hook.py line 109 2775932] Train: [59/100][450/800] Data 0.004 (0.003) Batch 0.152 (0.144) Remain 01:19:40 loss: -0.5187 Lr: 2.40512e-03 +[2025-02-22 13:08:29,393 INFO hook.py line 109 2775932] Train: [59/100][500/800] Data 0.004 (0.003) Batch 0.133 (0.144) Remain 01:19:40 loss: -0.5760 Lr: 2.39904e-03 +[2025-02-22 13:08:36,614 INFO hook.py line 109 2775932] Train: [59/100][550/800] Data 0.004 (0.003) Batch 0.151 (0.144) Remain 01:19:33 loss: -0.6703 Lr: 2.39297e-03 +[2025-02-22 13:08:43,715 INFO hook.py line 109 2775932] Train: [59/100][600/800] Data 0.002 (0.003) Batch 0.154 (0.144) Remain 01:19:19 loss: -0.6113 Lr: 2.38690e-03 +[2025-02-22 13:08:51,059 INFO hook.py line 109 2775932] Train: [59/100][650/800] Data 0.003 (0.003) Batch 0.121 (0.144) Remain 01:19:19 loss: -0.6079 Lr: 2.38083e-03 +[2025-02-22 13:08:58,252 INFO hook.py line 109 2775932] Train: [59/100][700/800] Data 0.003 (0.003) Batch 0.130 (0.144) Remain 01:19:10 loss: -0.3533 Lr: 2.37477e-03 +[2025-02-22 13:09:05,452 INFO hook.py line 109 2775932] Train: [59/100][750/800] Data 0.002 (0.003) Batch 0.145 (0.144) Remain 01:19:02 loss: -0.5709 Lr: 2.36871e-03 +[2025-02-22 13:09:12,635 INFO hook.py line 109 2775932] Train: [59/100][800/800] Data 0.002 (0.003) Batch 0.116 (0.144) Remain 01:18:53 loss: -0.2935 Lr: 2.36265e-03 +[2025-02-22 13:09:12,635 INFO misc.py line 135 2775932] Train result: loss: -0.5275 seg_loss: 0.1894 bias_l1_loss: 0.2236 bias_cosine_loss: -0.9405 +[2025-02-22 13:09:12,636 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:09:19,795 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8036 +[2025-02-22 13:09:20,007 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4058 +[2025-02-22 13:09:20,077 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4666 +[2025-02-22 13:09:20,169 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4467 +[2025-02-22 13:09:20,235 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.5796 +[2025-02-22 13:09:20,294 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.3891 +[2025-02-22 13:09:20,579 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5294 +[2025-02-22 13:09:20,610 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5280 +[2025-02-22 13:09:20,768 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.4304 +[2025-02-22 13:09:20,839 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2076 +[2025-02-22 13:09:21,096 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2429 +[2025-02-22 13:09:21,214 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1539 +[2025-02-22 13:09:21,289 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.5459 +[2025-02-22 13:09:21,400 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3986 +[2025-02-22 13:09:21,505 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4038 +[2025-02-22 13:09:21,584 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5364 +[2025-02-22 13:09:21,730 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4423 +[2025-02-22 13:09:21,855 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4689 +[2025-02-22 13:09:22,047 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2008 +[2025-02-22 13:09:22,113 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.3884 +[2025-02-22 13:09:22,275 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6672 +[2025-02-22 13:09:22,472 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3692 +[2025-02-22 13:09:22,547 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0862 +[2025-02-22 13:09:22,601 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0892 +[2025-02-22 13:09:22,665 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.0805 +[2025-02-22 13:09:22,727 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5371 +[2025-02-22 13:09:22,871 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.1872 +[2025-02-22 13:09:22,959 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4879 +[2025-02-22 13:09:23,036 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6080 +[2025-02-22 13:09:23,110 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6386 +[2025-02-22 13:09:23,918 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4429 +[2025-02-22 13:09:24,044 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1038 +[2025-02-22 13:09:24,086 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6707 +[2025-02-22 13:09:24,195 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0796 +[2025-02-22 13:09:24,235 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5831 +[2025-02-22 13:09:24,361 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8758 +[2025-02-22 13:09:24,430 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5420 +[2025-02-22 13:09:24,575 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7049 +[2025-02-22 13:09:24,745 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.9108 +[2025-02-22 13:09:24,968 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8775 +[2025-02-22 13:09:25,153 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3869 +[2025-02-22 13:09:25,210 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1940 +[2025-02-22 13:09:25,260 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7732 +[2025-02-22 13:09:25,529 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5987 +[2025-02-22 13:09:25,579 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3091 +[2025-02-22 13:09:25,627 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4660 +[2025-02-22 13:09:25,719 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4292 +[2025-02-22 13:09:25,846 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.0804 +[2025-02-22 13:09:25,972 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2121 +[2025-02-22 13:09:26,060 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0226 +[2025-02-22 13:09:26,136 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1859 +[2025-02-22 13:09:26,263 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2999 +[2025-02-22 13:09:26,306 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6169 +[2025-02-22 13:09:26,420 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2404 +[2025-02-22 13:09:26,528 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8396 +[2025-02-22 13:09:26,576 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7588 +[2025-02-22 13:09:26,720 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1913 +[2025-02-22 13:09:26,767 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3976 +[2025-02-22 13:09:26,990 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3005 +[2025-02-22 13:09:27,098 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0660 +[2025-02-22 13:09:27,170 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4880 +[2025-02-22 13:09:27,225 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5250 +[2025-02-22 13:09:27,381 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0809 +[2025-02-22 13:09:27,487 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3836 +[2025-02-22 13:09:27,563 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0371 +[2025-02-22 13:09:27,685 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0859 +[2025-02-22 13:09:27,895 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5949 +[2025-02-22 13:09:27,988 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0414 +[2025-02-22 13:09:28,053 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6725 +[2025-02-22 13:09:28,103 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2239 +[2025-02-22 13:09:28,255 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2279 +[2025-02-22 13:09:28,289 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3849 +[2025-02-22 13:09:28,342 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7704 +[2025-02-22 13:09:28,453 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3321 +[2025-02-22 13:09:28,675 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6445 +[2025-02-22 13:09:28,752 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2850 +[2025-02-22 13:09:28,941 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4422 +[2025-02-22 13:09:29,031 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6415 +[2025-02-22 13:09:41,367 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:09:41,368 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:09:41,368 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] cabinet : 0.2640 0.5006 0.6941 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] bed : 0.3673 0.7114 0.8376 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] chair : 0.7276 0.8822 0.9275 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] sofa : 0.3129 0.5358 0.8056 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] table : 0.4117 0.6418 0.7545 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] door : 0.2042 0.3691 0.5364 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] window : 0.1433 0.2655 0.5015 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] bookshelf : 0.2329 0.4859 0.6992 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] picture : 0.2911 0.4290 0.5179 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] counter : 0.0267 0.0868 0.5467 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] desk : 0.0874 0.2744 0.6950 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] curtain : 0.2305 0.4014 0.5613 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] refridgerator : 0.3634 0.5017 0.6306 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] shower curtain : 0.4591 0.6051 0.6350 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] toilet : 0.8237 0.9812 0.9982 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] sink : 0.3406 0.6665 0.8725 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] bathtub : 0.6298 0.8262 0.8673 +[2025-02-22 13:09:41,368 INFO evaluator.py line 547 2775932] otherfurniture : 0.3525 0.5249 0.6523 +[2025-02-22 13:09:41,368 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:09:41,368 INFO evaluator.py line 554 2775932] average : 0.3483 0.5383 0.7074 +[2025-02-22 13:09:41,368 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:09:41,369 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:09:41,408 INFO misc.py line 164 2775932] Currently Best AP50: 0.5613 +[2025-02-22 13:09:41,414 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:09:49,975 INFO hook.py line 109 2775932] Train: [60/100][50/800] Data 0.003 (0.008) Batch 0.151 (0.146) Remain 01:19:33 loss: -0.4109 Lr: 2.35659e-03 +[2025-02-22 13:09:57,269 INFO hook.py line 109 2775932] Train: [60/100][100/800] Data 0.003 (0.005) Batch 0.159 (0.146) Remain 01:19:28 loss: -0.7131 Lr: 2.35053e-03 +[2025-02-22 13:10:04,489 INFO hook.py line 109 2775932] Train: [60/100][150/800] Data 0.003 (0.005) Batch 0.155 (0.145) Remain 01:19:04 loss: -0.4985 Lr: 2.34448e-03 +[2025-02-22 13:10:11,761 INFO hook.py line 109 2775932] Train: [60/100][200/800] Data 0.004 (0.004) Batch 0.129 (0.145) Remain 01:18:58 loss: -0.5788 Lr: 2.33844e-03 +[2025-02-22 13:10:18,959 INFO hook.py line 109 2775932] Train: [60/100][250/800] Data 0.004 (0.004) Batch 0.159 (0.145) Remain 01:18:42 loss: -0.4707 Lr: 2.33239e-03 +[2025-02-22 13:10:26,283 INFO hook.py line 109 2775932] Train: [60/100][300/800] Data 0.003 (0.004) Batch 0.134 (0.145) Remain 01:18:42 loss: -0.2061 Lr: 2.32635e-03 +[2025-02-22 13:10:33,545 INFO hook.py line 109 2775932] Train: [60/100][350/800] Data 0.003 (0.004) Batch 0.149 (0.145) Remain 01:18:35 loss: -0.6432 Lr: 2.32031e-03 +[2025-02-22 13:10:40,766 INFO hook.py line 109 2775932] Train: [60/100][400/800] Data 0.004 (0.004) Batch 0.133 (0.145) Remain 01:18:24 loss: -0.5098 Lr: 2.31427e-03 +[2025-02-22 13:10:48,353 INFO hook.py line 109 2775932] Train: [60/100][450/800] Data 0.004 (0.004) Batch 0.132 (0.146) Remain 01:18:40 loss: -0.4973 Lr: 2.30824e-03 +[2025-02-22 13:10:55,811 INFO hook.py line 109 2775932] Train: [60/100][500/800] Data 0.003 (0.003) Batch 0.134 (0.146) Remain 01:18:43 loss: -0.7370 Lr: 2.30220e-03 +[2025-02-22 13:11:03,275 INFO hook.py line 109 2775932] Train: [60/100][550/800] Data 0.004 (0.003) Batch 0.150 (0.147) Remain 01:18:45 loss: -0.7942 Lr: 2.29618e-03 +[2025-02-22 13:11:10,726 INFO hook.py line 109 2775932] Train: [60/100][600/800] Data 0.003 (0.003) Batch 0.139 (0.147) Remain 01:18:44 loss: -0.5774 Lr: 2.29015e-03 +[2025-02-22 13:11:17,981 INFO hook.py line 109 2775932] Train: [60/100][650/800] Data 0.002 (0.003) Batch 0.149 (0.147) Remain 01:18:33 loss: -0.5034 Lr: 2.28413e-03 +[2025-02-22 13:11:25,358 INFO hook.py line 109 2775932] Train: [60/100][700/800] Data 0.002 (0.003) Batch 0.149 (0.147) Remain 01:18:28 loss: -0.5677 Lr: 2.27811e-03 +[2025-02-22 13:11:32,305 INFO hook.py line 109 2775932] Train: [60/100][750/800] Data 0.003 (0.003) Batch 0.140 (0.146) Remain 01:18:04 loss: 0.2591 Lr: 2.27221e-03 +[2025-02-22 13:11:39,479 INFO hook.py line 109 2775932] Train: [60/100][800/800] Data 0.002 (0.004) Batch 0.132 (0.146) Remain 01:17:51 loss: 0.1594 Lr: 2.26620e-03 +[2025-02-22 13:11:39,480 INFO misc.py line 135 2775932] Train result: loss: -0.5380 seg_loss: 0.1818 bias_l1_loss: 0.2219 bias_cosine_loss: -0.9416 +[2025-02-22 13:11:39,480 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:11:46,840 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7975 +[2025-02-22 13:11:47,172 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4432 +[2025-02-22 13:11:47,252 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5523 +[2025-02-22 13:11:47,341 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6246 +[2025-02-22 13:11:47,414 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7144 +[2025-02-22 13:11:47,484 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.6916 +[2025-02-22 13:11:47,829 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5703 +[2025-02-22 13:11:47,861 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5549 +[2025-02-22 13:11:47,984 INFO evaluator.py line 595 2775932] Test: [9/78] Loss 0.0112 +[2025-02-22 13:11:48,049 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0011 +[2025-02-22 13:11:48,336 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0137 +[2025-02-22 13:11:48,474 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.3195 +[2025-02-22 13:11:48,555 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1640 +[2025-02-22 13:11:48,648 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8484 +[2025-02-22 13:11:48,732 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0545 +[2025-02-22 13:11:48,821 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6823 +[2025-02-22 13:11:48,969 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4719 +[2025-02-22 13:11:49,080 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4533 +[2025-02-22 13:11:49,239 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1313 +[2025-02-22 13:11:49,305 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.3186 +[2025-02-22 13:11:49,487 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6732 +[2025-02-22 13:11:49,655 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1962 +[2025-02-22 13:11:49,734 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0461 +[2025-02-22 13:11:49,797 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0154 +[2025-02-22 13:11:49,881 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2389 +[2025-02-22 13:11:49,945 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6765 +[2025-02-22 13:11:50,097 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0430 +[2025-02-22 13:11:50,193 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5481 +[2025-02-22 13:11:50,266 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6370 +[2025-02-22 13:11:50,349 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5906 +[2025-02-22 13:11:51,114 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5627 +[2025-02-22 13:11:51,254 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1531 +[2025-02-22 13:11:51,291 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7432 +[2025-02-22 13:11:51,391 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2131 +[2025-02-22 13:11:51,428 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6700 +[2025-02-22 13:11:51,566 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0530 +[2025-02-22 13:11:51,633 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4653 +[2025-02-22 13:11:51,753 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7315 +[2025-02-22 13:11:51,892 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8030 +[2025-02-22 13:11:52,098 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5869 +[2025-02-22 13:11:52,286 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5509 +[2025-02-22 13:11:52,332 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3587 +[2025-02-22 13:11:52,367 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7550 +[2025-02-22 13:11:52,635 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6801 +[2025-02-22 13:11:52,670 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4584 +[2025-02-22 13:11:52,710 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5889 +[2025-02-22 13:11:52,801 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3387 +[2025-02-22 13:11:52,937 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2417 +[2025-02-22 13:11:53,063 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1503 +[2025-02-22 13:11:53,162 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.1432 +[2025-02-22 13:11:53,246 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3913 +[2025-02-22 13:11:53,382 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3305 +[2025-02-22 13:11:53,423 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7060 +[2025-02-22 13:11:53,533 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2871 +[2025-02-22 13:11:53,628 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8612 +[2025-02-22 13:11:53,684 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7657 +[2025-02-22 13:11:53,830 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1104 +[2025-02-22 13:11:53,875 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5414 +[2025-02-22 13:11:54,170 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3948 +[2025-02-22 13:11:54,280 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0973 +[2025-02-22 13:11:54,374 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6834 +[2025-02-22 13:11:54,445 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.7015 +[2025-02-22 13:11:54,624 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0399 +[2025-02-22 13:11:54,745 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.4029 +[2025-02-22 13:11:54,825 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1959 +[2025-02-22 13:11:54,983 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1326 +[2025-02-22 13:11:55,191 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6654 +[2025-02-22 13:11:55,318 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.2186 +[2025-02-22 13:11:55,377 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8184 +[2025-02-22 13:11:55,432 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3087 +[2025-02-22 13:11:55,601 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1476 +[2025-02-22 13:11:55,640 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5562 +[2025-02-22 13:11:55,718 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6544 +[2025-02-22 13:11:55,843 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.4402 +[2025-02-22 13:11:56,064 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6498 +[2025-02-22 13:11:56,161 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1374 +[2025-02-22 13:11:56,418 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5704 +[2025-02-22 13:11:56,525 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5369 +[2025-02-22 13:12:08,972 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:12:08,972 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:12:08,972 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] cabinet : 0.2209 0.4295 0.6599 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] bed : 0.3695 0.7157 0.8303 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] chair : 0.7508 0.9078 0.9460 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] sofa : 0.3317 0.5450 0.8148 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] table : 0.4282 0.6425 0.7612 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] door : 0.2374 0.4587 0.5989 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] window : 0.2380 0.4302 0.6011 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] bookshelf : 0.2331 0.5156 0.8086 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] picture : 0.3514 0.5075 0.5911 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] counter : 0.0431 0.1679 0.5630 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] desk : 0.1165 0.3093 0.7140 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] curtain : 0.2775 0.4653 0.5810 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] refridgerator : 0.3648 0.4836 0.6026 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] shower curtain : 0.4754 0.6533 0.7110 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] toilet : 0.8325 0.9757 0.9924 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] sink : 0.3015 0.6037 0.8946 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] bathtub : 0.5683 0.7334 0.8414 +[2025-02-22 13:12:08,972 INFO evaluator.py line 547 2775932] otherfurniture : 0.4205 0.6063 0.7044 +[2025-02-22 13:12:08,972 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:12:08,972 INFO evaluator.py line 554 2775932] average : 0.3645 0.5639 0.7342 +[2025-02-22 13:12:08,972 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:12:08,973 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:12:09,012 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5639 +[2025-02-22 13:12:09,019 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:12:09,019 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:12:18,001 INFO hook.py line 109 2775932] Train: [61/100][50/800] Data 0.003 (0.003) Batch 0.147 (0.145) Remain 01:17:28 loss: -0.5230 Lr: 2.26019e-03 +[2025-02-22 13:12:25,103 INFO hook.py line 109 2775932] Train: [61/100][100/800] Data 0.003 (0.003) Batch 0.159 (0.144) Remain 01:16:24 loss: -0.5157 Lr: 2.25418e-03 +[2025-02-22 13:12:32,147 INFO hook.py line 109 2775932] Train: [61/100][150/800] Data 0.003 (0.003) Batch 0.177 (0.143) Remain 01:15:46 loss: -0.4302 Lr: 2.24818e-03 +[2025-02-22 13:12:39,339 INFO hook.py line 109 2775932] Train: [61/100][200/800] Data 0.003 (0.003) Batch 0.151 (0.143) Remain 01:15:48 loss: -0.3705 Lr: 2.24218e-03 +[2025-02-22 13:12:46,511 INFO hook.py line 109 2775932] Train: [61/100][250/800] Data 0.003 (0.004) Batch 0.125 (0.143) Remain 01:15:43 loss: -0.5243 Lr: 2.23618e-03 +[2025-02-22 13:12:53,816 INFO hook.py line 109 2775932] Train: [61/100][300/800] Data 0.003 (0.004) Batch 0.159 (0.144) Remain 01:15:52 loss: -0.5139 Lr: 2.23019e-03 +[2025-02-22 13:13:00,920 INFO hook.py line 109 2775932] Train: [61/100][350/800] Data 0.004 (0.004) Batch 0.145 (0.143) Remain 01:15:38 loss: -0.4231 Lr: 2.22420e-03 +[2025-02-22 13:13:08,029 INFO hook.py line 109 2775932] Train: [61/100][400/800] Data 0.002 (0.003) Batch 0.128 (0.143) Remain 01:15:26 loss: -0.5914 Lr: 2.21821e-03 +[2025-02-22 13:13:15,368 INFO hook.py line 109 2775932] Train: [61/100][450/800] Data 0.003 (0.003) Batch 0.123 (0.144) Remain 01:15:31 loss: -0.5547 Lr: 2.21223e-03 +[2025-02-22 13:13:22,653 INFO hook.py line 109 2775932] Train: [61/100][500/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 01:15:31 loss: -0.4929 Lr: 2.20625e-03 +[2025-02-22 13:13:29,752 INFO hook.py line 109 2775932] Train: [61/100][550/800] Data 0.003 (0.003) Batch 0.144 (0.144) Remain 01:15:18 loss: -0.4263 Lr: 2.20027e-03 +[2025-02-22 13:13:37,063 INFO hook.py line 109 2775932] Train: [61/100][600/800] Data 0.003 (0.003) Batch 0.112 (0.144) Remain 01:15:18 loss: -0.6083 Lr: 2.19430e-03 +[2025-02-22 13:13:44,461 INFO hook.py line 109 2775932] Train: [61/100][650/800] Data 0.003 (0.003) Batch 0.146 (0.144) Remain 01:15:20 loss: -0.6178 Lr: 2.18833e-03 +[2025-02-22 13:13:51,845 INFO hook.py line 109 2775932] Train: [61/100][700/800] Data 0.002 (0.003) Batch 0.129 (0.144) Remain 01:15:21 loss: -0.6352 Lr: 2.18236e-03 +[2025-02-22 13:13:59,117 INFO hook.py line 109 2775932] Train: [61/100][750/800] Data 0.003 (0.003) Batch 0.167 (0.145) Remain 01:15:16 loss: -0.5919 Lr: 2.17640e-03 +[2025-02-22 13:14:06,010 INFO hook.py line 109 2775932] Train: [61/100][800/800] Data 0.002 (0.003) Batch 0.110 (0.144) Remain 01:14:55 loss: -0.4751 Lr: 2.17044e-03 +[2025-02-22 13:14:06,011 INFO misc.py line 135 2775932] Train result: loss: -0.5497 seg_loss: 0.1821 bias_l1_loss: 0.2121 bias_cosine_loss: -0.9440 +[2025-02-22 13:14:06,012 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:14:13,197 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7902 +[2025-02-22 13:14:14,011 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4529 +[2025-02-22 13:14:14,093 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5650 +[2025-02-22 13:14:14,164 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.4867 +[2025-02-22 13:14:14,241 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6287 +[2025-02-22 13:14:14,310 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.4432 +[2025-02-22 13:14:14,597 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5432 +[2025-02-22 13:14:14,630 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4959 +[2025-02-22 13:14:14,768 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1047 +[2025-02-22 13:14:14,833 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0821 +[2025-02-22 13:14:15,096 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0326 +[2025-02-22 13:14:15,224 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1210 +[2025-02-22 13:14:15,305 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1268 +[2025-02-22 13:14:15,429 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0336 +[2025-02-22 13:14:15,536 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3753 +[2025-02-22 13:14:15,632 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6179 +[2025-02-22 13:14:15,791 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4975 +[2025-02-22 13:14:15,912 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.2853 +[2025-02-22 13:14:16,103 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1333 +[2025-02-22 13:14:16,198 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1221 +[2025-02-22 13:14:16,427 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5689 +[2025-02-22 13:14:16,670 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2700 +[2025-02-22 13:14:16,777 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1135 +[2025-02-22 13:14:16,869 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0102 +[2025-02-22 13:14:16,978 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1260 +[2025-02-22 13:14:17,046 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6084 +[2025-02-22 13:14:17,220 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.1777 +[2025-02-22 13:14:17,347 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4406 +[2025-02-22 13:14:17,447 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5617 +[2025-02-22 13:14:17,537 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6821 +[2025-02-22 13:14:18,497 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4563 +[2025-02-22 13:14:18,628 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0021 +[2025-02-22 13:14:18,680 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7255 +[2025-02-22 13:14:18,800 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3848 +[2025-02-22 13:14:18,846 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5560 +[2025-02-22 13:14:18,980 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8519 +[2025-02-22 13:14:19,053 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7226 +[2025-02-22 13:14:19,209 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6995 +[2025-02-22 13:14:19,428 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1993 +[2025-02-22 13:14:19,670 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6352 +[2025-02-22 13:14:19,880 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6525 +[2025-02-22 13:14:19,948 INFO evaluator.py line 595 2775932] Test: [42/78] Loss 0.1093 +[2025-02-22 13:14:20,119 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7845 +[2025-02-22 13:14:20,430 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.5931 +[2025-02-22 13:14:20,481 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5954 +[2025-02-22 13:14:20,532 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4208 +[2025-02-22 13:14:20,631 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1711 +[2025-02-22 13:14:20,767 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1848 +[2025-02-22 13:14:20,902 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0741 +[2025-02-22 13:14:21,006 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.1197 +[2025-02-22 13:14:21,099 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.0814 +[2025-02-22 13:14:21,263 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3272 +[2025-02-22 13:14:21,310 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6615 +[2025-02-22 13:14:21,453 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.5478 +[2025-02-22 13:14:21,595 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8379 +[2025-02-22 13:14:21,669 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6933 +[2025-02-22 13:14:21,840 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2501 +[2025-02-22 13:14:21,891 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.2455 +[2025-02-22 13:14:22,139 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2791 +[2025-02-22 13:14:22,259 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.3710 +[2025-02-22 13:14:22,342 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6431 +[2025-02-22 13:14:22,410 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6307 +[2025-02-22 13:14:22,584 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1592 +[2025-02-22 13:14:22,706 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.7536 +[2025-02-22 13:14:22,791 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1100 +[2025-02-22 13:14:22,938 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1387 +[2025-02-22 13:14:23,144 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5153 +[2025-02-22 13:14:23,262 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.1218 +[2025-02-22 13:14:23,321 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7324 +[2025-02-22 13:14:23,380 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1449 +[2025-02-22 13:14:23,571 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1485 +[2025-02-22 13:14:23,611 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4853 +[2025-02-22 13:14:23,665 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7461 +[2025-02-22 13:14:23,817 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6411 +[2025-02-22 13:14:24,045 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5884 +[2025-02-22 13:14:24,134 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1080 +[2025-02-22 13:14:24,313 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4652 +[2025-02-22 13:14:24,418 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6046 +[2025-02-22 13:14:36,581 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:14:36,581 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:14:36,581 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] cabinet : 0.2494 0.4763 0.7060 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] bed : 0.3423 0.6546 0.7871 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] chair : 0.7413 0.8937 0.9436 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] sofa : 0.3315 0.5479 0.8051 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] table : 0.3328 0.5423 0.6996 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] door : 0.2770 0.5052 0.6512 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] window : 0.2548 0.4418 0.6487 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] bookshelf : 0.1942 0.4617 0.6457 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] picture : 0.3203 0.4951 0.5994 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] counter : 0.0301 0.1151 0.5822 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] desk : 0.1035 0.3088 0.6865 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] curtain : 0.2683 0.4724 0.6988 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] refridgerator : 0.3045 0.3750 0.4229 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] shower curtain : 0.4814 0.6441 0.8085 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] toilet : 0.8873 1.0000 1.0000 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] sink : 0.3563 0.6486 0.8507 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] bathtub : 0.6912 0.8664 0.8686 +[2025-02-22 13:14:36,581 INFO evaluator.py line 547 2775932] otherfurniture : 0.3990 0.5915 0.7033 +[2025-02-22 13:14:36,581 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:14:36,581 INFO evaluator.py line 554 2775932] average : 0.3647 0.5578 0.7282 +[2025-02-22 13:14:36,581 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:14:36,582 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:14:36,622 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:14:36,627 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:14:45,243 INFO hook.py line 109 2775932] Train: [62/100][50/800] Data 0.002 (0.003) Batch 0.155 (0.147) Remain 01:16:25 loss: -0.5570 Lr: 2.16448e-03 +[2025-02-22 13:14:52,611 INFO hook.py line 109 2775932] Train: [62/100][100/800] Data 0.002 (0.003) Batch 0.147 (0.147) Remain 01:16:20 loss: -0.6545 Lr: 2.15853e-03 +[2025-02-22 13:14:59,937 INFO hook.py line 109 2775932] Train: [62/100][150/800] Data 0.004 (0.004) Batch 0.145 (0.147) Remain 01:16:05 loss: -0.3823 Lr: 2.15258e-03 +[2025-02-22 13:15:07,421 INFO hook.py line 109 2775932] Train: [62/100][200/800] Data 0.003 (0.004) Batch 0.135 (0.148) Remain 01:16:18 loss: -0.6733 Lr: 2.14664e-03 +[2025-02-22 13:15:14,639 INFO hook.py line 109 2775932] Train: [62/100][250/800] Data 0.003 (0.004) Batch 0.133 (0.147) Remain 01:15:50 loss: -0.6331 Lr: 2.14069e-03 +[2025-02-22 13:15:22,249 INFO hook.py line 109 2775932] Train: [62/100][300/800] Data 0.003 (0.004) Batch 0.151 (0.148) Remain 01:16:09 loss: -0.4492 Lr: 2.13476e-03 +[2025-02-22 13:15:29,670 INFO hook.py line 109 2775932] Train: [62/100][350/800] Data 0.008 (0.004) Batch 0.162 (0.148) Remain 01:16:04 loss: -0.6452 Lr: 2.12882e-03 +[2025-02-22 13:15:36,909 INFO hook.py line 109 2775932] Train: [62/100][400/800] Data 0.003 (0.004) Batch 0.137 (0.148) Remain 01:15:45 loss: -0.6701 Lr: 2.12289e-03 +[2025-02-22 13:15:44,258 INFO hook.py line 109 2775932] Train: [62/100][450/800] Data 0.003 (0.004) Batch 0.127 (0.148) Remain 01:15:35 loss: -0.6835 Lr: 2.11696e-03 +[2025-02-22 13:15:51,268 INFO hook.py line 109 2775932] Train: [62/100][500/800] Data 0.002 (0.004) Batch 0.136 (0.147) Remain 01:15:05 loss: -0.5380 Lr: 2.11104e-03 +[2025-02-22 13:15:58,145 INFO hook.py line 109 2775932] Train: [62/100][550/800] Data 0.004 (0.004) Batch 0.127 (0.146) Remain 01:14:32 loss: -0.5082 Lr: 2.10512e-03 +[2025-02-22 13:16:05,251 INFO hook.py line 109 2775932] Train: [62/100][600/800] Data 0.004 (0.004) Batch 0.154 (0.146) Remain 01:14:15 loss: -0.6162 Lr: 2.09921e-03 +[2025-02-22 13:16:12,621 INFO hook.py line 109 2775932] Train: [62/100][650/800] Data 0.004 (0.003) Batch 0.151 (0.146) Remain 01:14:12 loss: -0.7614 Lr: 2.09329e-03 +[2025-02-22 13:16:19,745 INFO hook.py line 109 2775932] Train: [62/100][700/800] Data 0.002 (0.003) Batch 0.128 (0.146) Remain 01:13:58 loss: -0.3669 Lr: 2.08739e-03 +[2025-02-22 13:16:26,728 INFO hook.py line 109 2775932] Train: [62/100][750/800] Data 0.003 (0.003) Batch 0.125 (0.145) Remain 01:13:38 loss: -0.6330 Lr: 2.08148e-03 +[2025-02-22 13:16:33,633 INFO hook.py line 109 2775932] Train: [62/100][800/800] Data 0.002 (0.003) Batch 0.119 (0.145) Remain 01:13:18 loss: -0.5590 Lr: 2.07558e-03 +[2025-02-22 13:16:33,634 INFO misc.py line 135 2775932] Train result: loss: -0.5513 seg_loss: 0.1745 bias_l1_loss: 0.2176 bias_cosine_loss: -0.9434 +[2025-02-22 13:16:33,634 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:16:40,656 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8074 +[2025-02-22 13:16:41,216 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4369 +[2025-02-22 13:16:41,319 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.4678 +[2025-02-22 13:16:41,407 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5194 +[2025-02-22 13:16:41,466 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6911 +[2025-02-22 13:16:41,528 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8947 +[2025-02-22 13:16:41,831 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5740 +[2025-02-22 13:16:41,861 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5536 +[2025-02-22 13:16:42,005 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.0599 +[2025-02-22 13:16:42,062 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.2117 +[2025-02-22 13:16:42,305 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1487 +[2025-02-22 13:16:42,449 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1546 +[2025-02-22 13:16:42,535 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2165 +[2025-02-22 13:16:42,620 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0895 +[2025-02-22 13:16:42,718 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1071 +[2025-02-22 13:16:42,808 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6257 +[2025-02-22 13:16:42,964 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6220 +[2025-02-22 13:16:43,062 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3518 +[2025-02-22 13:16:43,236 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0875 +[2025-02-22 13:16:43,301 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1131 +[2025-02-22 13:16:43,480 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6022 +[2025-02-22 13:16:43,644 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1258 +[2025-02-22 13:16:43,723 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0172 +[2025-02-22 13:16:43,788 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0283 +[2025-02-22 13:16:43,862 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1788 +[2025-02-22 13:16:43,923 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4307 +[2025-02-22 13:16:44,052 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2513 +[2025-02-22 13:16:44,147 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5604 +[2025-02-22 13:16:44,225 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.5858 +[2025-02-22 13:16:44,297 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6832 +[2025-02-22 13:16:45,092 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5052 +[2025-02-22 13:16:45,244 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2070 +[2025-02-22 13:16:45,305 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7160 +[2025-02-22 13:16:45,400 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3166 +[2025-02-22 13:16:45,436 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6933 +[2025-02-22 13:16:45,566 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8623 +[2025-02-22 13:16:45,633 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7468 +[2025-02-22 13:16:45,759 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6898 +[2025-02-22 13:16:45,917 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7303 +[2025-02-22 13:16:46,129 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8239 +[2025-02-22 13:16:46,294 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3801 +[2025-02-22 13:16:46,349 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.1342 +[2025-02-22 13:16:46,397 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7876 +[2025-02-22 13:16:46,684 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6811 +[2025-02-22 13:16:46,729 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4851 +[2025-02-22 13:16:46,782 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4605 +[2025-02-22 13:16:46,897 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2424 +[2025-02-22 13:16:47,027 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1073 +[2025-02-22 13:16:47,143 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0726 +[2025-02-22 13:16:47,229 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2282 +[2025-02-22 13:16:47,309 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2445 +[2025-02-22 13:16:47,441 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1465 +[2025-02-22 13:16:47,480 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7043 +[2025-02-22 13:16:47,588 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.0130 +[2025-02-22 13:16:47,677 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8431 +[2025-02-22 13:16:47,718 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7896 +[2025-02-22 13:16:47,865 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0865 +[2025-02-22 13:16:47,925 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3681 +[2025-02-22 13:16:48,130 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2859 +[2025-02-22 13:16:48,235 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1254 +[2025-02-22 13:16:48,305 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6337 +[2025-02-22 13:16:48,355 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.2593 +[2025-02-22 13:16:48,525 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0889 +[2025-02-22 13:16:48,624 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.3454 +[2025-02-22 13:16:48,699 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2017 +[2025-02-22 13:16:48,842 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0959 +[2025-02-22 13:16:49,022 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5979 +[2025-02-22 13:16:49,134 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0138 +[2025-02-22 13:16:49,185 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6991 +[2025-02-22 13:16:49,230 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1404 +[2025-02-22 13:16:49,377 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2493 +[2025-02-22 13:16:49,421 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6034 +[2025-02-22 13:16:49,489 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7181 +[2025-02-22 13:16:49,603 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 0.8899 +[2025-02-22 13:16:49,803 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5864 +[2025-02-22 13:16:49,892 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0882 +[2025-02-22 13:16:50,045 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5925 +[2025-02-22 13:16:50,138 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5144 +[2025-02-22 13:17:03,808 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:17:03,809 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:17:03,809 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] cabinet : 0.2844 0.5148 0.7042 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] bed : 0.3265 0.6477 0.7774 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] chair : 0.7318 0.8882 0.9280 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] sofa : 0.3204 0.5580 0.7906 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] table : 0.3435 0.5863 0.7461 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] door : 0.2308 0.4441 0.5831 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] window : 0.2256 0.4092 0.6443 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] bookshelf : 0.2184 0.4934 0.7077 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] picture : 0.3270 0.4932 0.5317 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] counter : 0.0383 0.1454 0.5646 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] desk : 0.0639 0.2522 0.7901 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] curtain : 0.2855 0.4767 0.5640 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] refridgerator : 0.2476 0.2963 0.4022 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] shower curtain : 0.4861 0.6162 0.6184 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] toilet : 0.8459 0.9640 0.9960 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] sink : 0.3393 0.6043 0.8713 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] bathtub : 0.6767 0.8065 0.8710 +[2025-02-22 13:17:03,809 INFO evaluator.py line 547 2775932] otherfurniture : 0.3479 0.5184 0.6618 +[2025-02-22 13:17:03,809 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:17:03,809 INFO evaluator.py line 554 2775932] average : 0.3522 0.5397 0.7085 +[2025-02-22 13:17:03,809 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:17:03,809 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:17:03,848 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:17:03,853 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:17:12,528 INFO hook.py line 109 2775932] Train: [63/100][50/800] Data 0.003 (0.005) Batch 0.136 (0.148) Remain 01:14:56 loss: -0.4641 Lr: 2.06969e-03 +[2025-02-22 13:17:19,746 INFO hook.py line 109 2775932] Train: [63/100][100/800] Data 0.003 (0.004) Batch 0.146 (0.146) Remain 01:13:50 loss: -0.6462 Lr: 2.06379e-03 +[2025-02-22 13:17:26,744 INFO hook.py line 109 2775932] Train: [63/100][150/800] Data 0.003 (0.004) Batch 0.153 (0.144) Remain 01:12:38 loss: -0.5138 Lr: 2.05791e-03 +[2025-02-22 13:17:33,644 INFO hook.py line 109 2775932] Train: [63/100][200/800] Data 0.002 (0.003) Batch 0.152 (0.143) Remain 01:11:44 loss: -0.6925 Lr: 2.05202e-03 +[2025-02-22 13:17:40,831 INFO hook.py line 109 2775932] Train: [63/100][250/800] Data 0.003 (0.003) Batch 0.140 (0.143) Remain 01:11:44 loss: -0.5341 Lr: 2.04614e-03 +[2025-02-22 13:17:47,876 INFO hook.py line 109 2775932] Train: [63/100][300/800] Data 0.002 (0.003) Batch 0.137 (0.142) Remain 01:11:28 loss: -0.6289 Lr: 2.04027e-03 +[2025-02-22 13:17:55,153 INFO hook.py line 109 2775932] Train: [63/100][350/800] Data 0.003 (0.004) Batch 0.131 (0.143) Remain 01:11:34 loss: -0.5482 Lr: 2.03440e-03 +[2025-02-22 13:18:02,483 INFO hook.py line 109 2775932] Train: [63/100][400/800] Data 0.003 (0.004) Batch 0.155 (0.143) Remain 01:11:41 loss: -0.5055 Lr: 2.02853e-03 +[2025-02-22 13:18:09,587 INFO hook.py line 109 2775932] Train: [63/100][450/800] Data 0.002 (0.004) Batch 0.137 (0.143) Remain 01:11:29 loss: -0.6415 Lr: 2.02278e-03 +[2025-02-22 13:18:16,771 INFO hook.py line 109 2775932] Train: [63/100][500/800] Data 0.003 (0.004) Batch 0.133 (0.143) Remain 01:11:23 loss: -0.6606 Lr: 2.01692e-03 +[2025-02-22 13:18:23,858 INFO hook.py line 109 2775932] Train: [63/100][550/800] Data 0.002 (0.004) Batch 0.134 (0.143) Remain 01:11:12 loss: -0.4744 Lr: 2.01107e-03 +[2025-02-22 13:18:31,164 INFO hook.py line 109 2775932] Train: [63/100][600/800] Data 0.005 (0.004) Batch 0.142 (0.143) Remain 01:11:12 loss: -0.6967 Lr: 2.00522e-03 +[2025-02-22 13:18:38,629 INFO hook.py line 109 2775932] Train: [63/100][650/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 01:11:19 loss: -0.6797 Lr: 1.99937e-03 +[2025-02-22 13:18:45,911 INFO hook.py line 109 2775932] Train: [63/100][700/800] Data 0.003 (0.004) Batch 0.133 (0.144) Remain 01:11:15 loss: -0.5592 Lr: 1.99353e-03 +[2025-02-22 13:18:53,121 INFO hook.py line 109 2775932] Train: [63/100][750/800] Data 0.002 (0.003) Batch 0.128 (0.144) Remain 01:11:09 loss: -0.6518 Lr: 1.98769e-03 +[2025-02-22 13:19:00,114 INFO hook.py line 109 2775932] Train: [63/100][800/800] Data 0.002 (0.003) Batch 0.113 (0.144) Remain 01:10:54 loss: -0.3949 Lr: 1.98185e-03 +[2025-02-22 13:19:00,115 INFO misc.py line 135 2775932] Train result: loss: -0.5718 seg_loss: 0.1644 bias_l1_loss: 0.2098 bias_cosine_loss: -0.9461 +[2025-02-22 13:19:00,115 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:19:07,439 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8354 +[2025-02-22 13:19:07,853 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5077 +[2025-02-22 13:19:07,952 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5950 +[2025-02-22 13:19:08,061 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5137 +[2025-02-22 13:19:08,124 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6820 +[2025-02-22 13:19:08,206 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7663 +[2025-02-22 13:19:08,512 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5591 +[2025-02-22 13:19:08,547 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5064 +[2025-02-22 13:19:08,685 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3119 +[2025-02-22 13:19:08,748 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.2069 +[2025-02-22 13:19:09,069 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0573 +[2025-02-22 13:19:09,198 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0616 +[2025-02-22 13:19:09,283 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1695 +[2025-02-22 13:19:09,376 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.8052 +[2025-02-22 13:19:09,465 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0128 +[2025-02-22 13:19:09,559 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6505 +[2025-02-22 13:19:09,708 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5905 +[2025-02-22 13:19:09,822 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2860 +[2025-02-22 13:19:09,971 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1014 +[2025-02-22 13:19:10,040 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0382 +[2025-02-22 13:19:10,216 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.5641 +[2025-02-22 13:19:10,383 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1173 +[2025-02-22 13:19:10,469 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0742 +[2025-02-22 13:19:10,528 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1454 +[2025-02-22 13:19:10,611 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4749 +[2025-02-22 13:19:10,675 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5111 +[2025-02-22 13:19:10,817 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0780 +[2025-02-22 13:19:10,913 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5628 +[2025-02-22 13:19:10,984 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6781 +[2025-02-22 13:19:11,059 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6864 +[2025-02-22 13:19:11,873 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4507 +[2025-02-22 13:19:11,991 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0799 +[2025-02-22 13:19:12,032 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7008 +[2025-02-22 13:19:12,138 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4902 +[2025-02-22 13:19:12,179 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.3181 +[2025-02-22 13:19:12,300 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.1874 +[2025-02-22 13:19:12,362 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7115 +[2025-02-22 13:19:12,497 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6335 +[2025-02-22 13:19:12,678 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.9633 +[2025-02-22 13:19:12,926 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7744 +[2025-02-22 13:19:13,107 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4376 +[2025-02-22 13:19:13,167 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2559 +[2025-02-22 13:19:13,225 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8019 +[2025-02-22 13:19:13,478 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6439 +[2025-02-22 13:19:13,521 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4558 +[2025-02-22 13:19:13,568 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4638 +[2025-02-22 13:19:13,679 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3898 +[2025-02-22 13:19:13,826 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2300 +[2025-02-22 13:19:13,949 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3159 +[2025-02-22 13:19:14,042 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2988 +[2025-02-22 13:19:14,138 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1360 +[2025-02-22 13:19:14,289 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.2995 +[2025-02-22 13:19:14,334 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4327 +[2025-02-22 13:19:14,446 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.4667 +[2025-02-22 13:19:14,546 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.7874 +[2025-02-22 13:19:14,597 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7831 +[2025-02-22 13:19:14,744 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2091 +[2025-02-22 13:19:14,786 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4948 +[2025-02-22 13:19:15,034 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.2737 +[2025-02-22 13:19:15,133 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0356 +[2025-02-22 13:19:15,212 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6600 +[2025-02-22 13:19:15,268 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4193 +[2025-02-22 13:19:15,410 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1950 +[2025-02-22 13:19:15,518 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.1018 +[2025-02-22 13:19:15,591 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0901 +[2025-02-22 13:19:15,745 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3583 +[2025-02-22 13:19:15,943 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6728 +[2025-02-22 13:19:16,053 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2081 +[2025-02-22 13:19:16,110 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7345 +[2025-02-22 13:19:16,162 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0133 +[2025-02-22 13:19:16,342 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1391 +[2025-02-22 13:19:16,382 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6238 +[2025-02-22 13:19:16,436 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8199 +[2025-02-22 13:19:16,551 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.0484 +[2025-02-22 13:19:16,790 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3619 +[2025-02-22 13:19:16,899 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1317 +[2025-02-22 13:19:17,082 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6718 +[2025-02-22 13:19:17,185 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5463 +[2025-02-22 13:19:30,902 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:19:30,902 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:19:30,902 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] cabinet : 0.2774 0.5320 0.7160 +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] bed : 0.3820 0.7117 0.8511 +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] chair : 0.7462 0.9067 0.9488 +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] sofa : 0.3340 0.5606 0.7962 +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] table : 0.4027 0.6126 0.7335 +[2025-02-22 13:19:30,902 INFO evaluator.py line 547 2775932] door : 0.2210 0.4225 0.5658 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] window : 0.2513 0.4379 0.6346 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] bookshelf : 0.2436 0.5856 0.7727 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] picture : 0.3063 0.4414 0.5019 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] counter : 0.0285 0.0852 0.4719 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] desk : 0.0928 0.3191 0.7690 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] curtain : 0.2906 0.4971 0.6732 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] refridgerator : 0.3095 0.4472 0.4795 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] shower curtain : 0.4453 0.6134 0.7574 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] toilet : 0.8243 0.9818 0.9988 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] sink : 0.3463 0.6234 0.8822 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] bathtub : 0.6623 0.8029 0.8698 +[2025-02-22 13:19:30,903 INFO evaluator.py line 547 2775932] otherfurniture : 0.3806 0.5595 0.6754 +[2025-02-22 13:19:30,903 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:19:30,903 INFO evaluator.py line 554 2775932] average : 0.3636 0.5634 0.7277 +[2025-02-22 13:19:30,903 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:19:30,903 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:19:30,938 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:19:30,944 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:19:39,363 INFO hook.py line 109 2775932] Train: [64/100][50/800] Data 0.003 (0.003) Batch 0.131 (0.144) Remain 01:10:54 loss: -0.5279 Lr: 1.97603e-03 +[2025-02-22 13:19:46,604 INFO hook.py line 109 2775932] Train: [64/100][100/800] Data 0.003 (0.003) Batch 0.143 (0.144) Remain 01:10:59 loss: -0.5261 Lr: 1.97020e-03 +[2025-02-22 13:19:53,803 INFO hook.py line 109 2775932] Train: [64/100][150/800] Data 0.002 (0.003) Batch 0.151 (0.144) Remain 01:10:48 loss: -0.6447 Lr: 1.96438e-03 +[2025-02-22 13:20:01,112 INFO hook.py line 109 2775932] Train: [64/100][200/800] Data 0.003 (0.004) Batch 0.153 (0.145) Remain 01:10:55 loss: -0.6176 Lr: 1.95856e-03 +[2025-02-22 13:20:08,363 INFO hook.py line 109 2775932] Train: [64/100][250/800] Data 0.003 (0.004) Batch 0.139 (0.145) Remain 01:10:49 loss: -0.6387 Lr: 1.95275e-03 +[2025-02-22 13:20:15,524 INFO hook.py line 109 2775932] Train: [64/100][300/800] Data 0.003 (0.004) Batch 0.150 (0.145) Remain 01:10:34 loss: -0.6438 Lr: 1.94694e-03 +[2025-02-22 13:20:22,786 INFO hook.py line 109 2775932] Train: [64/100][350/800] Data 0.003 (0.003) Batch 0.146 (0.145) Remain 01:10:30 loss: -0.5713 Lr: 1.94114e-03 +[2025-02-22 13:20:30,096 INFO hook.py line 109 2775932] Train: [64/100][400/800] Data 0.003 (0.004) Batch 0.142 (0.145) Remain 01:10:28 loss: -0.4275 Lr: 1.93534e-03 +[2025-02-22 13:20:37,328 INFO hook.py line 109 2775932] Train: [64/100][450/800] Data 0.003 (0.004) Batch 0.129 (0.145) Remain 01:10:21 loss: -0.5067 Lr: 1.92955e-03 +[2025-02-22 13:20:44,591 INFO hook.py line 109 2775932] Train: [64/100][500/800] Data 0.003 (0.003) Batch 0.145 (0.145) Remain 01:10:15 loss: -0.6379 Lr: 1.92376e-03 +[2025-02-22 13:20:51,752 INFO hook.py line 109 2775932] Train: [64/100][550/800] Data 0.003 (0.004) Batch 0.152 (0.145) Remain 01:10:03 loss: -0.6533 Lr: 1.91798e-03 +[2025-02-22 13:20:59,080 INFO hook.py line 109 2775932] Train: [64/100][600/800] Data 0.003 (0.004) Batch 0.154 (0.145) Remain 01:10:00 loss: -0.6668 Lr: 1.91220e-03 +[2025-02-22 13:21:06,512 INFO hook.py line 109 2775932] Train: [64/100][650/800] Data 0.003 (0.004) Batch 0.154 (0.145) Remain 01:10:02 loss: -0.6851 Lr: 1.90642e-03 +[2025-02-22 13:21:13,696 INFO hook.py line 109 2775932] Train: [64/100][700/800] Data 0.003 (0.004) Batch 0.148 (0.145) Remain 01:09:51 loss: -0.4297 Lr: 1.90065e-03 +[2025-02-22 13:21:20,982 INFO hook.py line 109 2775932] Train: [64/100][750/800] Data 0.002 (0.003) Batch 0.146 (0.145) Remain 01:09:45 loss: -0.5684 Lr: 1.89488e-03 +[2025-02-22 13:21:27,917 INFO hook.py line 109 2775932] Train: [64/100][800/800] Data 0.002 (0.003) Batch 0.111 (0.145) Remain 01:09:27 loss: -0.6111 Lr: 1.88912e-03 +[2025-02-22 13:21:27,919 INFO misc.py line 135 2775932] Train result: loss: -0.5688 seg_loss: 0.1666 bias_l1_loss: 0.2107 bias_cosine_loss: -0.9461 +[2025-02-22 13:21:27,919 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:21:35,425 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7859 +[2025-02-22 13:21:36,246 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4964 +[2025-02-22 13:21:36,315 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5361 +[2025-02-22 13:21:36,409 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5593 +[2025-02-22 13:21:36,470 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7425 +[2025-02-22 13:21:36,530 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7781 +[2025-02-22 13:21:36,838 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5272 +[2025-02-22 13:21:36,869 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4883 +[2025-02-22 13:21:37,024 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2575 +[2025-02-22 13:21:37,091 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0025 +[2025-02-22 13:21:37,354 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1560 +[2025-02-22 13:21:37,474 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0702 +[2025-02-22 13:21:37,559 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1726 +[2025-02-22 13:21:37,666 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.4619 +[2025-02-22 13:21:37,758 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3179 +[2025-02-22 13:21:37,828 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5695 +[2025-02-22 13:21:37,978 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5033 +[2025-02-22 13:21:38,092 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3545 +[2025-02-22 13:21:38,268 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2039 +[2025-02-22 13:21:38,366 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.3253 +[2025-02-22 13:21:38,571 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6585 +[2025-02-22 13:21:38,794 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1526 +[2025-02-22 13:21:38,912 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1667 +[2025-02-22 13:21:38,974 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0932 +[2025-02-22 13:21:39,072 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2381 +[2025-02-22 13:21:39,135 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4842 +[2025-02-22 13:21:39,288 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0192 +[2025-02-22 13:21:39,395 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6643 +[2025-02-22 13:21:39,476 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6902 +[2025-02-22 13:21:39,555 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7097 +[2025-02-22 13:21:40,384 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5041 +[2025-02-22 13:21:40,517 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2158 +[2025-02-22 13:21:40,555 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7324 +[2025-02-22 13:21:40,649 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1770 +[2025-02-22 13:21:40,685 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5459 +[2025-02-22 13:21:40,795 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8834 +[2025-02-22 13:21:40,867 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6027 +[2025-02-22 13:21:40,993 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7481 +[2025-02-22 13:21:41,145 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4212 +[2025-02-22 13:21:41,362 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7191 +[2025-02-22 13:21:41,545 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4368 +[2025-02-22 13:21:41,604 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2465 +[2025-02-22 13:21:41,649 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7765 +[2025-02-22 13:21:41,910 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6052 +[2025-02-22 13:21:41,957 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4669 +[2025-02-22 13:21:42,006 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4530 +[2025-02-22 13:21:42,115 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1544 +[2025-02-22 13:21:42,290 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.1877 +[2025-02-22 13:21:42,415 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2442 +[2025-02-22 13:21:42,511 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1802 +[2025-02-22 13:21:42,603 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2598 +[2025-02-22 13:21:42,739 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.1912 +[2025-02-22 13:21:42,815 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6731 +[2025-02-22 13:21:42,931 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 0.8808 +[2025-02-22 13:21:43,026 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8206 +[2025-02-22 13:21:43,084 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6790 +[2025-02-22 13:21:43,233 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.3275 +[2025-02-22 13:21:43,289 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5710 +[2025-02-22 13:21:43,539 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4221 +[2025-02-22 13:21:43,638 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0239 +[2025-02-22 13:21:43,714 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5478 +[2025-02-22 13:21:43,763 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5267 +[2025-02-22 13:21:43,911 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0019 +[2025-02-22 13:21:44,007 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.5283 +[2025-02-22 13:21:44,073 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2510 +[2025-02-22 13:21:44,193 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3615 +[2025-02-22 13:21:44,379 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4164 +[2025-02-22 13:21:44,461 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.3726 +[2025-02-22 13:21:44,510 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7449 +[2025-02-22 13:21:44,554 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1865 +[2025-02-22 13:21:44,702 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1924 +[2025-02-22 13:21:44,733 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6167 +[2025-02-22 13:21:44,776 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8054 +[2025-02-22 13:21:44,878 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.0438 +[2025-02-22 13:21:45,085 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6481 +[2025-02-22 13:21:45,163 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1987 +[2025-02-22 13:21:45,315 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5280 +[2025-02-22 13:21:45,404 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6925 +[2025-02-22 13:21:58,104 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:21:58,104 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:21:58,104 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] cabinet : 0.2869 0.4979 0.7178 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] bed : 0.3651 0.6971 0.8916 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] chair : 0.7426 0.8914 0.9312 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] sofa : 0.3427 0.5689 0.8128 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] table : 0.3936 0.6661 0.7674 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] door : 0.2474 0.4785 0.5968 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] window : 0.2537 0.4217 0.6003 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] bookshelf : 0.1450 0.3999 0.6464 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] picture : 0.3117 0.4430 0.5173 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] counter : 0.0462 0.1704 0.5231 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] desk : 0.0950 0.3422 0.7527 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] curtain : 0.2626 0.3786 0.5172 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] refridgerator : 0.3713 0.5005 0.6549 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] shower curtain : 0.4939 0.6321 0.6321 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] toilet : 0.8681 0.9975 0.9975 +[2025-02-22 13:21:58,104 INFO evaluator.py line 547 2775932] sink : 0.3585 0.6506 0.8841 +[2025-02-22 13:21:58,105 INFO evaluator.py line 547 2775932] bathtub : 0.6203 0.7934 0.8617 +[2025-02-22 13:21:58,105 INFO evaluator.py line 547 2775932] otherfurniture : 0.4022 0.5798 0.6979 +[2025-02-22 13:21:58,105 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:21:58,105 INFO evaluator.py line 554 2775932] average : 0.3670 0.5616 0.7224 +[2025-02-22 13:21:58,105 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:21:58,105 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:21:58,143 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:21:58,150 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:22:06,983 INFO hook.py line 109 2775932] Train: [65/100][50/800] Data 0.005 (0.008) Batch 0.139 (0.148) Remain 01:10:59 loss: -0.5556 Lr: 1.88337e-03 +[2025-02-22 13:22:14,251 INFO hook.py line 109 2775932] Train: [65/100][100/800] Data 0.003 (0.005) Batch 0.139 (0.147) Remain 01:10:10 loss: -0.4336 Lr: 1.87761e-03 +[2025-02-22 13:22:21,510 INFO hook.py line 109 2775932] Train: [65/100][150/800] Data 0.003 (0.005) Batch 0.150 (0.146) Remain 01:09:48 loss: -0.6771 Lr: 1.87187e-03 +[2025-02-22 13:22:28,583 INFO hook.py line 109 2775932] Train: [65/100][200/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 01:09:06 loss: -0.5665 Lr: 1.86613e-03 +[2025-02-22 13:22:35,741 INFO hook.py line 109 2775932] Train: [65/100][250/800] Data 0.003 (0.004) Batch 0.157 (0.145) Remain 01:08:48 loss: -0.2789 Lr: 1.86039e-03 +[2025-02-22 13:22:42,815 INFO hook.py line 109 2775932] Train: [65/100][300/800] Data 0.003 (0.004) Batch 0.129 (0.144) Remain 01:08:26 loss: -0.5579 Lr: 1.85466e-03 +[2025-02-22 13:22:50,135 INFO hook.py line 109 2775932] Train: [65/100][350/800] Data 0.002 (0.004) Batch 0.151 (0.144) Remain 01:08:28 loss: -0.5366 Lr: 1.84893e-03 +[2025-02-22 13:22:57,357 INFO hook.py line 109 2775932] Train: [65/100][400/800] Data 0.003 (0.004) Batch 0.111 (0.144) Remain 01:08:21 loss: -0.7527 Lr: 1.84321e-03 +[2025-02-22 13:23:04,520 INFO hook.py line 109 2775932] Train: [65/100][450/800] Data 0.003 (0.004) Batch 0.157 (0.144) Remain 01:08:10 loss: -0.4454 Lr: 1.83749e-03 +[2025-02-22 13:23:11,644 INFO hook.py line 109 2775932] Train: [65/100][500/800] Data 0.003 (0.004) Batch 0.149 (0.144) Remain 01:07:58 loss: -0.4753 Lr: 1.83178e-03 +[2025-02-22 13:23:18,789 INFO hook.py line 109 2775932] Train: [65/100][550/800] Data 0.003 (0.004) Batch 0.162 (0.144) Remain 01:07:48 loss: -0.6735 Lr: 1.82607e-03 +[2025-02-22 13:23:25,915 INFO hook.py line 109 2775932] Train: [65/100][600/800] Data 0.004 (0.004) Batch 0.128 (0.144) Remain 01:07:37 loss: -0.6313 Lr: 1.82037e-03 +[2025-02-22 13:23:33,189 INFO hook.py line 109 2775932] Train: [65/100][650/800] Data 0.002 (0.004) Batch 0.145 (0.144) Remain 01:07:33 loss: -0.5895 Lr: 1.81467e-03 +[2025-02-22 13:23:40,545 INFO hook.py line 109 2775932] Train: [65/100][700/800] Data 0.003 (0.004) Batch 0.154 (0.144) Remain 01:07:32 loss: -0.5134 Lr: 1.80898e-03 +[2025-02-22 13:23:47,733 INFO hook.py line 109 2775932] Train: [65/100][750/800] Data 0.003 (0.004) Batch 0.158 (0.144) Remain 01:07:24 loss: -0.4956 Lr: 1.80329e-03 +[2025-02-22 13:23:54,720 INFO hook.py line 109 2775932] Train: [65/100][800/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 01:07:09 loss: -0.5861 Lr: 1.79761e-03 +[2025-02-22 13:23:54,721 INFO misc.py line 135 2775932] Train result: loss: -0.5781 seg_loss: 0.1657 bias_l1_loss: 0.2047 bias_cosine_loss: -0.9485 +[2025-02-22 13:23:54,721 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:24:01,802 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8104 +[2025-02-22 13:24:02,541 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.3400 +[2025-02-22 13:24:02,618 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5855 +[2025-02-22 13:24:03,210 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5608 +[2025-02-22 13:24:03,275 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6987 +[2025-02-22 13:24:03,339 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9074 +[2025-02-22 13:24:03,637 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5170 +[2025-02-22 13:24:03,668 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5786 +[2025-02-22 13:24:03,815 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2121 +[2025-02-22 13:24:03,873 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0732 +[2025-02-22 13:24:04,130 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1062 +[2025-02-22 13:24:04,256 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1581 +[2025-02-22 13:24:04,340 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4291 +[2025-02-22 13:24:04,459 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9129 +[2025-02-22 13:24:04,614 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1498 +[2025-02-22 13:24:04,694 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6117 +[2025-02-22 13:24:04,900 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5298 +[2025-02-22 13:24:05,030 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4483 +[2025-02-22 13:24:05,208 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4890 +[2025-02-22 13:24:05,288 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0294 +[2025-02-22 13:24:05,479 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6578 +[2025-02-22 13:24:05,689 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3746 +[2025-02-22 13:24:05,801 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.3126 +[2025-02-22 13:24:05,880 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1964 +[2025-02-22 13:24:05,961 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1634 +[2025-02-22 13:24:06,015 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4108 +[2025-02-22 13:24:06,160 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4168 +[2025-02-22 13:24:06,263 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6367 +[2025-02-22 13:24:06,341 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6756 +[2025-02-22 13:24:06,407 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6360 +[2025-02-22 13:24:07,191 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5181 +[2025-02-22 13:24:07,311 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7572 +[2025-02-22 13:24:07,356 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6806 +[2025-02-22 13:24:07,454 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3127 +[2025-02-22 13:24:07,493 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6345 +[2025-02-22 13:24:07,606 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9830 +[2025-02-22 13:24:07,676 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6427 +[2025-02-22 13:24:07,807 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7149 +[2025-02-22 13:24:07,970 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5603 +[2025-02-22 13:24:08,203 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7506 +[2025-02-22 13:24:08,359 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5111 +[2025-02-22 13:24:08,412 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2871 +[2025-02-22 13:24:08,465 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7326 +[2025-02-22 13:24:08,735 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6999 +[2025-02-22 13:24:08,776 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4983 +[2025-02-22 13:24:08,820 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.6182 +[2025-02-22 13:24:08,939 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7520 +[2025-02-22 13:24:09,091 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3513 +[2025-02-22 13:24:09,205 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1727 +[2025-02-22 13:24:09,309 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0146 +[2025-02-22 13:24:09,401 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2672 +[2025-02-22 13:24:09,564 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3612 +[2025-02-22 13:24:09,616 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7103 +[2025-02-22 13:24:09,734 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.6760 +[2025-02-22 13:24:09,835 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8650 +[2025-02-22 13:24:09,881 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7933 +[2025-02-22 13:24:10,031 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0290 +[2025-02-22 13:24:10,096 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4899 +[2025-02-22 13:24:10,352 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3254 +[2025-02-22 13:24:10,460 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1213 +[2025-02-22 13:24:10,535 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5738 +[2025-02-22 13:24:10,595 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5673 +[2025-02-22 13:24:10,772 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0940 +[2025-02-22 13:24:10,882 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.1891 +[2025-02-22 13:24:10,969 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.1473 +[2025-02-22 13:24:11,112 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0195 +[2025-02-22 13:24:11,318 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6925 +[2025-02-22 13:24:11,426 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.2302 +[2025-02-22 13:24:11,506 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7373 +[2025-02-22 13:24:11,579 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0479 +[2025-02-22 13:24:11,775 INFO evaluator.py line 595 2775932] Test: [71/78] Loss 0.2646 +[2025-02-22 13:24:11,813 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5268 +[2025-02-22 13:24:11,869 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8166 +[2025-02-22 13:24:11,986 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5748 +[2025-02-22 13:24:12,214 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6170 +[2025-02-22 13:24:12,296 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2376 +[2025-02-22 13:24:12,484 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.3413 +[2025-02-22 13:24:12,596 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.4329 +[2025-02-22 13:24:25,009 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:24:25,009 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:24:25,009 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] cabinet : 0.2189 0.4117 0.6415 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] bed : 0.3541 0.7012 0.8659 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] chair : 0.7271 0.8820 0.9246 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] sofa : 0.3378 0.5250 0.7611 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] table : 0.4225 0.6463 0.7548 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] door : 0.2785 0.4994 0.6303 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] window : 0.2219 0.3980 0.6028 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] bookshelf : 0.2717 0.5490 0.7532 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] picture : 0.3271 0.4846 0.5990 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] counter : 0.0504 0.1833 0.6532 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] desk : 0.1001 0.2803 0.6423 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] curtain : 0.2956 0.4931 0.6661 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] refridgerator : 0.3465 0.4379 0.4531 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] shower curtain : 0.5138 0.6645 0.7676 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] toilet : 0.8893 1.0000 1.0000 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] sink : 0.3205 0.5890 0.8899 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] bathtub : 0.5284 0.6832 0.8518 +[2025-02-22 13:24:25,009 INFO evaluator.py line 547 2775932] otherfurniture : 0.4034 0.5772 0.6889 +[2025-02-22 13:24:25,009 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:24:25,009 INFO evaluator.py line 554 2775932] average : 0.3671 0.5559 0.7303 +[2025-02-22 13:24:25,009 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:24:25,010 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:24:25,049 INFO misc.py line 164 2775932] Currently Best AP50: 0.5639 +[2025-02-22 13:24:25,055 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:24:33,808 INFO hook.py line 109 2775932] Train: [66/100][50/800] Data 0.003 (0.005) Batch 0.174 (0.151) Remain 01:10:23 loss: -0.6321 Lr: 1.79193e-03 +[2025-02-22 13:24:41,047 INFO hook.py line 109 2775932] Train: [66/100][100/800] Data 0.004 (0.004) Batch 0.174 (0.148) Remain 01:08:45 loss: -0.6592 Lr: 1.78626e-03 +[2025-02-22 13:24:48,115 INFO hook.py line 109 2775932] Train: [66/100][150/800] Data 0.005 (0.004) Batch 0.146 (0.146) Remain 01:07:35 loss: -0.3016 Lr: 1.78059e-03 +[2025-02-22 13:24:55,350 INFO hook.py line 109 2775932] Train: [66/100][200/800] Data 0.004 (0.003) Batch 0.130 (0.145) Remain 01:07:21 loss: -0.5664 Lr: 1.77493e-03 +[2025-02-22 13:25:02,422 INFO hook.py line 109 2775932] Train: [66/100][250/800] Data 0.003 (0.004) Batch 0.119 (0.145) Remain 01:06:52 loss: -0.5857 Lr: 1.76938e-03 +[2025-02-22 13:25:09,408 INFO hook.py line 109 2775932] Train: [66/100][300/800] Data 0.003 (0.004) Batch 0.140 (0.144) Remain 01:06:22 loss: -0.5815 Lr: 1.76373e-03 +[2025-02-22 13:25:16,645 INFO hook.py line 109 2775932] Train: [66/100][350/800] Data 0.003 (0.004) Batch 0.164 (0.144) Remain 01:06:19 loss: -0.5658 Lr: 1.75809e-03 +[2025-02-22 13:25:23,565 INFO hook.py line 109 2775932] Train: [66/100][400/800] Data 0.002 (0.004) Batch 0.154 (0.143) Remain 01:05:52 loss: -0.6632 Lr: 1.75245e-03 +[2025-02-22 13:25:30,688 INFO hook.py line 109 2775932] Train: [66/100][450/800] Data 0.002 (0.004) Batch 0.163 (0.143) Remain 01:05:43 loss: -0.5608 Lr: 1.74681e-03 +[2025-02-22 13:25:37,957 INFO hook.py line 109 2775932] Train: [66/100][500/800] Data 0.002 (0.003) Batch 0.144 (0.143) Remain 01:05:42 loss: -0.5161 Lr: 1.74118e-03 +[2025-02-22 13:25:45,101 INFO hook.py line 109 2775932] Train: [66/100][550/800] Data 0.003 (0.003) Batch 0.137 (0.143) Remain 01:05:34 loss: -0.7294 Lr: 1.73556e-03 +[2025-02-22 13:25:52,332 INFO hook.py line 109 2775932] Train: [66/100][600/800] Data 0.003 (0.003) Batch 0.144 (0.143) Remain 01:05:29 loss: -0.7311 Lr: 1.72994e-03 +[2025-02-22 13:25:59,504 INFO hook.py line 109 2775932] Train: [66/100][650/800] Data 0.002 (0.003) Batch 0.140 (0.143) Remain 01:05:22 loss: -0.6836 Lr: 1.72432e-03 +[2025-02-22 13:26:07,558 INFO hook.py line 109 2775932] Train: [66/100][700/800] Data 0.003 (0.003) Batch 0.155 (0.145) Remain 01:05:50 loss: -0.7253 Lr: 1.71872e-03 +[2025-02-22 13:26:14,928 INFO hook.py line 109 2775932] Train: [66/100][750/800] Data 0.002 (0.003) Batch 0.134 (0.145) Remain 01:05:47 loss: -0.5121 Lr: 1.71311e-03 +[2025-02-22 13:26:22,060 INFO hook.py line 109 2775932] Train: [66/100][800/800] Data 0.002 (0.003) Batch 0.148 (0.145) Remain 01:05:36 loss: -0.4548 Lr: 1.70752e-03 +[2025-02-22 13:26:22,062 INFO misc.py line 135 2775932] Train result: loss: -0.5983 seg_loss: 0.1527 bias_l1_loss: 0.1996 bias_cosine_loss: -0.9506 +[2025-02-22 13:26:22,062 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:26:30,032 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.7945 +[2025-02-22 13:26:30,318 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.4488 +[2025-02-22 13:26:30,391 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5323 +[2025-02-22 13:26:30,461 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.3981 +[2025-02-22 13:26:30,523 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6758 +[2025-02-22 13:26:30,579 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.1743 +[2025-02-22 13:26:30,856 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5011 +[2025-02-22 13:26:30,893 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5329 +[2025-02-22 13:26:31,032 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3845 +[2025-02-22 13:26:31,095 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1469 +[2025-02-22 13:26:31,354 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0919 +[2025-02-22 13:26:31,484 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.4037 +[2025-02-22 13:26:31,592 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0305 +[2025-02-22 13:26:31,687 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9946 +[2025-02-22 13:26:31,798 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0480 +[2025-02-22 13:26:31,866 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5885 +[2025-02-22 13:26:32,012 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4771 +[2025-02-22 13:26:32,111 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3400 +[2025-02-22 13:26:32,262 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0310 +[2025-02-22 13:26:32,325 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0113 +[2025-02-22 13:26:32,503 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6959 +[2025-02-22 13:26:32,710 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0217 +[2025-02-22 13:26:32,799 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1022 +[2025-02-22 13:26:32,867 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1418 +[2025-02-22 13:26:32,936 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1630 +[2025-02-22 13:26:32,998 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5876 +[2025-02-22 13:26:33,128 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.1068 +[2025-02-22 13:26:33,225 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6037 +[2025-02-22 13:26:33,314 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7001 +[2025-02-22 13:26:33,402 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5813 +[2025-02-22 13:26:34,304 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5192 +[2025-02-22 13:26:34,439 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0186 +[2025-02-22 13:26:34,484 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6887 +[2025-02-22 13:26:34,612 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4694 +[2025-02-22 13:26:34,673 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5762 +[2025-02-22 13:26:34,795 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9663 +[2025-02-22 13:26:34,871 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4999 +[2025-02-22 13:26:35,028 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7393 +[2025-02-22 13:26:35,201 INFO evaluator.py line 595 2775932] Test: [39/78] Loss -0.1739 +[2025-02-22 13:26:35,426 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8637 +[2025-02-22 13:26:35,628 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4164 +[2025-02-22 13:26:35,683 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3616 +[2025-02-22 13:26:35,737 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7334 +[2025-02-22 13:26:36,030 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7451 +[2025-02-22 13:26:36,073 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.3628 +[2025-02-22 13:26:36,118 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5752 +[2025-02-22 13:26:36,213 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.0949 +[2025-02-22 13:26:36,351 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2963 +[2025-02-22 13:26:36,468 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1469 +[2025-02-22 13:26:36,571 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.4381 +[2025-02-22 13:26:36,652 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3208 +[2025-02-22 13:26:36,812 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3856 +[2025-02-22 13:26:36,860 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6583 +[2025-02-22 13:26:36,973 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3867 +[2025-02-22 13:26:37,075 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8274 +[2025-02-22 13:26:37,135 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7336 +[2025-02-22 13:26:37,288 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2206 +[2025-02-22 13:26:37,328 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5135 +[2025-02-22 13:26:37,565 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3400 +[2025-02-22 13:26:37,664 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1613 +[2025-02-22 13:26:37,729 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6832 +[2025-02-22 13:26:37,796 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5402 +[2025-02-22 13:26:37,955 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0049 +[2025-02-22 13:26:38,063 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.2786 +[2025-02-22 13:26:38,143 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0865 +[2025-02-22 13:26:38,279 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2837 +[2025-02-22 13:26:38,461 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6331 +[2025-02-22 13:26:38,550 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0682 +[2025-02-22 13:26:38,607 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7165 +[2025-02-22 13:26:38,663 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3752 +[2025-02-22 13:26:38,849 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0678 +[2025-02-22 13:26:38,902 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5257 +[2025-02-22 13:26:38,964 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8416 +[2025-02-22 13:26:39,074 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6824 +[2025-02-22 13:26:39,298 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6624 +[2025-02-22 13:26:39,378 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2694 +[2025-02-22 13:26:39,558 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4083 +[2025-02-22 13:26:39,659 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6046 +[2025-02-22 13:26:50,723 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:26:50,723 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:26:50,723 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] cabinet : 0.2499 0.4903 0.7010 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] bed : 0.3649 0.7242 0.8272 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] chair : 0.7416 0.8951 0.9354 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] sofa : 0.3544 0.5924 0.8416 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] table : 0.4211 0.6862 0.7956 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] door : 0.2675 0.4839 0.6171 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] window : 0.1965 0.3563 0.5154 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] bookshelf : 0.2171 0.5099 0.6627 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] picture : 0.3370 0.4926 0.5666 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] counter : 0.0478 0.1292 0.6311 +[2025-02-22 13:26:50,723 INFO evaluator.py line 547 2775932] desk : 0.1076 0.3632 0.7747 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] curtain : 0.2986 0.4865 0.6159 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] refridgerator : 0.4137 0.5433 0.5745 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] shower curtain : 0.4864 0.7066 0.7872 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] toilet : 0.8770 0.9803 0.9982 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] sink : 0.3964 0.6968 0.8813 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] bathtub : 0.5862 0.6909 0.8545 +[2025-02-22 13:26:50,724 INFO evaluator.py line 547 2775932] otherfurniture : 0.3799 0.5473 0.6731 +[2025-02-22 13:26:50,724 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:26:50,724 INFO evaluator.py line 554 2775932] average : 0.3746 0.5764 0.7363 +[2025-02-22 13:26:50,724 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:26:50,724 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:26:50,759 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5764 +[2025-02-22 13:26:50,766 INFO misc.py line 164 2775932] Currently Best AP50: 0.5764 +[2025-02-22 13:26:50,766 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:26:59,891 INFO hook.py line 109 2775932] Train: [67/100][50/800] Data 0.002 (0.004) Batch 0.174 (0.143) Remain 01:04:52 loss: -0.6654 Lr: 1.70192e-03 +[2025-02-22 13:27:07,389 INFO hook.py line 109 2775932] Train: [67/100][100/800] Data 0.003 (0.006) Batch 0.137 (0.147) Remain 01:06:17 loss: -0.6246 Lr: 1.69634e-03 +[2025-02-22 13:27:14,512 INFO hook.py line 109 2775932] Train: [67/100][150/800] Data 0.002 (0.005) Batch 0.157 (0.145) Remain 01:05:30 loss: -0.6347 Lr: 1.69076e-03 +[2025-02-22 13:27:21,572 INFO hook.py line 109 2775932] Train: [67/100][200/800] Data 0.003 (0.004) Batch 0.158 (0.144) Remain 01:04:54 loss: -0.5651 Lr: 1.68518e-03 +[2025-02-22 13:27:28,626 INFO hook.py line 109 2775932] Train: [67/100][250/800] Data 0.003 (0.004) Batch 0.140 (0.144) Remain 01:04:30 loss: -0.4715 Lr: 1.67961e-03 +[2025-02-22 13:27:35,717 INFO hook.py line 109 2775932] Train: [67/100][300/800] Data 0.002 (0.004) Batch 0.129 (0.143) Remain 01:04:15 loss: -0.5292 Lr: 1.67405e-03 +[2025-02-22 13:27:42,995 INFO hook.py line 109 2775932] Train: [67/100][350/800] Data 0.003 (0.004) Batch 0.133 (0.144) Remain 01:04:16 loss: -0.6057 Lr: 1.66849e-03 +[2025-02-22 13:27:50,345 INFO hook.py line 109 2775932] Train: [67/100][400/800] Data 0.003 (0.004) Batch 0.124 (0.144) Remain 01:04:20 loss: -0.4901 Lr: 1.66294e-03 +[2025-02-22 13:27:57,497 INFO hook.py line 109 2775932] Train: [67/100][450/800] Data 0.003 (0.004) Batch 0.141 (0.144) Remain 01:04:10 loss: -0.4467 Lr: 1.65739e-03 +[2025-02-22 13:28:04,653 INFO hook.py line 109 2775932] Train: [67/100][500/800] Data 0.003 (0.004) Batch 0.163 (0.144) Remain 01:04:01 loss: -0.4249 Lr: 1.65185e-03 +[2025-02-22 13:28:11,747 INFO hook.py line 109 2775932] Train: [67/100][550/800] Data 0.002 (0.003) Batch 0.134 (0.144) Remain 01:03:49 loss: -0.5347 Lr: 1.64631e-03 +[2025-02-22 13:28:19,098 INFO hook.py line 109 2775932] Train: [67/100][600/800] Data 0.004 (0.003) Batch 0.133 (0.144) Remain 01:03:49 loss: -0.5249 Lr: 1.64079e-03 +[2025-02-22 13:28:26,396 INFO hook.py line 109 2775932] Train: [67/100][650/800] Data 0.002 (0.003) Batch 0.153 (0.144) Remain 01:03:46 loss: -0.5044 Lr: 1.63526e-03 +[2025-02-22 13:28:33,544 INFO hook.py line 109 2775932] Train: [67/100][700/800] Data 0.002 (0.003) Batch 0.129 (0.144) Remain 01:03:36 loss: -0.6539 Lr: 1.62974e-03 +[2025-02-22 13:28:40,740 INFO hook.py line 109 2775932] Train: [67/100][750/800] Data 0.002 (0.003) Batch 0.135 (0.144) Remain 01:03:29 loss: -0.6548 Lr: 1.62423e-03 +[2025-02-22 13:28:47,622 INFO hook.py line 109 2775932] Train: [67/100][800/800] Data 0.002 (0.003) Batch 0.111 (0.144) Remain 01:03:11 loss: -0.4402 Lr: 1.61873e-03 +[2025-02-22 13:28:47,623 INFO misc.py line 135 2775932] Train result: loss: -0.6044 seg_loss: 0.1507 bias_l1_loss: 0.1957 bias_cosine_loss: -0.9508 +[2025-02-22 13:28:47,623 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:28:55,123 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8018 +[2025-02-22 13:28:55,316 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5120 +[2025-02-22 13:28:55,404 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6077 +[2025-02-22 13:28:55,495 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6604 +[2025-02-22 13:28:55,558 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6904 +[2025-02-22 13:28:55,621 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.3485 +[2025-02-22 13:28:55,945 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5617 +[2025-02-22 13:28:55,976 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3195 +[2025-02-22 13:28:56,148 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1139 +[2025-02-22 13:28:56,203 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0395 +[2025-02-22 13:28:56,495 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0304 +[2025-02-22 13:28:56,615 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0334 +[2025-02-22 13:28:56,701 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0896 +[2025-02-22 13:28:56,800 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2202 +[2025-02-22 13:28:56,895 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0353 +[2025-02-22 13:28:56,977 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6335 +[2025-02-22 13:28:57,137 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6023 +[2025-02-22 13:28:57,240 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2862 +[2025-02-22 13:28:57,412 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2724 +[2025-02-22 13:28:57,480 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2337 +[2025-02-22 13:28:57,643 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6605 +[2025-02-22 13:28:57,854 INFO evaluator.py line 595 2775932] Test: [22/78] Loss -0.0438 +[2025-02-22 13:28:57,932 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0498 +[2025-02-22 13:28:57,988 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1102 +[2025-02-22 13:28:58,059 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2776 +[2025-02-22 13:28:58,127 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6075 +[2025-02-22 13:28:58,267 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2415 +[2025-02-22 13:28:58,357 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5518 +[2025-02-22 13:28:58,431 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6768 +[2025-02-22 13:28:58,504 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6884 +[2025-02-22 13:28:59,499 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5396 +[2025-02-22 13:28:59,663 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2083 +[2025-02-22 13:28:59,714 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6895 +[2025-02-22 13:28:59,839 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.2363 +[2025-02-22 13:28:59,882 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5946 +[2025-02-22 13:29:00,008 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.7636 +[2025-02-22 13:29:00,088 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6021 +[2025-02-22 13:29:00,240 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7426 +[2025-02-22 13:29:00,399 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5796 +[2025-02-22 13:29:00,618 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9251 +[2025-02-22 13:29:00,794 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3904 +[2025-02-22 13:29:00,851 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3752 +[2025-02-22 13:29:00,906 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7544 +[2025-02-22 13:29:01,200 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6131 +[2025-02-22 13:29:01,253 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5771 +[2025-02-22 13:29:01,308 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5199 +[2025-02-22 13:29:01,424 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2956 +[2025-02-22 13:29:01,572 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3156 +[2025-02-22 13:29:01,703 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.5187 +[2025-02-22 13:29:01,800 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1897 +[2025-02-22 13:29:01,894 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0663 +[2025-02-22 13:29:02,042 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4554 +[2025-02-22 13:29:02,087 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6439 +[2025-02-22 13:29:02,212 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.1117 +[2025-02-22 13:29:02,299 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8662 +[2025-02-22 13:29:02,338 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7332 +[2025-02-22 13:29:02,480 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1313 +[2025-02-22 13:29:02,517 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4924 +[2025-02-22 13:29:02,746 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3043 +[2025-02-22 13:29:02,854 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.0949 +[2025-02-22 13:29:02,967 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 1.2312 +[2025-02-22 13:29:03,042 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6846 +[2025-02-22 13:29:03,228 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3020 +[2025-02-22 13:29:03,333 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0713 +[2025-02-22 13:29:03,406 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.2096 +[2025-02-22 13:29:03,572 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2509 +[2025-02-22 13:29:03,784 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6900 +[2025-02-22 13:29:03,882 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1662 +[2025-02-22 13:29:03,940 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6420 +[2025-02-22 13:29:03,991 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4640 +[2025-02-22 13:29:04,174 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.0313 +[2025-02-22 13:29:04,215 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4623 +[2025-02-22 13:29:04,281 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.6346 +[2025-02-22 13:29:04,403 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2603 +[2025-02-22 13:29:04,637 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.5972 +[2025-02-22 13:29:04,726 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1632 +[2025-02-22 13:29:04,914 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4703 +[2025-02-22 13:29:05,024 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6344 +[2025-02-22 13:29:18,270 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:29:18,270 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:29:18,270 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] cabinet : 0.2493 0.4711 0.6749 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] bed : 0.3321 0.7173 0.8498 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] chair : 0.7349 0.8930 0.9354 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] sofa : 0.3290 0.5510 0.7892 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] table : 0.3785 0.6133 0.7247 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] door : 0.2355 0.4555 0.5935 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] window : 0.2012 0.3811 0.5837 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] bookshelf : 0.2079 0.4448 0.7599 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] picture : 0.3110 0.4449 0.5281 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] counter : 0.0604 0.1809 0.5821 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] desk : 0.1387 0.4108 0.8036 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] curtain : 0.2527 0.4416 0.5712 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] refridgerator : 0.3488 0.4541 0.5342 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] shower curtain : 0.5118 0.6786 0.8436 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] toilet : 0.8374 0.9629 0.9799 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] sink : 0.3754 0.6584 0.8674 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] bathtub : 0.6286 0.7446 0.8673 +[2025-02-22 13:29:18,270 INFO evaluator.py line 547 2775932] otherfurniture : 0.4043 0.5815 0.7084 +[2025-02-22 13:29:18,270 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:29:18,270 INFO evaluator.py line 554 2775932] average : 0.3632 0.5603 0.7332 +[2025-02-22 13:29:18,270 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:29:18,271 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:29:18,315 INFO misc.py line 164 2775932] Currently Best AP50: 0.5764 +[2025-02-22 13:29:18,322 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:29:26,842 INFO hook.py line 109 2775932] Train: [68/100][50/800] Data 0.003 (0.003) Batch 0.130 (0.143) Remain 01:02:58 loss: -0.6827 Lr: 1.61323e-03 +[2025-02-22 13:29:34,080 INFO hook.py line 109 2775932] Train: [68/100][100/800] Data 0.003 (0.003) Batch 0.156 (0.144) Remain 01:03:09 loss: -0.7026 Lr: 1.60773e-03 +[2025-02-22 13:29:41,331 INFO hook.py line 109 2775932] Train: [68/100][150/800] Data 0.003 (0.003) Batch 0.151 (0.144) Remain 01:03:10 loss: -0.5749 Lr: 1.60224e-03 +[2025-02-22 13:29:48,609 INFO hook.py line 109 2775932] Train: [68/100][200/800] Data 0.004 (0.003) Batch 0.157 (0.145) Remain 01:03:11 loss: -0.4482 Lr: 1.59676e-03 +[2025-02-22 13:29:55,865 INFO hook.py line 109 2775932] Train: [68/100][250/800] Data 0.003 (0.003) Batch 0.143 (0.145) Remain 01:03:06 loss: -0.5501 Lr: 1.59128e-03 +[2025-02-22 13:30:03,118 INFO hook.py line 109 2775932] Train: [68/100][300/800] Data 0.004 (0.004) Batch 0.130 (0.145) Remain 01:03:00 loss: -0.5749 Lr: 1.58581e-03 +[2025-02-22 13:30:10,237 INFO hook.py line 109 2775932] Train: [68/100][350/800] Data 0.003 (0.004) Batch 0.142 (0.144) Remain 01:02:43 loss: -0.6569 Lr: 1.58035e-03 +[2025-02-22 13:30:17,333 INFO hook.py line 109 2775932] Train: [68/100][400/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 01:02:28 loss: -0.5460 Lr: 1.57489e-03 +[2025-02-22 13:30:24,599 INFO hook.py line 109 2775932] Train: [68/100][450/800] Data 0.004 (0.003) Batch 0.165 (0.144) Remain 01:02:24 loss: -0.5252 Lr: 1.56944e-03 +[2025-02-22 13:30:31,904 INFO hook.py line 109 2775932] Train: [68/100][500/800] Data 0.003 (0.003) Batch 0.154 (0.144) Remain 01:02:21 loss: -0.0387 Lr: 1.56399e-03 +[2025-02-22 13:30:39,194 INFO hook.py line 109 2775932] Train: [68/100][550/800] Data 0.003 (0.003) Batch 0.163 (0.145) Remain 01:02:17 loss: -0.4808 Lr: 1.55855e-03 +[2025-02-22 13:30:46,509 INFO hook.py line 109 2775932] Train: [68/100][600/800] Data 0.003 (0.003) Batch 0.136 (0.145) Remain 01:02:14 loss: -0.6375 Lr: 1.55312e-03 +[2025-02-22 13:30:53,665 INFO hook.py line 109 2775932] Train: [68/100][650/800] Data 0.003 (0.003) Batch 0.132 (0.145) Remain 01:02:03 loss: -0.6083 Lr: 1.54769e-03 +[2025-02-22 13:31:01,008 INFO hook.py line 109 2775932] Train: [68/100][700/800] Data 0.003 (0.003) Batch 0.122 (0.145) Remain 01:02:00 loss: -0.7055 Lr: 1.54227e-03 +[2025-02-22 13:31:08,147 INFO hook.py line 109 2775932] Train: [68/100][750/800] Data 0.003 (0.003) Batch 0.147 (0.145) Remain 01:01:49 loss: -0.5819 Lr: 1.53686e-03 +[2025-02-22 13:31:14,927 INFO hook.py line 109 2775932] Train: [68/100][800/800] Data 0.002 (0.003) Batch 0.112 (0.144) Remain 01:01:28 loss: -0.4935 Lr: 1.53145e-03 +[2025-02-22 13:31:14,927 INFO misc.py line 135 2775932] Train result: loss: -0.5957 seg_loss: 0.1579 bias_l1_loss: 0.1978 bias_cosine_loss: -0.9513 +[2025-02-22 13:31:14,927 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:31:22,018 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8267 +[2025-02-22 13:31:22,240 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5963 +[2025-02-22 13:31:22,371 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5091 +[2025-02-22 13:31:22,800 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6777 +[2025-02-22 13:31:22,859 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7047 +[2025-02-22 13:31:22,924 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.8251 +[2025-02-22 13:31:23,229 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.4999 +[2025-02-22 13:31:23,261 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4895 +[2025-02-22 13:31:23,406 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3005 +[2025-02-22 13:31:23,474 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1514 +[2025-02-22 13:31:23,739 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.3229 +[2025-02-22 13:31:23,856 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1421 +[2025-02-22 13:31:23,932 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2667 +[2025-02-22 13:31:24,045 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0582 +[2025-02-22 13:31:24,151 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0661 +[2025-02-22 13:31:24,252 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.5964 +[2025-02-22 13:31:24,384 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.4245 +[2025-02-22 13:31:24,505 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4559 +[2025-02-22 13:31:24,678 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4939 +[2025-02-22 13:31:24,740 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0600 +[2025-02-22 13:31:24,936 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7001 +[2025-02-22 13:31:25,099 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1554 +[2025-02-22 13:31:25,177 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0312 +[2025-02-22 13:31:25,232 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1738 +[2025-02-22 13:31:25,285 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4734 +[2025-02-22 13:31:25,344 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5927 +[2025-02-22 13:31:25,468 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0553 +[2025-02-22 13:31:25,570 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.3553 +[2025-02-22 13:31:25,678 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7021 +[2025-02-22 13:31:25,774 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7201 +[2025-02-22 13:31:26,649 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5222 +[2025-02-22 13:31:26,793 INFO evaluator.py line 595 2775932] Test: [32/78] Loss -0.0404 +[2025-02-22 13:31:26,839 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6146 +[2025-02-22 13:31:26,958 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3058 +[2025-02-22 13:31:27,005 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5052 +[2025-02-22 13:31:27,140 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9505 +[2025-02-22 13:31:27,216 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7323 +[2025-02-22 13:31:27,370 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6772 +[2025-02-22 13:31:27,583 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0564 +[2025-02-22 13:31:27,842 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9777 +[2025-02-22 13:31:28,025 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1900 +[2025-02-22 13:31:28,084 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3787 +[2025-02-22 13:31:28,139 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7874 +[2025-02-22 13:31:28,398 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7201 +[2025-02-22 13:31:28,443 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5129 +[2025-02-22 13:31:28,489 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4995 +[2025-02-22 13:31:28,595 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1588 +[2025-02-22 13:31:28,745 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5116 +[2025-02-22 13:31:28,871 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1551 +[2025-02-22 13:31:28,983 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0582 +[2025-02-22 13:31:29,071 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.0573 +[2025-02-22 13:31:29,228 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4489 +[2025-02-22 13:31:29,282 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5253 +[2025-02-22 13:31:29,420 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.8183 +[2025-02-22 13:31:29,524 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8126 +[2025-02-22 13:31:29,581 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7515 +[2025-02-22 13:31:29,755 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0591 +[2025-02-22 13:31:29,797 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4726 +[2025-02-22 13:31:30,038 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3176 +[2025-02-22 13:31:30,152 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0429 +[2025-02-22 13:31:30,225 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3744 +[2025-02-22 13:31:30,292 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6724 +[2025-02-22 13:31:30,444 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1856 +[2025-02-22 13:31:30,553 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.1220 +[2025-02-22 13:31:30,632 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1132 +[2025-02-22 13:31:30,779 INFO evaluator.py line 595 2775932] Test: [66/78] Loss 0.0792 +[2025-02-22 13:31:30,962 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.4281 +[2025-02-22 13:31:31,069 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1971 +[2025-02-22 13:31:31,126 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8009 +[2025-02-22 13:31:31,182 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0950 +[2025-02-22 13:31:31,353 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4758 +[2025-02-22 13:31:31,392 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5592 +[2025-02-22 13:31:31,450 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7995 +[2025-02-22 13:31:31,573 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.8957 +[2025-02-22 13:31:31,803 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6760 +[2025-02-22 13:31:31,900 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.4653 +[2025-02-22 13:31:32,099 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5309 +[2025-02-22 13:31:32,213 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6161 +[2025-02-22 13:31:44,413 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:31:44,413 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:31:44,413 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] cabinet : 0.2764 0.5109 0.7177 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] bed : 0.3780 0.7515 0.8392 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] chair : 0.7348 0.8908 0.9330 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] sofa : 0.4233 0.6983 0.8366 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] table : 0.3838 0.6267 0.7695 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] door : 0.2657 0.4580 0.5988 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] window : 0.2162 0.4119 0.5789 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] bookshelf : 0.2535 0.5203 0.7631 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] picture : 0.3113 0.4480 0.5471 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] counter : 0.0583 0.2357 0.6506 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] desk : 0.0851 0.2994 0.6826 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] curtain : 0.2044 0.3521 0.6155 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] refridgerator : 0.3928 0.5477 0.5812 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] shower curtain : 0.4937 0.6397 0.7957 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] toilet : 0.8163 0.9655 0.9828 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] sink : 0.3984 0.6889 0.8369 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] bathtub : 0.6178 0.7653 0.8632 +[2025-02-22 13:31:44,413 INFO evaluator.py line 547 2775932] otherfurniture : 0.3871 0.5680 0.6523 +[2025-02-22 13:31:44,413 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:31:44,413 INFO evaluator.py line 554 2775932] average : 0.3721 0.5766 0.7358 +[2025-02-22 13:31:44,413 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:31:44,414 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:31:44,447 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5766 +[2025-02-22 13:31:44,454 INFO misc.py line 164 2775932] Currently Best AP50: 0.5766 +[2025-02-22 13:31:44,454 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:31:53,218 INFO hook.py line 109 2775932] Train: [69/100][50/800] Data 0.003 (0.004) Batch 0.134 (0.145) Remain 01:01:54 loss: -0.5789 Lr: 1.52604e-03 +[2025-02-22 13:32:00,426 INFO hook.py line 109 2775932] Train: [69/100][100/800] Data 0.003 (0.004) Batch 0.141 (0.145) Remain 01:01:31 loss: -0.7036 Lr: 1.52065e-03 +[2025-02-22 13:32:07,551 INFO hook.py line 109 2775932] Train: [69/100][150/800] Data 0.003 (0.003) Batch 0.151 (0.144) Remain 01:01:04 loss: -0.5888 Lr: 1.51526e-03 +[2025-02-22 13:32:14,915 INFO hook.py line 109 2775932] Train: [69/100][200/800] Data 0.003 (0.004) Batch 0.148 (0.145) Remain 01:01:18 loss: -0.7947 Lr: 1.50987e-03 +[2025-02-22 13:32:22,092 INFO hook.py line 109 2775932] Train: [69/100][250/800] Data 0.003 (0.004) Batch 0.157 (0.145) Remain 01:01:04 loss: -0.5712 Lr: 1.50450e-03 +[2025-02-22 13:32:29,264 INFO hook.py line 109 2775932] Train: [69/100][300/800] Data 0.003 (0.004) Batch 0.139 (0.144) Remain 01:00:52 loss: -0.4084 Lr: 1.49913e-03 +[2025-02-22 13:32:36,409 INFO hook.py line 109 2775932] Train: [69/100][350/800] Data 0.003 (0.004) Batch 0.161 (0.144) Remain 01:00:40 loss: -0.5537 Lr: 1.49376e-03 +[2025-02-22 13:32:43,653 INFO hook.py line 109 2775932] Train: [69/100][400/800] Data 0.002 (0.004) Batch 0.143 (0.144) Remain 01:00:35 loss: -0.6874 Lr: 1.48840e-03 +[2025-02-22 13:32:50,756 INFO hook.py line 109 2775932] Train: [69/100][450/800] Data 0.004 (0.004) Batch 0.137 (0.144) Remain 01:00:21 loss: -0.6123 Lr: 1.48305e-03 +[2025-02-22 13:32:57,913 INFO hook.py line 109 2775932] Train: [69/100][500/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 01:00:12 loss: -0.5522 Lr: 1.47771e-03 +[2025-02-22 13:33:05,214 INFO hook.py line 109 2775932] Train: [69/100][550/800] Data 0.003 (0.004) Batch 0.159 (0.144) Remain 01:00:09 loss: -0.6241 Lr: 1.47237e-03 +[2025-02-22 13:33:12,369 INFO hook.py line 109 2775932] Train: [69/100][600/800] Data 0.003 (0.003) Batch 0.156 (0.144) Remain 01:00:00 loss: -0.4196 Lr: 1.46704e-03 +[2025-02-22 13:33:19,675 INFO hook.py line 109 2775932] Train: [69/100][650/800] Data 0.005 (0.003) Batch 0.143 (0.144) Remain 00:59:57 loss: -0.5545 Lr: 1.46171e-03 +[2025-02-22 13:33:26,943 INFO hook.py line 109 2775932] Train: [69/100][700/800] Data 0.003 (0.003) Batch 0.141 (0.144) Remain 00:59:52 loss: -0.6442 Lr: 1.45639e-03 +[2025-02-22 13:33:34,262 INFO hook.py line 109 2775932] Train: [69/100][750/800] Data 0.003 (0.003) Batch 0.128 (0.144) Remain 00:59:48 loss: -0.5362 Lr: 1.45108e-03 +[2025-02-22 13:33:41,235 INFO hook.py line 109 2775932] Train: [69/100][800/800] Data 0.003 (0.003) Batch 0.122 (0.144) Remain 00:59:33 loss: -0.3877 Lr: 1.44577e-03 +[2025-02-22 13:33:41,235 INFO misc.py line 135 2775932] Train result: loss: -0.6144 seg_loss: 0.1465 bias_l1_loss: 0.1922 bias_cosine_loss: -0.9531 +[2025-02-22 13:33:41,236 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:33:48,300 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8480 +[2025-02-22 13:33:48,555 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5646 +[2025-02-22 13:33:48,642 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6134 +[2025-02-22 13:33:48,736 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6695 +[2025-02-22 13:33:48,841 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7057 +[2025-02-22 13:33:48,911 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.1561 +[2025-02-22 13:33:49,232 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6158 +[2025-02-22 13:33:49,266 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5158 +[2025-02-22 13:33:49,416 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2684 +[2025-02-22 13:33:49,479 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0252 +[2025-02-22 13:33:49,754 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1624 +[2025-02-22 13:33:49,867 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.1263 +[2025-02-22 13:33:49,946 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1318 +[2025-02-22 13:33:50,054 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2749 +[2025-02-22 13:33:50,154 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.4759 +[2025-02-22 13:33:50,233 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6576 +[2025-02-22 13:33:50,373 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5491 +[2025-02-22 13:33:50,485 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.0945 +[2025-02-22 13:33:50,635 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.4314 +[2025-02-22 13:33:50,699 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0580 +[2025-02-22 13:33:50,877 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6919 +[2025-02-22 13:33:51,054 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4266 +[2025-02-22 13:33:51,139 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0125 +[2025-02-22 13:33:51,194 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1319 +[2025-02-22 13:33:51,275 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2575 +[2025-02-22 13:33:51,336 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5549 +[2025-02-22 13:33:51,479 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2165 +[2025-02-22 13:33:51,576 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5472 +[2025-02-22 13:33:51,652 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7431 +[2025-02-22 13:33:51,730 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6740 +[2025-02-22 13:33:52,601 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5378 +[2025-02-22 13:33:52,739 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0526 +[2025-02-22 13:33:52,780 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7333 +[2025-02-22 13:33:52,910 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.0557 +[2025-02-22 13:33:52,960 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4375 +[2025-02-22 13:33:53,087 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8908 +[2025-02-22 13:33:53,168 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6994 +[2025-02-22 13:33:53,321 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7515 +[2025-02-22 13:33:53,509 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1923 +[2025-02-22 13:33:53,764 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8526 +[2025-02-22 13:33:53,971 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5132 +[2025-02-22 13:33:54,029 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4042 +[2025-02-22 13:33:54,084 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7934 +[2025-02-22 13:33:54,368 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7054 +[2025-02-22 13:33:54,421 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6267 +[2025-02-22 13:33:54,494 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4951 +[2025-02-22 13:33:54,600 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.4074 +[2025-02-22 13:33:54,744 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3904 +[2025-02-22 13:33:54,877 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1633 +[2025-02-22 13:33:54,979 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0119 +[2025-02-22 13:33:55,071 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3233 +[2025-02-22 13:33:55,234 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4215 +[2025-02-22 13:33:55,281 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5106 +[2025-02-22 13:33:55,404 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3447 +[2025-02-22 13:33:55,502 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8769 +[2025-02-22 13:33:55,554 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7857 +[2025-02-22 13:33:55,706 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2057 +[2025-02-22 13:33:55,749 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5482 +[2025-02-22 13:33:56,004 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3173 +[2025-02-22 13:33:56,120 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0820 +[2025-02-22 13:33:56,214 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5576 +[2025-02-22 13:33:56,283 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6834 +[2025-02-22 13:33:56,425 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.1935 +[2025-02-22 13:33:56,556 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0164 +[2025-02-22 13:33:56,642 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0590 +[2025-02-22 13:33:56,790 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3243 +[2025-02-22 13:33:56,987 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.5848 +[2025-02-22 13:33:57,091 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0854 +[2025-02-22 13:33:57,146 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.8337 +[2025-02-22 13:33:57,201 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2901 +[2025-02-22 13:33:57,393 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3649 +[2025-02-22 13:33:57,431 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5657 +[2025-02-22 13:33:57,485 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8186 +[2025-02-22 13:33:57,603 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.1633 +[2025-02-22 13:33:57,821 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.3550 +[2025-02-22 13:33:57,904 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0175 +[2025-02-22 13:33:58,084 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5994 +[2025-02-22 13:33:58,191 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6305 +[2025-02-22 13:34:11,205 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:34:11,205 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:34:11,205 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:34:11,205 INFO evaluator.py line 547 2775932] cabinet : 0.2682 0.5157 0.6957 +[2025-02-22 13:34:11,205 INFO evaluator.py line 547 2775932] bed : 0.3773 0.6459 0.7271 +[2025-02-22 13:34:11,205 INFO evaluator.py line 547 2775932] chair : 0.7533 0.9097 0.9439 +[2025-02-22 13:34:11,205 INFO evaluator.py line 547 2775932] sofa : 0.2868 0.5405 0.7889 +[2025-02-22 13:34:11,205 INFO evaluator.py line 547 2775932] table : 0.4312 0.6818 0.8009 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] door : 0.2487 0.4729 0.6039 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] window : 0.2102 0.3844 0.5671 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] bookshelf : 0.2538 0.5282 0.7967 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] picture : 0.3835 0.5287 0.6169 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] counter : 0.0091 0.0349 0.4795 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] desk : 0.1341 0.4473 0.8478 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] curtain : 0.3076 0.4999 0.6291 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] refridgerator : 0.3332 0.4182 0.4730 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] shower curtain : 0.4734 0.6586 0.7948 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] toilet : 0.8515 0.9809 1.0000 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] sink : 0.3938 0.6715 0.8830 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] bathtub : 0.6414 0.7865 0.8710 +[2025-02-22 13:34:11,206 INFO evaluator.py line 547 2775932] otherfurniture : 0.4182 0.5878 0.6724 +[2025-02-22 13:34:11,206 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:34:11,206 INFO evaluator.py line 554 2775932] average : 0.3764 0.5719 0.7329 +[2025-02-22 13:34:11,206 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:34:11,206 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:34:11,240 INFO misc.py line 164 2775932] Currently Best AP50: 0.5766 +[2025-02-22 13:34:11,246 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:34:20,446 INFO hook.py line 109 2775932] Train: [70/100][50/800] Data 0.002 (0.008) Batch 0.239 (0.154) Remain 01:03:20 loss: -0.5522 Lr: 1.44047e-03 +[2025-02-22 13:34:27,514 INFO hook.py line 109 2775932] Train: [70/100][100/800] Data 0.006 (0.005) Batch 0.139 (0.147) Remain 01:00:37 loss: -0.7011 Lr: 1.43518e-03 +[2025-02-22 13:34:34,703 INFO hook.py line 109 2775932] Train: [70/100][150/800] Data 0.002 (0.004) Batch 0.143 (0.146) Remain 01:00:01 loss: -0.6202 Lr: 1.42990e-03 +[2025-02-22 13:34:41,875 INFO hook.py line 109 2775932] Train: [70/100][200/800] Data 0.003 (0.004) Batch 0.155 (0.145) Remain 00:59:37 loss: -0.5526 Lr: 1.42462e-03 +[2025-02-22 13:34:49,095 INFO hook.py line 109 2775932] Train: [70/100][250/800] Data 0.004 (0.004) Batch 0.154 (0.145) Remain 00:59:24 loss: -0.7641 Lr: 1.41934e-03 +[2025-02-22 13:34:56,320 INFO hook.py line 109 2775932] Train: [70/100][300/800] Data 0.003 (0.004) Batch 0.139 (0.145) Remain 00:59:14 loss: -0.6077 Lr: 1.41408e-03 +[2025-02-22 13:35:03,611 INFO hook.py line 109 2775932] Train: [70/100][350/800] Data 0.003 (0.004) Batch 0.125 (0.145) Remain 00:59:10 loss: -0.6998 Lr: 1.40882e-03 +[2025-02-22 13:35:10,777 INFO hook.py line 109 2775932] Train: [70/100][400/800] Data 0.003 (0.004) Batch 0.144 (0.145) Remain 00:58:56 loss: -0.6857 Lr: 1.40357e-03 +[2025-02-22 13:35:18,099 INFO hook.py line 109 2775932] Train: [70/100][450/800] Data 0.002 (0.003) Batch 0.151 (0.145) Remain 00:58:53 loss: -0.5579 Lr: 1.39832e-03 +[2025-02-22 13:35:25,196 INFO hook.py line 109 2775932] Train: [70/100][500/800] Data 0.003 (0.003) Batch 0.118 (0.145) Remain 00:58:38 loss: -0.5667 Lr: 1.39309e-03 +[2025-02-22 13:35:32,372 INFO hook.py line 109 2775932] Train: [70/100][550/800] Data 0.003 (0.003) Batch 0.143 (0.145) Remain 00:58:28 loss: -0.6181 Lr: 1.38785e-03 +[2025-02-22 13:35:39,432 INFO hook.py line 109 2775932] Train: [70/100][600/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 00:58:14 loss: -0.5246 Lr: 1.38263e-03 +[2025-02-22 13:35:46,490 INFO hook.py line 109 2775932] Train: [70/100][650/800] Data 0.004 (0.003) Batch 0.138 (0.144) Remain 00:58:01 loss: -0.6569 Lr: 1.37752e-03 +[2025-02-22 13:35:53,575 INFO hook.py line 109 2775932] Train: [70/100][700/800] Data 0.002 (0.003) Batch 0.126 (0.144) Remain 00:57:49 loss: -0.5179 Lr: 1.37230e-03 +[2025-02-22 13:36:00,672 INFO hook.py line 109 2775932] Train: [70/100][750/800] Data 0.003 (0.003) Batch 0.151 (0.144) Remain 00:57:39 loss: -0.6592 Lr: 1.36710e-03 +[2025-02-22 13:36:07,897 INFO hook.py line 109 2775932] Train: [70/100][800/800] Data 0.003 (0.003) Batch 0.132 (0.144) Remain 00:57:32 loss: -0.6436 Lr: 1.36190e-03 +[2025-02-22 13:36:07,897 INFO misc.py line 135 2775932] Train result: loss: -0.6210 seg_loss: 0.1416 bias_l1_loss: 0.1907 bias_cosine_loss: -0.9533 +[2025-02-22 13:36:07,898 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:36:14,786 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8535 +[2025-02-22 13:36:15,297 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5779 +[2025-02-22 13:36:15,409 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5288 +[2025-02-22 13:36:15,496 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5720 +[2025-02-22 13:36:15,597 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7525 +[2025-02-22 13:36:15,667 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9947 +[2025-02-22 13:36:16,007 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5957 +[2025-02-22 13:36:16,042 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5147 +[2025-02-22 13:36:16,212 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2263 +[2025-02-22 13:36:16,284 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.1569 +[2025-02-22 13:36:16,608 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0701 +[2025-02-22 13:36:16,755 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0541 +[2025-02-22 13:36:16,866 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.5288 +[2025-02-22 13:36:16,996 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.0291 +[2025-02-22 13:36:17,104 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.6901 +[2025-02-22 13:36:17,195 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6441 +[2025-02-22 13:36:17,361 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6316 +[2025-02-22 13:36:17,483 INFO evaluator.py line 595 2775932] Test: [18/78] Loss 0.2876 +[2025-02-22 13:36:17,645 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2426 +[2025-02-22 13:36:17,711 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1373 +[2025-02-22 13:36:17,879 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6301 +[2025-02-22 13:36:18,072 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0534 +[2025-02-22 13:36:18,162 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.2423 +[2025-02-22 13:36:18,221 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0765 +[2025-02-22 13:36:18,312 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3561 +[2025-02-22 13:36:18,372 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6147 +[2025-02-22 13:36:18,520 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.3080 +[2025-02-22 13:36:18,627 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5003 +[2025-02-22 13:36:18,701 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6792 +[2025-02-22 13:36:18,790 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6298 +[2025-02-22 13:36:19,758 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.4952 +[2025-02-22 13:36:19,952 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0129 +[2025-02-22 13:36:19,995 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7294 +[2025-02-22 13:36:20,092 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3065 +[2025-02-22 13:36:20,141 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6972 +[2025-02-22 13:36:20,239 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8940 +[2025-02-22 13:36:20,311 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6520 +[2025-02-22 13:36:20,443 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7467 +[2025-02-22 13:36:20,625 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1345 +[2025-02-22 13:36:20,847 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.5624 +[2025-02-22 13:36:21,044 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4356 +[2025-02-22 13:36:21,106 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4195 +[2025-02-22 13:36:21,156 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8333 +[2025-02-22 13:36:21,464 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6807 +[2025-02-22 13:36:21,523 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4284 +[2025-02-22 13:36:21,584 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4563 +[2025-02-22 13:36:21,707 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.9659 +[2025-02-22 13:36:21,894 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2027 +[2025-02-22 13:36:22,057 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1643 +[2025-02-22 13:36:22,192 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3248 +[2025-02-22 13:36:22,313 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2941 +[2025-02-22 13:36:22,473 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4530 +[2025-02-22 13:36:22,518 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7270 +[2025-02-22 13:36:22,645 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2777 +[2025-02-22 13:36:22,757 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8892 +[2025-02-22 13:36:22,822 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.8176 +[2025-02-22 13:36:23,003 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0126 +[2025-02-22 13:36:23,049 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.3806 +[2025-02-22 13:36:23,388 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4155 +[2025-02-22 13:36:23,505 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.1175 +[2025-02-22 13:36:23,598 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3660 +[2025-02-22 13:36:23,668 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5435 +[2025-02-22 13:36:23,894 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.2570 +[2025-02-22 13:36:24,010 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0816 +[2025-02-22 13:36:24,094 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1641 +[2025-02-22 13:36:24,251 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1730 +[2025-02-22 13:36:24,453 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7276 +[2025-02-22 13:36:24,574 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0182 +[2025-02-22 13:36:24,636 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7258 +[2025-02-22 13:36:24,695 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2154 +[2025-02-22 13:36:24,895 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3006 +[2025-02-22 13:36:24,934 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5194 +[2025-02-22 13:36:24,996 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7732 +[2025-02-22 13:36:25,124 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.2010 +[2025-02-22 13:36:25,364 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6619 +[2025-02-22 13:36:25,452 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1780 +[2025-02-22 13:36:25,647 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.4783 +[2025-02-22 13:36:25,748 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6771 +[2025-02-22 13:36:39,003 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:36:39,003 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:36:39,003 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] cabinet : 0.2910 0.5527 0.7270 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] bed : 0.3172 0.5609 0.7262 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] chair : 0.7456 0.9026 0.9401 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] sofa : 0.2947 0.4874 0.7531 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] table : 0.4335 0.7014 0.8083 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] door : 0.2792 0.5195 0.6393 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] window : 0.2509 0.4711 0.6472 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] bookshelf : 0.2927 0.5823 0.7384 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] picture : 0.3743 0.5414 0.6460 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] counter : 0.0765 0.2587 0.6248 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] desk : 0.0942 0.3520 0.7458 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] curtain : 0.3174 0.5127 0.6761 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] refridgerator : 0.3814 0.5138 0.5813 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] shower curtain : 0.4056 0.5956 0.6961 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] toilet : 0.8764 0.9975 0.9975 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] sink : 0.3270 0.5435 0.8589 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] bathtub : 0.6623 0.7742 0.8710 +[2025-02-22 13:36:39,003 INFO evaluator.py line 547 2775932] otherfurniture : 0.3774 0.5645 0.6796 +[2025-02-22 13:36:39,003 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:36:39,003 INFO evaluator.py line 554 2775932] average : 0.3776 0.5796 0.7420 +[2025-02-22 13:36:39,003 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:36:39,003 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:36:39,034 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5796 +[2025-02-22 13:36:39,041 INFO misc.py line 164 2775932] Currently Best AP50: 0.5796 +[2025-02-22 13:36:39,041 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:36:47,794 INFO hook.py line 109 2775932] Train: [71/100][50/800] Data 0.003 (0.005) Batch 0.134 (0.147) Remain 00:58:39 loss: -0.6533 Lr: 1.35671e-03 +[2025-02-22 13:36:54,768 INFO hook.py line 109 2775932] Train: [71/100][100/800] Data 0.002 (0.004) Batch 0.144 (0.143) Remain 00:57:00 loss: -0.6710 Lr: 1.35153e-03 +[2025-02-22 13:37:01,742 INFO hook.py line 109 2775932] Train: [71/100][150/800] Data 0.003 (0.004) Batch 0.143 (0.142) Remain 00:56:23 loss: -0.6709 Lr: 1.34636e-03 +[2025-02-22 13:37:08,749 INFO hook.py line 109 2775932] Train: [71/100][200/800] Data 0.003 (0.003) Batch 0.142 (0.141) Remain 00:56:05 loss: -0.6121 Lr: 1.34119e-03 +[2025-02-22 13:37:15,989 INFO hook.py line 109 2775932] Train: [71/100][250/800] Data 0.003 (0.004) Batch 0.168 (0.142) Remain 00:56:15 loss: -0.6133 Lr: 1.33602e-03 +[2025-02-22 13:37:23,088 INFO hook.py line 109 2775932] Train: [71/100][300/800] Data 0.003 (0.004) Batch 0.150 (0.142) Remain 00:56:07 loss: -0.5551 Lr: 1.33087e-03 +[2025-02-22 13:37:30,079 INFO hook.py line 109 2775932] Train: [71/100][350/800] Data 0.003 (0.004) Batch 0.145 (0.142) Remain 00:55:52 loss: -0.6601 Lr: 1.32572e-03 +[2025-02-22 13:37:37,257 INFO hook.py line 109 2775932] Train: [71/100][400/800] Data 0.003 (0.004) Batch 0.134 (0.142) Remain 00:55:50 loss: -0.5690 Lr: 1.32058e-03 +[2025-02-22 13:37:44,356 INFO hook.py line 109 2775932] Train: [71/100][450/800] Data 0.004 (0.004) Batch 0.135 (0.142) Remain 00:55:43 loss: -0.5540 Lr: 1.31545e-03 +[2025-02-22 13:37:51,420 INFO hook.py line 109 2775932] Train: [71/100][500/800] Data 0.005 (0.004) Batch 0.144 (0.142) Remain 00:55:34 loss: -0.5483 Lr: 1.31032e-03 +[2025-02-22 13:37:58,563 INFO hook.py line 109 2775932] Train: [71/100][550/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 00:55:29 loss: -0.7455 Lr: 1.30520e-03 +[2025-02-22 13:38:05,873 INFO hook.py line 109 2775932] Train: [71/100][600/800] Data 0.002 (0.004) Batch 0.131 (0.142) Remain 00:55:31 loss: -0.6437 Lr: 1.30009e-03 +[2025-02-22 13:38:12,992 INFO hook.py line 109 2775932] Train: [71/100][650/800] Data 0.003 (0.004) Batch 0.247 (0.142) Remain 00:55:23 loss: -0.5636 Lr: 1.29499e-03 +[2025-02-22 13:38:20,044 INFO hook.py line 109 2775932] Train: [71/100][700/800] Data 0.003 (0.004) Batch 0.138 (0.142) Remain 00:55:14 loss: -0.5498 Lr: 1.28989e-03 +[2025-02-22 13:38:26,923 INFO hook.py line 109 2775932] Train: [71/100][750/800] Data 0.003 (0.004) Batch 0.133 (0.142) Remain 00:55:00 loss: -0.7745 Lr: 1.28480e-03 +[2025-02-22 13:38:33,886 INFO hook.py line 109 2775932] Train: [71/100][800/800] Data 0.001 (0.004) Batch 0.135 (0.142) Remain 00:54:49 loss: -0.7786 Lr: 1.27972e-03 +[2025-02-22 13:38:33,886 INFO misc.py line 135 2775932] Train result: loss: -0.6313 seg_loss: 0.1357 bias_l1_loss: 0.1881 bias_cosine_loss: -0.9552 +[2025-02-22 13:38:33,887 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:38:41,092 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8515 +[2025-02-22 13:38:41,367 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6154 +[2025-02-22 13:38:41,445 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6187 +[2025-02-22 13:38:41,514 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.5964 +[2025-02-22 13:38:41,580 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7351 +[2025-02-22 13:38:41,646 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.1993 +[2025-02-22 13:38:41,923 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5367 +[2025-02-22 13:38:41,955 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5853 +[2025-02-22 13:38:42,095 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3562 +[2025-02-22 13:38:42,158 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2082 +[2025-02-22 13:38:42,406 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2156 +[2025-02-22 13:38:42,519 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.4915 +[2025-02-22 13:38:42,600 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4063 +[2025-02-22 13:38:42,700 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6539 +[2025-02-22 13:38:42,792 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0050 +[2025-02-22 13:38:42,881 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6868 +[2025-02-22 13:38:43,022 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5907 +[2025-02-22 13:38:43,134 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3525 +[2025-02-22 13:38:43,294 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.0921 +[2025-02-22 13:38:43,367 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0550 +[2025-02-22 13:38:43,532 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6369 +[2025-02-22 13:38:43,687 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0248 +[2025-02-22 13:38:43,777 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0953 +[2025-02-22 13:38:43,847 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0006 +[2025-02-22 13:38:43,929 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2019 +[2025-02-22 13:38:43,990 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.4861 +[2025-02-22 13:38:44,148 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.1136 +[2025-02-22 13:38:44,252 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6082 +[2025-02-22 13:38:44,338 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.6855 +[2025-02-22 13:38:44,423 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7485 +[2025-02-22 13:38:45,264 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5639 +[2025-02-22 13:38:45,403 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0224 +[2025-02-22 13:38:45,449 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6644 +[2025-02-22 13:38:45,553 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.1690 +[2025-02-22 13:38:45,604 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4986 +[2025-02-22 13:38:45,732 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9854 +[2025-02-22 13:38:45,811 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7559 +[2025-02-22 13:38:45,974 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7391 +[2025-02-22 13:38:46,171 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3996 +[2025-02-22 13:38:46,399 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8897 +[2025-02-22 13:38:46,605 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5555 +[2025-02-22 13:38:46,690 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3142 +[2025-02-22 13:38:46,756 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8140 +[2025-02-22 13:38:47,079 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6930 +[2025-02-22 13:38:47,181 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4771 +[2025-02-22 13:38:47,258 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5337 +[2025-02-22 13:38:47,377 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2305 +[2025-02-22 13:38:47,559 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3587 +[2025-02-22 13:38:47,695 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1330 +[2025-02-22 13:38:47,802 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.3845 +[2025-02-22 13:38:47,891 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.4149 +[2025-02-22 13:38:48,042 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5323 +[2025-02-22 13:38:48,088 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.3791 +[2025-02-22 13:38:48,201 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.4056 +[2025-02-22 13:38:48,305 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8867 +[2025-02-22 13:38:48,362 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6881 +[2025-02-22 13:38:48,551 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2357 +[2025-02-22 13:38:48,602 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5543 +[2025-02-22 13:38:48,885 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3730 +[2025-02-22 13:38:48,999 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2088 +[2025-02-22 13:38:49,080 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5524 +[2025-02-22 13:38:49,144 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.3455 +[2025-02-22 13:38:49,334 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0940 +[2025-02-22 13:38:49,453 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0005 +[2025-02-22 13:38:49,541 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1670 +[2025-02-22 13:38:49,715 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2347 +[2025-02-22 13:38:49,931 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6848 +[2025-02-22 13:38:50,045 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1410 +[2025-02-22 13:38:50,109 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6978 +[2025-02-22 13:38:50,179 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.0365 +[2025-02-22 13:38:50,354 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2110 +[2025-02-22 13:38:50,397 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5986 +[2025-02-22 13:38:50,458 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7873 +[2025-02-22 13:38:50,592 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5402 +[2025-02-22 13:38:50,852 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6226 +[2025-02-22 13:38:50,950 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.3165 +[2025-02-22 13:38:51,161 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6010 +[2025-02-22 13:38:51,264 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6501 +[2025-02-22 13:39:03,503 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:39:03,503 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:39:03,503 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] cabinet : 0.2610 0.4988 0.6995 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] bed : 0.3428 0.7401 0.8395 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] chair : 0.7277 0.8845 0.9305 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] sofa : 0.3021 0.5330 0.7750 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] table : 0.4050 0.6627 0.7879 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] door : 0.2490 0.4662 0.6100 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] window : 0.2598 0.4547 0.6413 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] bookshelf : 0.2746 0.5863 0.7354 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] picture : 0.3162 0.4287 0.4958 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] counter : 0.0549 0.1814 0.6150 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] desk : 0.1213 0.3746 0.8072 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] curtain : 0.2902 0.4962 0.6805 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] refridgerator : 0.3616 0.5214 0.5834 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] shower curtain : 0.4860 0.6149 0.7081 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] toilet : 0.8314 0.9483 0.9816 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] sink : 0.4010 0.7017 0.8868 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] bathtub : 0.6593 0.7742 0.8710 +[2025-02-22 13:39:03,503 INFO evaluator.py line 547 2775932] otherfurniture : 0.3954 0.5905 0.6724 +[2025-02-22 13:39:03,503 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:39:03,503 INFO evaluator.py line 554 2775932] average : 0.3744 0.5810 0.7400 +[2025-02-22 13:39:03,503 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:39:03,503 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:39:03,533 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5810 +[2025-02-22 13:39:03,541 INFO misc.py line 164 2775932] Currently Best AP50: 0.5810 +[2025-02-22 13:39:03,541 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:39:12,748 INFO hook.py line 109 2775932] Train: [72/100][50/800] Data 0.003 (0.003) Batch 0.129 (0.148) Remain 00:57:04 loss: -0.6891 Lr: 1.27465e-03 +[2025-02-22 13:39:20,124 INFO hook.py line 109 2775932] Train: [72/100][100/800] Data 0.003 (0.005) Batch 0.147 (0.148) Remain 00:56:51 loss: -0.6014 Lr: 1.26958e-03 +[2025-02-22 13:39:27,276 INFO hook.py line 109 2775932] Train: [72/100][150/800] Data 0.004 (0.005) Batch 0.131 (0.146) Remain 00:56:08 loss: -0.5315 Lr: 1.26452e-03 +[2025-02-22 13:39:34,537 INFO hook.py line 109 2775932] Train: [72/100][200/800] Data 0.003 (0.004) Batch 0.137 (0.146) Remain 00:55:55 loss: -0.4934 Lr: 1.25946e-03 +[2025-02-22 13:39:41,636 INFO hook.py line 109 2775932] Train: [72/100][250/800] Data 0.002 (0.004) Batch 0.130 (0.145) Remain 00:55:29 loss: -0.7097 Lr: 1.25442e-03 +[2025-02-22 13:39:48,595 INFO hook.py line 109 2775932] Train: [72/100][300/800] Data 0.004 (0.004) Batch 0.133 (0.144) Remain 00:54:59 loss: -0.6745 Lr: 1.24938e-03 +[2025-02-22 13:39:55,784 INFO hook.py line 109 2775932] Train: [72/100][350/800] Data 0.003 (0.004) Batch 0.148 (0.144) Remain 00:54:51 loss: -0.7156 Lr: 1.24435e-03 +[2025-02-22 13:40:03,074 INFO hook.py line 109 2775932] Train: [72/100][400/800] Data 0.003 (0.004) Batch 0.160 (0.144) Remain 00:54:49 loss: -0.6911 Lr: 1.23933e-03 +[2025-02-22 13:40:10,114 INFO hook.py line 109 2775932] Train: [72/100][450/800] Data 0.003 (0.003) Batch 0.134 (0.144) Remain 00:54:33 loss: -0.6608 Lr: 1.23431e-03 +[2025-02-22 13:40:17,041 INFO hook.py line 109 2775932] Train: [72/100][500/800] Data 0.002 (0.003) Batch 0.122 (0.143) Remain 00:54:13 loss: -0.5861 Lr: 1.22931e-03 +[2025-02-22 13:40:24,040 INFO hook.py line 109 2775932] Train: [72/100][550/800] Data 0.004 (0.003) Batch 0.147 (0.143) Remain 00:53:59 loss: -0.7457 Lr: 1.22430e-03 +[2025-02-22 13:40:30,890 INFO hook.py line 109 2775932] Train: [72/100][600/800] Data 0.003 (0.003) Batch 0.164 (0.143) Remain 00:53:41 loss: -0.5805 Lr: 1.21931e-03 +[2025-02-22 13:40:38,469 INFO hook.py line 109 2775932] Train: [72/100][650/800] Data 0.003 (0.003) Batch 0.162 (0.143) Remain 00:53:49 loss: -0.6986 Lr: 1.21433e-03 +[2025-02-22 13:40:45,431 INFO hook.py line 109 2775932] Train: [72/100][700/800] Data 0.003 (0.003) Batch 0.122 (0.143) Remain 00:53:36 loss: -0.3284 Lr: 1.20935e-03 +[2025-02-22 13:40:52,607 INFO hook.py line 109 2775932] Train: [72/100][750/800] Data 0.003 (0.003) Batch 0.139 (0.143) Remain 00:53:29 loss: -0.6190 Lr: 1.20438e-03 +[2025-02-22 13:40:59,851 INFO hook.py line 109 2775932] Train: [72/100][800/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 00:53:25 loss: -0.7409 Lr: 1.19942e-03 +[2025-02-22 13:40:59,852 INFO misc.py line 135 2775932] Train result: loss: -0.6455 seg_loss: 0.1329 bias_l1_loss: 0.1788 bias_cosine_loss: -0.9572 +[2025-02-22 13:40:59,852 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:41:06,647 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8275 +[2025-02-22 13:41:07,717 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5668 +[2025-02-22 13:41:07,786 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6221 +[2025-02-22 13:41:07,861 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6626 +[2025-02-22 13:41:07,942 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7519 +[2025-02-22 13:41:08,003 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.2434 +[2025-02-22 13:41:08,285 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6596 +[2025-02-22 13:41:08,316 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4772 +[2025-02-22 13:41:08,455 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3720 +[2025-02-22 13:41:08,529 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.3327 +[2025-02-22 13:41:08,801 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0143 +[2025-02-22 13:41:08,923 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0184 +[2025-02-22 13:41:09,008 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2059 +[2025-02-22 13:41:09,116 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 0.9044 +[2025-02-22 13:41:09,210 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0757 +[2025-02-22 13:41:09,300 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6952 +[2025-02-22 13:41:09,442 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6309 +[2025-02-22 13:41:09,552 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.5526 +[2025-02-22 13:41:09,710 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1243 +[2025-02-22 13:41:09,800 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.2457 +[2025-02-22 13:41:09,999 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6830 +[2025-02-22 13:41:10,216 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.0283 +[2025-02-22 13:41:10,309 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0721 +[2025-02-22 13:41:10,384 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0606 +[2025-02-22 13:41:10,469 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3232 +[2025-02-22 13:41:10,535 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5762 +[2025-02-22 13:41:10,705 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0284 +[2025-02-22 13:41:10,833 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6141 +[2025-02-22 13:41:10,923 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7502 +[2025-02-22 13:41:11,005 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5340 +[2025-02-22 13:41:12,009 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5656 +[2025-02-22 13:41:12,198 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0105 +[2025-02-22 13:41:12,244 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6650 +[2025-02-22 13:41:12,363 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2191 +[2025-02-22 13:41:12,418 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4255 +[2025-02-22 13:41:12,544 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0010 +[2025-02-22 13:41:12,647 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6509 +[2025-02-22 13:41:12,809 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7427 +[2025-02-22 13:41:13,017 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6784 +[2025-02-22 13:41:13,287 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.6468 +[2025-02-22 13:41:13,478 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4502 +[2025-02-22 13:41:13,575 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4486 +[2025-02-22 13:41:13,628 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7823 +[2025-02-22 13:41:13,957 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7390 +[2025-02-22 13:41:14,019 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5784 +[2025-02-22 13:41:14,075 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5160 +[2025-02-22 13:41:14,191 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5021 +[2025-02-22 13:41:14,343 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5100 +[2025-02-22 13:41:14,475 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3014 +[2025-02-22 13:41:14,577 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0547 +[2025-02-22 13:41:14,671 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2398 +[2025-02-22 13:41:14,805 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4467 +[2025-02-22 13:41:14,845 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4635 +[2025-02-22 13:41:14,968 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.7779 +[2025-02-22 13:41:15,073 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8668 +[2025-02-22 13:41:15,130 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7966 +[2025-02-22 13:41:15,290 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1688 +[2025-02-22 13:41:15,333 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5368 +[2025-02-22 13:41:15,579 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.5314 +[2025-02-22 13:41:15,689 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3074 +[2025-02-22 13:41:15,791 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5852 +[2025-02-22 13:41:15,855 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4769 +[2025-02-22 13:41:16,040 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3502 +[2025-02-22 13:41:16,147 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0605 +[2025-02-22 13:41:16,237 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1001 +[2025-02-22 13:41:16,382 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1999 +[2025-02-22 13:41:16,565 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7744 +[2025-02-22 13:41:16,672 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0715 +[2025-02-22 13:41:16,732 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7686 +[2025-02-22 13:41:16,795 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4393 +[2025-02-22 13:41:16,976 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1670 +[2025-02-22 13:41:17,021 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5396 +[2025-02-22 13:41:17,081 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7976 +[2025-02-22 13:41:17,195 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7519 +[2025-02-22 13:41:17,434 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6865 +[2025-02-22 13:41:17,528 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1377 +[2025-02-22 13:41:17,716 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6269 +[2025-02-22 13:41:17,823 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6972 +[2025-02-22 13:41:31,997 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:41:31,997 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:41:31,997 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] cabinet : 0.2639 0.4989 0.7089 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] bed : 0.3444 0.7215 0.8392 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] chair : 0.7571 0.9085 0.9447 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] sofa : 0.3468 0.5832 0.7964 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] table : 0.4455 0.6618 0.7825 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] door : 0.2647 0.4705 0.6189 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] window : 0.2617 0.4586 0.6410 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] bookshelf : 0.2420 0.5128 0.7605 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] picture : 0.3465 0.4991 0.6067 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] counter : 0.0329 0.1373 0.6710 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] desk : 0.1326 0.4032 0.7875 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] curtain : 0.3067 0.4974 0.6441 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] refridgerator : 0.3561 0.4725 0.5427 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] shower curtain : 0.4293 0.5387 0.5949 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] toilet : 0.8131 0.9963 0.9963 +[2025-02-22 13:41:31,997 INFO evaluator.py line 547 2775932] sink : 0.3934 0.6611 0.8456 +[2025-02-22 13:41:31,998 INFO evaluator.py line 547 2775932] bathtub : 0.6251 0.7393 0.8673 +[2025-02-22 13:41:31,998 INFO evaluator.py line 547 2775932] otherfurniture : 0.3946 0.5605 0.6557 +[2025-02-22 13:41:31,998 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:41:31,998 INFO evaluator.py line 554 2775932] average : 0.3753 0.5734 0.7391 +[2025-02-22 13:41:31,998 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:41:31,998 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:41:32,025 INFO misc.py line 164 2775932] Currently Best AP50: 0.5810 +[2025-02-22 13:41:32,031 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:41:41,202 INFO hook.py line 109 2775932] Train: [73/100][50/800] Data 0.003 (0.003) Batch 0.141 (0.148) Remain 00:55:06 loss: -0.4731 Lr: 1.19446e-03 +[2025-02-22 13:41:48,159 INFO hook.py line 109 2775932] Train: [73/100][100/800] Data 0.003 (0.003) Batch 0.119 (0.143) Remain 00:53:18 loss: -0.5881 Lr: 1.18952e-03 +[2025-02-22 13:41:55,175 INFO hook.py line 109 2775932] Train: [73/100][150/800] Data 0.002 (0.003) Batch 0.143 (0.142) Remain 00:52:47 loss: -0.7626 Lr: 1.18458e-03 +[2025-02-22 13:42:02,391 INFO hook.py line 109 2775932] Train: [73/100][200/800] Data 0.004 (0.003) Batch 0.131 (0.143) Remain 00:52:51 loss: -0.6447 Lr: 1.17965e-03 +[2025-02-22 13:42:09,634 INFO hook.py line 109 2775932] Train: [73/100][250/800] Data 0.003 (0.003) Batch 0.123 (0.143) Remain 00:52:53 loss: -0.6489 Lr: 1.17472e-03 +[2025-02-22 13:42:16,837 INFO hook.py line 109 2775932] Train: [73/100][300/800] Data 0.002 (0.004) Batch 0.134 (0.143) Remain 00:52:49 loss: -0.7088 Lr: 1.16981e-03 +[2025-02-22 13:42:23,801 INFO hook.py line 109 2775932] Train: [73/100][350/800] Data 0.003 (0.004) Batch 0.142 (0.143) Remain 00:52:28 loss: -0.6572 Lr: 1.16490e-03 +[2025-02-22 13:42:30,712 INFO hook.py line 109 2775932] Train: [73/100][400/800] Data 0.003 (0.004) Batch 0.147 (0.142) Remain 00:52:08 loss: -0.7155 Lr: 1.16000e-03 +[2025-02-22 13:42:37,738 INFO hook.py line 109 2775932] Train: [73/100][450/800] Data 0.002 (0.004) Batch 0.165 (0.142) Remain 00:51:57 loss: -0.7955 Lr: 1.15511e-03 +[2025-02-22 13:42:44,917 INFO hook.py line 109 2775932] Train: [73/100][500/800] Data 0.002 (0.003) Batch 0.150 (0.142) Remain 00:51:53 loss: -0.5445 Lr: 1.15022e-03 +[2025-02-22 13:42:51,950 INFO hook.py line 109 2775932] Train: [73/100][550/800] Data 0.003 (0.003) Batch 0.131 (0.142) Remain 00:51:43 loss: -0.4790 Lr: 1.14535e-03 +[2025-02-22 13:42:59,343 INFO hook.py line 109 2775932] Train: [73/100][600/800] Data 0.003 (0.003) Batch 0.157 (0.143) Remain 00:51:47 loss: -0.5192 Lr: 1.14048e-03 +[2025-02-22 13:43:06,572 INFO hook.py line 109 2775932] Train: [73/100][650/800] Data 0.003 (0.003) Batch 0.140 (0.143) Remain 00:51:43 loss: -0.6720 Lr: 1.13562e-03 +[2025-02-22 13:43:13,715 INFO hook.py line 109 2775932] Train: [73/100][700/800] Data 0.002 (0.003) Batch 0.124 (0.143) Remain 00:51:36 loss: -0.7227 Lr: 1.13077e-03 +[2025-02-22 13:43:20,937 INFO hook.py line 109 2775932] Train: [73/100][750/800] Data 0.003 (0.003) Batch 0.117 (0.143) Remain 00:51:32 loss: -0.8316 Lr: 1.12592e-03 +[2025-02-22 13:43:27,638 INFO hook.py line 109 2775932] Train: [73/100][800/800] Data 0.002 (0.003) Batch 0.109 (0.142) Remain 00:51:13 loss: -0.6005 Lr: 1.12108e-03 +[2025-02-22 13:43:27,639 INFO misc.py line 135 2775932] Train result: loss: -0.6457 seg_loss: 0.1317 bias_l1_loss: 0.1791 bias_cosine_loss: -0.9566 +[2025-02-22 13:43:27,639 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:43:34,855 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8483 +[2025-02-22 13:43:35,391 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6732 +[2025-02-22 13:43:35,461 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.5927 +[2025-02-22 13:43:35,532 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.7144 +[2025-02-22 13:43:35,650 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6662 +[2025-02-22 13:43:35,721 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7219 +[2025-02-22 13:43:36,007 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6485 +[2025-02-22 13:43:36,041 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3282 +[2025-02-22 13:43:36,180 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3745 +[2025-02-22 13:43:36,356 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0526 +[2025-02-22 13:43:36,642 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.0101 +[2025-02-22 13:43:36,775 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0879 +[2025-02-22 13:43:36,862 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2334 +[2025-02-22 13:43:36,972 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2933 +[2025-02-22 13:43:37,070 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0419 +[2025-02-22 13:43:37,159 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6709 +[2025-02-22 13:43:37,300 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5758 +[2025-02-22 13:43:37,407 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3422 +[2025-02-22 13:43:37,570 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2187 +[2025-02-22 13:43:37,638 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1167 +[2025-02-22 13:43:37,804 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6940 +[2025-02-22 13:43:37,986 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1196 +[2025-02-22 13:43:38,075 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0648 +[2025-02-22 13:43:38,149 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1008 +[2025-02-22 13:43:38,228 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1614 +[2025-02-22 13:43:38,306 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6013 +[2025-02-22 13:43:38,454 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0240 +[2025-02-22 13:43:38,569 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5713 +[2025-02-22 13:43:38,646 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7115 +[2025-02-22 13:43:38,733 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6167 +[2025-02-22 13:43:39,548 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6208 +[2025-02-22 13:43:39,711 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5911 +[2025-02-22 13:43:39,753 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6255 +[2025-02-22 13:43:39,869 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4158 +[2025-02-22 13:43:39,915 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4721 +[2025-02-22 13:43:40,029 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9052 +[2025-02-22 13:43:40,100 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5964 +[2025-02-22 13:43:40,240 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7649 +[2025-02-22 13:43:40,411 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.1295 +[2025-02-22 13:43:40,627 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8573 +[2025-02-22 13:43:40,808 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3786 +[2025-02-22 13:43:40,860 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3340 +[2025-02-22 13:43:40,906 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8132 +[2025-02-22 13:43:41,188 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6141 +[2025-02-22 13:43:41,240 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4813 +[2025-02-22 13:43:41,304 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5373 +[2025-02-22 13:43:41,445 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7984 +[2025-02-22 13:43:41,601 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5244 +[2025-02-22 13:43:41,731 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2642 +[2025-02-22 13:43:41,836 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0773 +[2025-02-22 13:43:41,937 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.1126 +[2025-02-22 13:43:42,099 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3483 +[2025-02-22 13:43:42,147 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4866 +[2025-02-22 13:43:42,272 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.7033 +[2025-02-22 13:43:42,386 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8705 +[2025-02-22 13:43:42,437 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5974 +[2025-02-22 13:43:42,592 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2068 +[2025-02-22 13:43:42,638 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5757 +[2025-02-22 13:43:42,897 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3714 +[2025-02-22 13:43:43,013 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.0335 +[2025-02-22 13:43:43,108 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4175 +[2025-02-22 13:43:43,175 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6045 +[2025-02-22 13:43:43,400 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1341 +[2025-02-22 13:43:43,532 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.1707 +[2025-02-22 13:43:43,631 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1495 +[2025-02-22 13:43:43,937 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1491 +[2025-02-22 13:43:44,160 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.6523 +[2025-02-22 13:43:44,295 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1185 +[2025-02-22 13:43:44,382 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6819 +[2025-02-22 13:43:44,448 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2412 +[2025-02-22 13:43:44,689 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3587 +[2025-02-22 13:43:44,747 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4786 +[2025-02-22 13:43:44,822 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7989 +[2025-02-22 13:43:44,959 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7081 +[2025-02-22 13:43:45,209 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6394 +[2025-02-22 13:43:45,313 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.3056 +[2025-02-22 13:43:45,525 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6587 +[2025-02-22 13:43:45,644 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6531 +[2025-02-22 13:43:58,856 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:43:58,856 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:43:58,856 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] cabinet : 0.2600 0.4944 0.6832 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] bed : 0.3563 0.7158 0.8759 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] chair : 0.7461 0.8968 0.9397 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] sofa : 0.3712 0.6126 0.8255 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] table : 0.4250 0.6243 0.7467 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] door : 0.2692 0.5008 0.6419 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] window : 0.2389 0.4428 0.6384 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] bookshelf : 0.2587 0.5097 0.7186 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] picture : 0.3702 0.5174 0.6100 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] counter : 0.0236 0.0943 0.5199 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] desk : 0.1173 0.3440 0.8023 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] curtain : 0.2920 0.5261 0.6729 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] refridgerator : 0.3517 0.4698 0.5098 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] shower curtain : 0.4930 0.6416 0.7600 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] toilet : 0.8678 1.0000 1.0000 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] sink : 0.3949 0.6909 0.8489 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] bathtub : 0.6324 0.8011 0.8698 +[2025-02-22 13:43:58,856 INFO evaluator.py line 547 2775932] otherfurniture : 0.4102 0.5889 0.6747 +[2025-02-22 13:43:58,856 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:43:58,856 INFO evaluator.py line 554 2775932] average : 0.3821 0.5817 0.7410 +[2025-02-22 13:43:58,856 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:43:58,856 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:43:58,889 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5817 +[2025-02-22 13:43:58,896 INFO misc.py line 164 2775932] Currently Best AP50: 0.5817 +[2025-02-22 13:43:58,896 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:44:07,876 INFO hook.py line 109 2775932] Train: [74/100][50/800] Data 0.002 (0.003) Batch 0.146 (0.145) Remain 00:52:11 loss: -0.5840 Lr: 1.11626e-03 +[2025-02-22 13:44:15,154 INFO hook.py line 109 2775932] Train: [74/100][100/800] Data 0.003 (0.003) Batch 0.167 (0.145) Remain 00:52:06 loss: -0.7147 Lr: 1.11144e-03 +[2025-02-22 13:44:22,438 INFO hook.py line 109 2775932] Train: [74/100][150/800] Data 0.002 (0.003) Batch 0.126 (0.146) Remain 00:52:01 loss: -0.7041 Lr: 1.10662e-03 +[2025-02-22 13:44:29,571 INFO hook.py line 109 2775932] Train: [74/100][200/800] Data 0.003 (0.004) Batch 0.149 (0.145) Remain 00:51:38 loss: -0.6377 Lr: 1.10182e-03 +[2025-02-22 13:44:36,642 INFO hook.py line 109 2775932] Train: [74/100][250/800] Data 0.003 (0.004) Batch 0.136 (0.144) Remain 00:51:16 loss: -0.7288 Lr: 1.09702e-03 +[2025-02-22 13:44:43,710 INFO hook.py line 109 2775932] Train: [74/100][300/800] Data 0.003 (0.004) Batch 0.124 (0.144) Remain 00:50:59 loss: -0.5989 Lr: 1.09223e-03 +[2025-02-22 13:44:50,881 INFO hook.py line 109 2775932] Train: [74/100][350/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 00:50:51 loss: -0.6886 Lr: 1.08746e-03 +[2025-02-22 13:44:57,920 INFO hook.py line 109 2775932] Train: [74/100][400/800] Data 0.003 (0.004) Batch 0.132 (0.143) Remain 00:50:37 loss: -0.7556 Lr: 1.08268e-03 +[2025-02-22 13:45:05,090 INFO hook.py line 109 2775932] Train: [74/100][450/800] Data 0.003 (0.004) Batch 0.134 (0.143) Remain 00:50:30 loss: -0.6420 Lr: 1.07792e-03 +[2025-02-22 13:45:12,020 INFO hook.py line 109 2775932] Train: [74/100][500/800] Data 0.003 (0.003) Batch 0.137 (0.143) Remain 00:50:13 loss: -0.7241 Lr: 1.07316e-03 +[2025-02-22 13:45:19,256 INFO hook.py line 109 2775932] Train: [74/100][550/800] Data 0.004 (0.003) Batch 0.133 (0.143) Remain 00:50:09 loss: -0.5528 Lr: 1.06842e-03 +[2025-02-22 13:45:26,409 INFO hook.py line 109 2775932] Train: [74/100][600/800] Data 0.005 (0.003) Batch 0.133 (0.143) Remain 00:50:02 loss: -0.6930 Lr: 1.06368e-03 +[2025-02-22 13:45:33,798 INFO hook.py line 109 2775932] Train: [74/100][650/800] Data 0.003 (0.003) Batch 0.251 (0.143) Remain 00:50:03 loss: -0.6435 Lr: 1.05895e-03 +[2025-02-22 13:45:40,902 INFO hook.py line 109 2775932] Train: [74/100][700/800] Data 0.003 (0.003) Batch 0.125 (0.143) Remain 00:49:54 loss: -0.7803 Lr: 1.05423e-03 +[2025-02-22 13:45:47,941 INFO hook.py line 109 2775932] Train: [74/100][750/800] Data 0.003 (0.003) Batch 0.127 (0.143) Remain 00:49:43 loss: -0.7078 Lr: 1.04951e-03 +[2025-02-22 13:45:54,982 INFO hook.py line 109 2775932] Train: [74/100][800/800] Data 0.003 (0.003) Batch 0.114 (0.143) Remain 00:49:33 loss: -0.6685 Lr: 1.04481e-03 +[2025-02-22 13:45:54,982 INFO misc.py line 135 2775932] Train result: loss: -0.6558 seg_loss: 0.1275 bias_l1_loss: 0.1751 bias_cosine_loss: -0.9584 +[2025-02-22 13:45:54,983 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:46:01,795 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8580 +[2025-02-22 13:46:02,290 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6773 +[2025-02-22 13:46:02,405 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6334 +[2025-02-22 13:46:02,491 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6490 +[2025-02-22 13:46:02,568 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.6926 +[2025-02-22 13:46:02,798 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.1701 +[2025-02-22 13:46:03,145 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5919 +[2025-02-22 13:46:03,189 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5618 +[2025-02-22 13:46:03,344 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.4452 +[2025-02-22 13:46:03,406 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1596 +[2025-02-22 13:46:03,691 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1650 +[2025-02-22 13:46:03,818 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0246 +[2025-02-22 13:46:03,910 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2580 +[2025-02-22 13:46:04,019 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.4875 +[2025-02-22 13:46:04,128 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0432 +[2025-02-22 13:46:04,225 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6627 +[2025-02-22 13:46:04,380 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6664 +[2025-02-22 13:46:04,502 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3906 +[2025-02-22 13:46:04,669 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1490 +[2025-02-22 13:46:04,762 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1083 +[2025-02-22 13:46:04,958 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.6774 +[2025-02-22 13:46:05,161 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3613 +[2025-02-22 13:46:05,261 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0234 +[2025-02-22 13:46:05,329 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0691 +[2025-02-22 13:46:05,417 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1896 +[2025-02-22 13:46:05,483 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5918 +[2025-02-22 13:46:05,637 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0148 +[2025-02-22 13:46:05,760 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6115 +[2025-02-22 13:46:05,852 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7394 +[2025-02-22 13:46:05,931 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6456 +[2025-02-22 13:46:06,902 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5470 +[2025-02-22 13:46:07,086 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3211 +[2025-02-22 13:46:07,134 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6646 +[2025-02-22 13:46:07,267 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3311 +[2025-02-22 13:46:07,311 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5361 +[2025-02-22 13:46:07,452 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9370 +[2025-02-22 13:46:07,534 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6648 +[2025-02-22 13:46:07,712 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7466 +[2025-02-22 13:46:07,937 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5602 +[2025-02-22 13:46:08,180 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9414 +[2025-02-22 13:46:08,382 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5164 +[2025-02-22 13:46:08,447 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3143 +[2025-02-22 13:46:08,498 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8497 +[2025-02-22 13:46:08,777 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7624 +[2025-02-22 13:46:08,837 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6503 +[2025-02-22 13:46:08,885 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5375 +[2025-02-22 13:46:08,993 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1810 +[2025-02-22 13:46:09,135 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6592 +[2025-02-22 13:46:09,269 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1221 +[2025-02-22 13:46:09,396 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0599 +[2025-02-22 13:46:09,531 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1952 +[2025-02-22 13:46:09,695 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4337 +[2025-02-22 13:46:09,748 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5944 +[2025-02-22 13:46:09,889 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.6752 +[2025-02-22 13:46:09,996 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8965 +[2025-02-22 13:46:10,051 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.8270 +[2025-02-22 13:46:10,215 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1021 +[2025-02-22 13:46:10,269 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6085 +[2025-02-22 13:46:10,522 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3230 +[2025-02-22 13:46:10,635 INFO evaluator.py line 595 2775932] Test: [60/78] Loss 0.2223 +[2025-02-22 13:46:10,729 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3395 +[2025-02-22 13:46:10,791 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5684 +[2025-02-22 13:46:10,960 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0632 +[2025-02-22 13:46:11,079 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0302 +[2025-02-22 13:46:11,162 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1697 +[2025-02-22 13:46:11,317 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1258 +[2025-02-22 13:46:11,508 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7267 +[2025-02-22 13:46:11,632 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1725 +[2025-02-22 13:46:11,694 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7320 +[2025-02-22 13:46:11,765 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2950 +[2025-02-22 13:46:11,966 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3323 +[2025-02-22 13:46:12,011 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6773 +[2025-02-22 13:46:12,081 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8439 +[2025-02-22 13:46:12,207 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6825 +[2025-02-22 13:46:12,449 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6780 +[2025-02-22 13:46:12,541 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0853 +[2025-02-22 13:46:12,732 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6417 +[2025-02-22 13:46:12,848 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6832 +[2025-02-22 13:46:25,383 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:46:25,383 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:46:25,383 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] cabinet : 0.2831 0.5289 0.7178 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] bed : 0.3647 0.6997 0.8395 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] chair : 0.7510 0.9075 0.9438 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] sofa : 0.3412 0.5529 0.7734 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] table : 0.3995 0.6446 0.7893 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] door : 0.2702 0.5013 0.6103 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] window : 0.2548 0.4505 0.6506 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] bookshelf : 0.2156 0.4989 0.7212 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] picture : 0.3419 0.4799 0.5614 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] counter : 0.0094 0.0393 0.4340 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] desk : 0.1247 0.3860 0.7970 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] curtain : 0.2975 0.4951 0.6429 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] refridgerator : 0.3750 0.5030 0.5690 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] shower curtain : 0.4623 0.6242 0.7147 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] toilet : 0.8781 0.9882 0.9882 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] sink : 0.4232 0.6951 0.8714 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] bathtub : 0.6377 0.7647 0.9010 +[2025-02-22 13:46:25,383 INFO evaluator.py line 547 2775932] otherfurniture : 0.3797 0.5512 0.6495 +[2025-02-22 13:46:25,383 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:46:25,383 INFO evaluator.py line 554 2775932] average : 0.3783 0.5728 0.7319 +[2025-02-22 13:46:25,383 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:46:25,383 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:46:25,414 INFO misc.py line 164 2775932] Currently Best AP50: 0.5817 +[2025-02-22 13:46:25,422 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:46:34,856 INFO hook.py line 109 2775932] Train: [75/100][50/800] Data 0.003 (0.009) Batch 0.133 (0.156) Remain 00:53:59 loss: -0.7699 Lr: 1.04011e-03 +[2025-02-22 13:46:42,201 INFO hook.py line 109 2775932] Train: [75/100][100/800] Data 0.003 (0.006) Batch 0.253 (0.151) Remain 00:52:13 loss: -0.7636 Lr: 1.03542e-03 +[2025-02-22 13:46:49,230 INFO hook.py line 109 2775932] Train: [75/100][150/800] Data 0.003 (0.005) Batch 0.155 (0.148) Remain 00:50:50 loss: -0.5702 Lr: 1.03074e-03 +[2025-02-22 13:46:56,522 INFO hook.py line 109 2775932] Train: [75/100][200/800] Data 0.003 (0.004) Batch 0.142 (0.147) Remain 00:50:32 loss: -0.7734 Lr: 1.02607e-03 +[2025-02-22 13:47:03,593 INFO hook.py line 109 2775932] Train: [75/100][250/800] Data 0.003 (0.004) Batch 0.128 (0.146) Remain 00:50:01 loss: -0.4810 Lr: 1.02140e-03 +[2025-02-22 13:47:10,738 INFO hook.py line 109 2775932] Train: [75/100][300/800] Data 0.002 (0.004) Batch 0.147 (0.146) Remain 00:49:43 loss: -0.6294 Lr: 1.01675e-03 +[2025-02-22 13:47:18,077 INFO hook.py line 109 2775932] Train: [75/100][350/800] Data 0.010 (0.004) Batch 0.141 (0.146) Remain 00:49:39 loss: -0.6613 Lr: 1.01210e-03 +[2025-02-22 13:47:25,294 INFO hook.py line 109 2775932] Train: [75/100][400/800] Data 0.004 (0.004) Batch 0.155 (0.146) Remain 00:49:28 loss: -0.6219 Lr: 1.00746e-03 +[2025-02-22 13:47:32,530 INFO hook.py line 109 2775932] Train: [75/100][450/800] Data 0.003 (0.004) Batch 0.111 (0.145) Remain 00:49:19 loss: -0.6440 Lr: 1.00283e-03 +[2025-02-22 13:47:39,550 INFO hook.py line 109 2775932] Train: [75/100][500/800] Data 0.003 (0.004) Batch 0.140 (0.145) Remain 00:49:02 loss: -0.6429 Lr: 9.98213e-04 +[2025-02-22 13:47:46,522 INFO hook.py line 109 2775932] Train: [75/100][550/800] Data 0.003 (0.004) Batch 0.162 (0.144) Remain 00:48:44 loss: -0.7217 Lr: 9.93600e-04 +[2025-02-22 13:47:53,785 INFO hook.py line 109 2775932] Train: [75/100][600/800] Data 0.002 (0.004) Batch 0.150 (0.144) Remain 00:48:38 loss: -0.6680 Lr: 9.88996e-04 +[2025-02-22 13:48:00,884 INFO hook.py line 109 2775932] Train: [75/100][650/800] Data 0.003 (0.004) Batch 0.124 (0.144) Remain 00:48:27 loss: -0.7600 Lr: 9.84493e-04 +[2025-02-22 13:48:08,226 INFO hook.py line 109 2775932] Train: [75/100][700/800] Data 0.002 (0.004) Batch 0.163 (0.144) Remain 00:48:24 loss: -0.5308 Lr: 9.79906e-04 +[2025-02-22 13:48:15,229 INFO hook.py line 109 2775932] Train: [75/100][750/800] Data 0.002 (0.003) Batch 0.145 (0.144) Remain 00:48:10 loss: -0.7812 Lr: 9.75327e-04 +[2025-02-22 13:48:21,908 INFO hook.py line 109 2775932] Train: [75/100][800/800] Data 0.002 (0.003) Batch 0.115 (0.144) Remain 00:47:50 loss: -0.6677 Lr: 9.70758e-04 +[2025-02-22 13:48:21,909 INFO misc.py line 135 2775932] Train result: loss: -0.6652 seg_loss: 0.1234 bias_l1_loss: 0.1714 bias_cosine_loss: -0.9601 +[2025-02-22 13:48:21,909 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:48:29,367 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8563 +[2025-02-22 13:48:29,562 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6754 +[2025-02-22 13:48:29,639 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6468 +[2025-02-22 13:48:29,714 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6711 +[2025-02-22 13:48:29,802 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7694 +[2025-02-22 13:48:29,865 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9647 +[2025-02-22 13:48:30,219 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6111 +[2025-02-22 13:48:30,250 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4583 +[2025-02-22 13:48:30,406 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.4163 +[2025-02-22 13:48:30,482 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0383 +[2025-02-22 13:48:30,755 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1130 +[2025-02-22 13:48:30,891 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0908 +[2025-02-22 13:48:30,990 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0643 +[2025-02-22 13:48:31,095 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2791 +[2025-02-22 13:48:31,192 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.1062 +[2025-02-22 13:48:31,269 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6454 +[2025-02-22 13:48:31,411 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6915 +[2025-02-22 13:48:31,523 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3206 +[2025-02-22 13:48:31,721 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2243 +[2025-02-22 13:48:31,795 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0167 +[2025-02-22 13:48:31,969 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7136 +[2025-02-22 13:48:32,185 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2629 +[2025-02-22 13:48:32,282 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.1040 +[2025-02-22 13:48:32,343 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.1806 +[2025-02-22 13:48:32,428 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1034 +[2025-02-22 13:48:32,484 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5469 +[2025-02-22 13:48:32,647 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0881 +[2025-02-22 13:48:32,758 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6115 +[2025-02-22 13:48:32,837 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7580 +[2025-02-22 13:48:32,913 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7224 +[2025-02-22 13:48:33,962 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6254 +[2025-02-22 13:48:34,167 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4719 +[2025-02-22 13:48:34,220 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.8136 +[2025-02-22 13:48:34,341 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4177 +[2025-02-22 13:48:34,393 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6564 +[2025-02-22 13:48:34,530 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.9295 +[2025-02-22 13:48:34,617 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6794 +[2025-02-22 13:48:34,781 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6658 +[2025-02-22 13:48:34,971 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.0752 +[2025-02-22 13:48:35,240 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.8684 +[2025-02-22 13:48:35,425 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.1887 +[2025-02-22 13:48:35,488 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4244 +[2025-02-22 13:48:35,535 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.7859 +[2025-02-22 13:48:35,816 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7862 +[2025-02-22 13:48:35,866 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6034 +[2025-02-22 13:48:35,913 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5156 +[2025-02-22 13:48:36,031 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1650 +[2025-02-22 13:48:36,169 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6041 +[2025-02-22 13:48:36,299 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0087 +[2025-02-22 13:48:36,415 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.2046 +[2025-02-22 13:48:36,508 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3480 +[2025-02-22 13:48:36,664 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5266 +[2025-02-22 13:48:36,711 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.7859 +[2025-02-22 13:48:36,842 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.5574 +[2025-02-22 13:48:36,943 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8625 +[2025-02-22 13:48:36,997 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.8660 +[2025-02-22 13:48:37,145 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2684 +[2025-02-22 13:48:37,197 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5532 +[2025-02-22 13:48:37,436 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4404 +[2025-02-22 13:48:37,550 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2244 +[2025-02-22 13:48:37,638 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6007 +[2025-02-22 13:48:37,701 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4737 +[2025-02-22 13:48:37,920 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3410 +[2025-02-22 13:48:38,065 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1390 +[2025-02-22 13:48:38,166 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0025 +[2025-02-22 13:48:38,350 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1753 +[2025-02-22 13:48:38,571 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7381 +[2025-02-22 13:48:38,705 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.4252 +[2025-02-22 13:48:38,778 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7450 +[2025-02-22 13:48:38,837 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4202 +[2025-02-22 13:48:39,057 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2955 +[2025-02-22 13:48:39,100 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5181 +[2025-02-22 13:48:39,165 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.7484 +[2025-02-22 13:48:39,313 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6070 +[2025-02-22 13:48:39,601 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6842 +[2025-02-22 13:48:39,721 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2940 +[2025-02-22 13:48:39,916 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6253 +[2025-02-22 13:48:40,048 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6276 +[2025-02-22 13:48:55,045 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:48:55,045 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:48:55,045 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] cabinet : 0.2832 0.5294 0.7384 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] bed : 0.3627 0.7394 0.8878 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] chair : 0.7441 0.9034 0.9389 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] sofa : 0.3737 0.6229 0.8319 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] table : 0.4643 0.7044 0.8139 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] door : 0.2846 0.5122 0.6361 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] window : 0.2521 0.4749 0.6653 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] bookshelf : 0.2595 0.5492 0.7126 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] picture : 0.3503 0.5169 0.6007 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] counter : 0.0385 0.1303 0.6029 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] desk : 0.1054 0.3027 0.7487 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] curtain : 0.2952 0.4863 0.6430 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] refridgerator : 0.4145 0.5614 0.6098 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] shower curtain : 0.4202 0.6055 0.7038 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] toilet : 0.8815 1.0000 1.0000 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] sink : 0.3869 0.6746 0.8585 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] bathtub : 0.6480 0.7913 0.8849 +[2025-02-22 13:48:55,045 INFO evaluator.py line 547 2775932] otherfurniture : 0.4269 0.6224 0.7118 +[2025-02-22 13:48:55,045 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:48:55,045 INFO evaluator.py line 554 2775932] average : 0.3884 0.5960 0.7550 +[2025-02-22 13:48:55,045 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:48:55,046 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:48:55,073 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5960 +[2025-02-22 13:48:55,080 INFO misc.py line 164 2775932] Currently Best AP50: 0.5960 +[2025-02-22 13:48:55,080 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:49:03,990 INFO hook.py line 109 2775932] Train: [76/100][50/800] Data 0.003 (0.004) Batch 0.131 (0.147) Remain 00:48:52 loss: -0.5851 Lr: 9.66197e-04 +[2025-02-22 13:49:11,602 INFO hook.py line 109 2775932] Train: [76/100][100/800] Data 0.003 (0.003) Batch 0.133 (0.150) Remain 00:49:39 loss: -0.6443 Lr: 9.61644e-04 +[2025-02-22 13:49:18,646 INFO hook.py line 109 2775932] Train: [76/100][150/800] Data 0.003 (0.003) Batch 0.152 (0.147) Remain 00:48:31 loss: -0.7166 Lr: 9.57101e-04 +[2025-02-22 13:49:25,633 INFO hook.py line 109 2775932] Train: [76/100][200/800] Data 0.003 (0.003) Batch 0.157 (0.145) Remain 00:47:49 loss: -0.6431 Lr: 9.52566e-04 +[2025-02-22 13:49:32,960 INFO hook.py line 109 2775932] Train: [76/100][250/800] Data 0.003 (0.004) Batch 0.141 (0.145) Remain 00:47:48 loss: -0.7517 Lr: 9.48039e-04 +[2025-02-22 13:49:40,079 INFO hook.py line 109 2775932] Train: [76/100][300/800] Data 0.004 (0.004) Batch 0.127 (0.145) Remain 00:47:31 loss: -0.5474 Lr: 9.43522e-04 +[2025-02-22 13:49:47,325 INFO hook.py line 109 2775932] Train: [76/100][350/800] Data 0.003 (0.004) Batch 0.136 (0.145) Remain 00:47:25 loss: -0.7523 Lr: 9.39013e-04 +[2025-02-22 13:49:54,556 INFO hook.py line 109 2775932] Train: [76/100][400/800] Data 0.003 (0.004) Batch 0.174 (0.145) Remain 00:47:17 loss: -0.6804 Lr: 9.34514e-04 +[2025-02-22 13:50:01,782 INFO hook.py line 109 2775932] Train: [76/100][450/800] Data 0.003 (0.004) Batch 0.135 (0.145) Remain 00:47:09 loss: -0.6583 Lr: 9.30023e-04 +[2025-02-22 13:50:09,009 INFO hook.py line 109 2775932] Train: [76/100][500/800] Data 0.004 (0.004) Batch 0.159 (0.145) Remain 00:47:02 loss: -0.6880 Lr: 9.25540e-04 +[2025-02-22 13:50:16,199 INFO hook.py line 109 2775932] Train: [76/100][550/800] Data 0.003 (0.004) Batch 0.124 (0.145) Remain 00:46:53 loss: -0.7079 Lr: 9.21067e-04 +[2025-02-22 13:50:23,439 INFO hook.py line 109 2775932] Train: [76/100][600/800] Data 0.003 (0.004) Batch 0.137 (0.145) Remain 00:46:46 loss: -0.6989 Lr: 9.16603e-04 +[2025-02-22 13:50:31,131 INFO hook.py line 109 2775932] Train: [76/100][650/800] Data 0.003 (0.004) Batch 0.128 (0.145) Remain 00:46:52 loss: -0.6264 Lr: 9.12147e-04 +[2025-02-22 13:50:38,231 INFO hook.py line 109 2775932] Train: [76/100][700/800] Data 0.002 (0.004) Batch 0.152 (0.145) Remain 00:46:40 loss: -0.5401 Lr: 9.07701e-04 +[2025-02-22 13:50:45,306 INFO hook.py line 109 2775932] Train: [76/100][750/800] Data 0.003 (0.004) Batch 0.151 (0.145) Remain 00:46:28 loss: -0.5760 Lr: 9.03263e-04 +[2025-02-22 13:50:52,018 INFO hook.py line 109 2775932] Train: [76/100][800/800] Data 0.002 (0.004) Batch 0.124 (0.144) Remain 00:46:08 loss: -0.5680 Lr: 8.98834e-04 +[2025-02-22 13:50:52,019 INFO misc.py line 135 2775932] Train result: loss: -0.6706 seg_loss: 0.1195 bias_l1_loss: 0.1694 bias_cosine_loss: -0.9595 +[2025-02-22 13:50:52,019 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:50:58,932 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8551 +[2025-02-22 13:50:59,631 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.5735 +[2025-02-22 13:50:59,698 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6325 +[2025-02-22 13:50:59,771 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.7147 +[2025-02-22 13:51:00,353 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7575 +[2025-02-22 13:51:00,417 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.9359 +[2025-02-22 13:51:00,719 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6136 +[2025-02-22 13:51:00,751 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5732 +[2025-02-22 13:51:00,900 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.4262 +[2025-02-22 13:51:00,977 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.1795 +[2025-02-22 13:51:01,312 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1414 +[2025-02-22 13:51:01,491 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0213 +[2025-02-22 13:51:01,607 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0062 +[2025-02-22 13:51:01,744 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3087 +[2025-02-22 13:51:01,855 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2679 +[2025-02-22 13:51:01,949 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6455 +[2025-02-22 13:51:02,115 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.7031 +[2025-02-22 13:51:02,228 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2534 +[2025-02-22 13:51:02,418 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2114 +[2025-02-22 13:51:02,502 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0743 +[2025-02-22 13:51:02,698 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7047 +[2025-02-22 13:51:02,910 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3804 +[2025-02-22 13:51:03,016 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1474 +[2025-02-22 13:51:03,089 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0363 +[2025-02-22 13:51:03,165 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4721 +[2025-02-22 13:51:03,230 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6947 +[2025-02-22 13:51:03,381 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2118 +[2025-02-22 13:51:03,511 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.7436 +[2025-02-22 13:51:03,597 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7799 +[2025-02-22 13:51:03,688 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.5592 +[2025-02-22 13:51:04,759 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5081 +[2025-02-22 13:51:04,957 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.4032 +[2025-02-22 13:51:05,009 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5924 +[2025-02-22 13:51:05,139 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0132 +[2025-02-22 13:51:05,180 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4943 +[2025-02-22 13:51:05,314 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.7605 +[2025-02-22 13:51:05,394 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5364 +[2025-02-22 13:51:05,589 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.6835 +[2025-02-22 13:51:05,808 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4596 +[2025-02-22 13:51:06,114 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9940 +[2025-02-22 13:51:06,361 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3221 +[2025-02-22 13:51:06,442 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.2800 +[2025-02-22 13:51:06,510 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8472 +[2025-02-22 13:51:06,837 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7862 +[2025-02-22 13:51:06,886 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5304 +[2025-02-22 13:51:06,944 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5186 +[2025-02-22 13:51:07,053 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.7556 +[2025-02-22 13:51:07,205 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6357 +[2025-02-22 13:51:07,377 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.4291 +[2025-02-22 13:51:07,520 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2405 +[2025-02-22 13:51:07,641 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2164 +[2025-02-22 13:51:07,816 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5083 +[2025-02-22 13:51:07,899 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.4790 +[2025-02-22 13:51:08,017 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2544 +[2025-02-22 13:51:08,118 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8797 +[2025-02-22 13:51:08,171 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6625 +[2025-02-22 13:51:08,334 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.0761 +[2025-02-22 13:51:08,384 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5306 +[2025-02-22 13:51:08,664 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3056 +[2025-02-22 13:51:08,794 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2054 +[2025-02-22 13:51:08,930 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6006 +[2025-02-22 13:51:09,006 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5633 +[2025-02-22 13:51:09,189 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2268 +[2025-02-22 13:51:09,322 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0442 +[2025-02-22 13:51:09,413 INFO evaluator.py line 595 2775932] Test: [65/78] Loss 0.0351 +[2025-02-22 13:51:09,597 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0869 +[2025-02-22 13:51:09,795 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7266 +[2025-02-22 13:51:09,914 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1467 +[2025-02-22 13:51:09,990 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7450 +[2025-02-22 13:51:10,062 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2873 +[2025-02-22 13:51:10,252 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2902 +[2025-02-22 13:51:10,303 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5481 +[2025-02-22 13:51:10,366 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8510 +[2025-02-22 13:51:10,496 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3691 +[2025-02-22 13:51:10,778 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6796 +[2025-02-22 13:51:10,881 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1901 +[2025-02-22 13:51:11,102 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6936 +[2025-02-22 13:51:11,238 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6281 +[2025-02-22 13:51:25,539 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:51:25,539 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:51:25,539 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] cabinet : 0.2338 0.4648 0.6470 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] bed : 0.3555 0.7300 0.8619 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] chair : 0.7453 0.9026 0.9400 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] sofa : 0.3277 0.5767 0.8168 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] table : 0.4498 0.7044 0.8304 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] door : 0.2372 0.4565 0.5871 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] window : 0.2409 0.4273 0.6317 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] bookshelf : 0.2862 0.5601 0.7021 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] picture : 0.2387 0.3602 0.4119 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] counter : 0.0492 0.1850 0.6101 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] desk : 0.1447 0.4678 0.7752 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] curtain : 0.3030 0.5337 0.6839 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] refridgerator : 0.3293 0.4189 0.4900 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] shower curtain : 0.4276 0.6058 0.7595 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] toilet : 0.8531 1.0000 1.0000 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] sink : 0.4063 0.7006 0.8821 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] bathtub : 0.6661 0.8065 0.8710 +[2025-02-22 13:51:25,539 INFO evaluator.py line 547 2775932] otherfurniture : 0.3918 0.5693 0.6631 +[2025-02-22 13:51:25,539 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:51:25,539 INFO evaluator.py line 554 2775932] average : 0.3715 0.5817 0.7313 +[2025-02-22 13:51:25,539 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:51:25,540 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:51:25,574 INFO misc.py line 164 2775932] Currently Best AP50: 0.5960 +[2025-02-22 13:51:25,581 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:51:33,930 INFO hook.py line 109 2775932] Train: [77/100][50/800] Data 0.004 (0.003) Batch 0.132 (0.143) Remain 00:45:35 loss: -0.7738 Lr: 8.94414e-04 +[2025-02-22 13:51:41,485 INFO hook.py line 109 2775932] Train: [77/100][100/800] Data 0.003 (0.005) Batch 0.142 (0.147) Remain 00:46:49 loss: -0.6405 Lr: 8.90004e-04 +[2025-02-22 13:51:48,515 INFO hook.py line 109 2775932] Train: [77/100][150/800] Data 0.004 (0.005) Batch 0.162 (0.145) Remain 00:46:00 loss: -0.7015 Lr: 8.85602e-04 +[2025-02-22 13:51:55,800 INFO hook.py line 109 2775932] Train: [77/100][200/800] Data 0.003 (0.005) Batch 0.139 (0.145) Remain 00:45:56 loss: -0.6978 Lr: 8.81209e-04 +[2025-02-22 13:52:02,819 INFO hook.py line 109 2775932] Train: [77/100][250/800] Data 0.003 (0.004) Batch 0.143 (0.144) Remain 00:45:31 loss: -0.6634 Lr: 8.76826e-04 +[2025-02-22 13:52:10,052 INFO hook.py line 109 2775932] Train: [77/100][300/800] Data 0.004 (0.004) Batch 0.150 (0.144) Remain 00:45:25 loss: -0.7991 Lr: 8.72451e-04 +[2025-02-22 13:52:17,240 INFO hook.py line 109 2775932] Train: [77/100][350/800] Data 0.005 (0.004) Batch 0.157 (0.144) Remain 00:45:17 loss: -0.7378 Lr: 8.68086e-04 +[2025-02-22 13:52:24,388 INFO hook.py line 109 2775932] Train: [77/100][400/800] Data 0.005 (0.004) Batch 0.139 (0.144) Remain 00:45:07 loss: -0.6446 Lr: 8.63729e-04 +[2025-02-22 13:52:31,565 INFO hook.py line 109 2775932] Train: [77/100][450/800] Data 0.003 (0.004) Batch 0.138 (0.144) Remain 00:44:59 loss: -0.6997 Lr: 8.59382e-04 +[2025-02-22 13:52:38,770 INFO hook.py line 109 2775932] Train: [77/100][500/800] Data 0.003 (0.004) Batch 0.122 (0.144) Remain 00:44:52 loss: -0.6896 Lr: 8.55044e-04 +[2025-02-22 13:52:45,889 INFO hook.py line 109 2775932] Train: [77/100][550/800] Data 0.003 (0.004) Batch 0.125 (0.144) Remain 00:44:42 loss: -0.7338 Lr: 8.50715e-04 +[2025-02-22 13:52:53,202 INFO hook.py line 109 2775932] Train: [77/100][600/800] Data 0.003 (0.004) Batch 0.125 (0.144) Remain 00:44:38 loss: -0.5337 Lr: 8.46395e-04 +[2025-02-22 13:53:00,404 INFO hook.py line 109 2775932] Train: [77/100][650/800] Data 0.004 (0.004) Batch 0.134 (0.144) Remain 00:44:31 loss: -0.7534 Lr: 8.42085e-04 +[2025-02-22 13:53:07,610 INFO hook.py line 109 2775932] Train: [77/100][700/800] Data 0.003 (0.004) Batch 0.149 (0.144) Remain 00:44:24 loss: -0.5929 Lr: 8.37784e-04 +[2025-02-22 13:53:14,931 INFO hook.py line 109 2775932] Train: [77/100][750/800] Data 0.003 (0.004) Batch 0.158 (0.144) Remain 00:44:20 loss: -0.6452 Lr: 8.33492e-04 +[2025-02-22 13:53:22,206 INFO hook.py line 109 2775932] Train: [77/100][800/800] Data 0.003 (0.004) Batch 0.123 (0.144) Remain 00:44:14 loss: -0.5179 Lr: 8.29209e-04 +[2025-02-22 13:53:22,206 INFO misc.py line 135 2775932] Train result: loss: -0.6882 seg_loss: 0.1136 bias_l1_loss: 0.1608 bias_cosine_loss: -0.9627 +[2025-02-22 13:53:22,206 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:53:29,221 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8516 +[2025-02-22 13:53:30,024 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6566 +[2025-02-22 13:53:30,102 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6461 +[2025-02-22 13:53:30,182 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6846 +[2025-02-22 13:53:30,253 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7266 +[2025-02-22 13:53:30,327 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 0.7630 +[2025-02-22 13:53:30,678 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6181 +[2025-02-22 13:53:30,721 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4788 +[2025-02-22 13:53:30,889 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2585 +[2025-02-22 13:53:30,969 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0773 +[2025-02-22 13:53:31,318 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0609 +[2025-02-22 13:53:31,491 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.2122 +[2025-02-22 13:53:31,602 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4996 +[2025-02-22 13:53:31,721 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 2.0480 +[2025-02-22 13:53:31,832 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2295 +[2025-02-22 13:53:31,924 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6647 +[2025-02-22 13:53:32,101 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5875 +[2025-02-22 13:53:32,227 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3449 +[2025-02-22 13:53:32,397 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1795 +[2025-02-22 13:53:32,475 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2339 +[2025-02-22 13:53:32,671 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7083 +[2025-02-22 13:53:32,900 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1556 +[2025-02-22 13:53:33,006 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1667 +[2025-02-22 13:53:33,090 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.3197 +[2025-02-22 13:53:33,192 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2356 +[2025-02-22 13:53:33,255 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6883 +[2025-02-22 13:53:33,425 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1773 +[2025-02-22 13:53:33,557 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.3910 +[2025-02-22 13:53:33,671 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7700 +[2025-02-22 13:53:33,759 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7412 +[2025-02-22 13:53:34,836 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6097 +[2025-02-22 13:53:35,053 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3892 +[2025-02-22 13:53:35,105 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4895 +[2025-02-22 13:53:35,265 INFO evaluator.py line 595 2775932] Test: [34/78] Loss 0.0103 +[2025-02-22 13:53:35,319 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4969 +[2025-02-22 13:53:35,466 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.7326 +[2025-02-22 13:53:35,547 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7146 +[2025-02-22 13:53:35,721 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7381 +[2025-02-22 13:53:35,926 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3401 +[2025-02-22 13:53:36,168 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.3717 +[2025-02-22 13:53:36,373 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.3654 +[2025-02-22 13:53:36,442 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4229 +[2025-02-22 13:53:36,514 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8327 +[2025-02-22 13:53:36,899 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7218 +[2025-02-22 13:53:36,967 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6958 +[2025-02-22 13:53:37,040 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5466 +[2025-02-22 13:53:37,170 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.2203 +[2025-02-22 13:53:37,348 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5337 +[2025-02-22 13:53:37,577 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1284 +[2025-02-22 13:53:37,706 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1705 +[2025-02-22 13:53:37,821 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3239 +[2025-02-22 13:53:37,996 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4307 +[2025-02-22 13:53:38,045 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5463 +[2025-02-22 13:53:38,190 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.2276 +[2025-02-22 13:53:38,296 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8991 +[2025-02-22 13:53:38,344 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6629 +[2025-02-22 13:53:38,509 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2981 +[2025-02-22 13:53:38,559 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.4887 +[2025-02-22 13:53:38,810 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4643 +[2025-02-22 13:53:38,927 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3874 +[2025-02-22 13:53:39,018 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4890 +[2025-02-22 13:53:39,084 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4615 +[2025-02-22 13:53:39,261 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1926 +[2025-02-22 13:53:39,378 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0374 +[2025-02-22 13:53:39,459 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0214 +[2025-02-22 13:53:39,624 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3614 +[2025-02-22 13:53:39,812 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7361 +[2025-02-22 13:53:39,919 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1284 +[2025-02-22 13:53:39,982 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7322 +[2025-02-22 13:53:40,041 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0076 +[2025-02-22 13:53:40,234 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.1804 +[2025-02-22 13:53:40,281 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4310 +[2025-02-22 13:53:40,336 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8605 +[2025-02-22 13:53:40,459 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3102 +[2025-02-22 13:53:40,699 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6866 +[2025-02-22 13:53:40,795 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1488 +[2025-02-22 13:53:40,971 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6940 +[2025-02-22 13:53:41,101 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6947 +[2025-02-22 13:53:54,476 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:53:54,476 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:53:54,476 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] cabinet : 0.3033 0.5505 0.7489 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] bed : 0.3604 0.7263 0.8617 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] chair : 0.7512 0.9007 0.9345 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] sofa : 0.4093 0.6414 0.8466 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] table : 0.4622 0.6922 0.8083 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] door : 0.2514 0.4505 0.5752 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] window : 0.2170 0.4152 0.6268 +[2025-02-22 13:53:54,476 INFO evaluator.py line 547 2775932] bookshelf : 0.2562 0.5534 0.7475 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] picture : 0.3570 0.5143 0.5670 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] counter : 0.0373 0.1074 0.5391 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] desk : 0.1155 0.3793 0.8517 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] curtain : 0.2843 0.4786 0.5945 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] refridgerator : 0.3928 0.5384 0.6377 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] shower curtain : 0.4115 0.5799 0.7040 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] toilet : 0.8941 1.0000 1.0000 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] sink : 0.3976 0.6960 0.8838 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] bathtub : 0.6775 0.7742 0.8710 +[2025-02-22 13:53:54,477 INFO evaluator.py line 547 2775932] otherfurniture : 0.4103 0.5886 0.6824 +[2025-02-22 13:53:54,477 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:53:54,477 INFO evaluator.py line 554 2775932] average : 0.3883 0.5882 0.7489 +[2025-02-22 13:53:54,477 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:53:54,477 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:53:54,509 INFO misc.py line 164 2775932] Currently Best AP50: 0.5960 +[2025-02-22 13:53:54,516 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:54:03,543 INFO hook.py line 109 2775932] Train: [78/100][50/800] Data 0.003 (0.003) Batch 0.146 (0.146) Remain 00:44:33 loss: -0.6909 Lr: 8.24935e-04 +[2025-02-22 13:54:10,562 INFO hook.py line 109 2775932] Train: [78/100][100/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 00:43:35 loss: -0.5802 Lr: 8.20671e-04 +[2025-02-22 13:54:17,829 INFO hook.py line 109 2775932] Train: [78/100][150/800] Data 0.003 (0.003) Batch 0.149 (0.144) Remain 00:43:43 loss: -0.5329 Lr: 8.16416e-04 +[2025-02-22 13:54:24,939 INFO hook.py line 109 2775932] Train: [78/100][200/800] Data 0.004 (0.003) Batch 0.133 (0.143) Remain 00:43:29 loss: -0.7120 Lr: 8.12170e-04 +[2025-02-22 13:54:32,340 INFO hook.py line 109 2775932] Train: [78/100][250/800] Data 0.003 (0.004) Batch 0.150 (0.144) Remain 00:43:39 loss: -0.6715 Lr: 8.08019e-04 +[2025-02-22 13:54:39,775 INFO hook.py line 109 2775932] Train: [78/100][300/800] Data 0.003 (0.005) Batch 0.174 (0.145) Remain 00:43:45 loss: -0.7324 Lr: 8.03792e-04 +[2025-02-22 13:54:46,859 INFO hook.py line 109 2775932] Train: [78/100][350/800] Data 0.006 (0.004) Batch 0.142 (0.145) Remain 00:43:29 loss: -0.6356 Lr: 7.99574e-04 +[2025-02-22 13:54:54,129 INFO hook.py line 109 2775932] Train: [78/100][400/800] Data 0.003 (0.004) Batch 0.129 (0.145) Remain 00:43:23 loss: -0.7205 Lr: 7.95366e-04 +[2025-02-22 13:55:01,207 INFO hook.py line 109 2775932] Train: [78/100][450/800] Data 0.003 (0.004) Batch 0.167 (0.144) Remain 00:43:10 loss: -0.7377 Lr: 7.91167e-04 +[2025-02-22 13:55:08,243 INFO hook.py line 109 2775932] Train: [78/100][500/800] Data 0.003 (0.004) Batch 0.130 (0.144) Remain 00:42:56 loss: -0.7953 Lr: 7.86977e-04 +[2025-02-22 13:55:15,195 INFO hook.py line 109 2775932] Train: [78/100][550/800] Data 0.003 (0.004) Batch 0.139 (0.144) Remain 00:42:41 loss: -0.8049 Lr: 7.82797e-04 +[2025-02-22 13:55:22,061 INFO hook.py line 109 2775932] Train: [78/100][600/800] Data 0.003 (0.004) Batch 0.121 (0.143) Remain 00:42:25 loss: -0.6886 Lr: 7.78627e-04 +[2025-02-22 13:55:29,295 INFO hook.py line 109 2775932] Train: [78/100][650/800] Data 0.002 (0.004) Batch 0.126 (0.143) Remain 00:42:20 loss: -0.8553 Lr: 7.74466e-04 +[2025-02-22 13:55:36,678 INFO hook.py line 109 2775932] Train: [78/100][700/800] Data 0.006 (0.004) Batch 0.182 (0.143) Remain 00:42:18 loss: -0.7937 Lr: 7.70314e-04 +[2025-02-22 13:55:43,921 INFO hook.py line 109 2775932] Train: [78/100][750/800] Data 0.003 (0.004) Batch 0.136 (0.144) Remain 00:42:13 loss: -0.6724 Lr: 7.66172e-04 +[2025-02-22 13:55:50,901 INFO hook.py line 109 2775932] Train: [78/100][800/800] Data 0.002 (0.004) Batch 0.118 (0.143) Remain 00:42:01 loss: -0.6494 Lr: 7.62040e-04 +[2025-02-22 13:55:50,902 INFO misc.py line 135 2775932] Train result: loss: -0.6946 seg_loss: 0.1079 bias_l1_loss: 0.1610 bias_cosine_loss: -0.9635 +[2025-02-22 13:55:50,902 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:55:57,717 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8596 +[2025-02-22 13:55:58,072 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7295 +[2025-02-22 13:55:58,169 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6492 +[2025-02-22 13:55:58,707 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6695 +[2025-02-22 13:55:58,807 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7712 +[2025-02-22 13:55:58,893 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.3264 +[2025-02-22 13:55:59,233 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6506 +[2025-02-22 13:55:59,276 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6508 +[2025-02-22 13:55:59,442 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3303 +[2025-02-22 13:55:59,518 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0155 +[2025-02-22 13:55:59,847 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1955 +[2025-02-22 13:56:00,004 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0223 +[2025-02-22 13:56:00,106 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4249 +[2025-02-22 13:56:00,235 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.3601 +[2025-02-22 13:56:00,366 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2083 +[2025-02-22 13:56:00,469 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6991 +[2025-02-22 13:56:00,622 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6153 +[2025-02-22 13:56:00,745 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1798 +[2025-02-22 13:56:00,915 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.2126 +[2025-02-22 13:56:00,984 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0971 +[2025-02-22 13:56:01,154 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7532 +[2025-02-22 13:56:01,341 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1925 +[2025-02-22 13:56:01,446 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0695 +[2025-02-22 13:56:01,529 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0798 +[2025-02-22 13:56:01,637 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2966 +[2025-02-22 13:56:01,721 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6632 +[2025-02-22 13:56:01,888 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0606 +[2025-02-22 13:56:02,023 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4928 +[2025-02-22 13:56:02,118 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7849 +[2025-02-22 13:56:02,203 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7127 +[2025-02-22 13:56:03,366 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5749 +[2025-02-22 13:56:03,649 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5361 +[2025-02-22 13:56:03,701 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7138 +[2025-02-22 13:56:03,812 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4630 +[2025-02-22 13:56:03,869 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5162 +[2025-02-22 13:56:04,004 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 1.0598 +[2025-02-22 13:56:04,117 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.4926 +[2025-02-22 13:56:04,285 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7539 +[2025-02-22 13:56:04,480 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3576 +[2025-02-22 13:56:04,742 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9190 +[2025-02-22 13:56:04,943 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.4486 +[2025-02-22 13:56:05,008 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4085 +[2025-02-22 13:56:05,060 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8447 +[2025-02-22 13:56:05,350 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7808 +[2025-02-22 13:56:05,403 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.4268 +[2025-02-22 13:56:05,460 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4281 +[2025-02-22 13:56:05,573 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.9730 +[2025-02-22 13:56:05,727 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3770 +[2025-02-22 13:56:05,876 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0081 +[2025-02-22 13:56:05,979 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1696 +[2025-02-22 13:56:06,082 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3604 +[2025-02-22 13:56:06,256 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5555 +[2025-02-22 13:56:06,305 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6169 +[2025-02-22 13:56:06,431 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.5289 +[2025-02-22 13:56:06,536 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9036 +[2025-02-22 13:56:06,593 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7169 +[2025-02-22 13:56:06,766 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1937 +[2025-02-22 13:56:06,819 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6102 +[2025-02-22 13:56:07,073 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.5014 +[2025-02-22 13:56:07,187 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1170 +[2025-02-22 13:56:07,283 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4505 +[2025-02-22 13:56:07,351 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5851 +[2025-02-22 13:56:07,553 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2107 +[2025-02-22 13:56:07,682 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0964 +[2025-02-22 13:56:07,771 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1125 +[2025-02-22 13:56:07,937 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1977 +[2025-02-22 13:56:08,129 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7471 +[2025-02-22 13:56:08,245 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0547 +[2025-02-22 13:56:08,303 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7095 +[2025-02-22 13:56:08,380 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3973 +[2025-02-22 13:56:08,579 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2602 +[2025-02-22 13:56:08,618 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6963 +[2025-02-22 13:56:08,678 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8629 +[2025-02-22 13:56:08,805 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.5361 +[2025-02-22 13:56:09,043 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6989 +[2025-02-22 13:56:09,160 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1474 +[2025-02-22 13:56:09,327 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6971 +[2025-02-22 13:56:09,423 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6533 +[2025-02-22 13:56:22,453 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:56:22,453 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:56:22,453 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] cabinet : 0.2772 0.5211 0.7187 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] bed : 0.3440 0.7117 0.8517 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] chair : 0.7573 0.9121 0.9476 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] sofa : 0.3629 0.5788 0.8042 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] table : 0.4781 0.7431 0.8510 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] door : 0.2795 0.5063 0.6472 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] window : 0.2604 0.4505 0.6467 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] bookshelf : 0.2638 0.5019 0.7284 +[2025-02-22 13:56:22,453 INFO evaluator.py line 547 2775932] picture : 0.3385 0.4857 0.5787 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] counter : 0.0427 0.1490 0.5622 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] desk : 0.0881 0.2776 0.6818 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] curtain : 0.2875 0.5156 0.6422 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] refridgerator : 0.4904 0.7320 0.7661 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] shower curtain : 0.4873 0.6991 0.8084 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] toilet : 0.8793 1.0000 1.0000 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] sink : 0.3664 0.6368 0.8718 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] bathtub : 0.6794 0.7742 0.8710 +[2025-02-22 13:56:22,454 INFO evaluator.py line 547 2775932] otherfurniture : 0.3905 0.5594 0.6555 +[2025-02-22 13:56:22,454 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:56:22,454 INFO evaluator.py line 554 2775932] average : 0.3930 0.5975 0.7574 +[2025-02-22 13:56:22,454 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:56:22,454 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:56:22,486 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.5975 +[2025-02-22 13:56:22,493 INFO misc.py line 164 2775932] Currently Best AP50: 0.5975 +[2025-02-22 13:56:22,493 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:56:31,876 INFO hook.py line 109 2775932] Train: [79/100][50/800] Data 0.003 (0.003) Batch 0.152 (0.152) Remain 00:44:28 loss: -0.6076 Lr: 7.57917e-04 +[2025-02-22 13:56:39,014 INFO hook.py line 109 2775932] Train: [79/100][100/800] Data 0.003 (0.003) Batch 0.140 (0.147) Remain 00:42:57 loss: -0.7630 Lr: 7.53804e-04 +[2025-02-22 13:56:46,476 INFO hook.py line 109 2775932] Train: [79/100][150/800] Data 0.003 (0.004) Batch 0.137 (0.148) Remain 00:43:01 loss: -0.7332 Lr: 7.49700e-04 +[2025-02-22 13:56:53,504 INFO hook.py line 109 2775932] Train: [79/100][200/800] Data 0.003 (0.004) Batch 0.151 (0.146) Remain 00:42:21 loss: -0.7591 Lr: 7.45606e-04 +[2025-02-22 13:57:00,626 INFO hook.py line 109 2775932] Train: [79/100][250/800] Data 0.003 (0.004) Batch 0.154 (0.145) Remain 00:42:01 loss: -0.7722 Lr: 7.41521e-04 +[2025-02-22 13:57:07,861 INFO hook.py line 109 2775932] Train: [79/100][300/800] Data 0.002 (0.004) Batch 0.146 (0.145) Remain 00:41:52 loss: -0.7412 Lr: 7.37447e-04 +[2025-02-22 13:57:14,858 INFO hook.py line 109 2775932] Train: [79/100][350/800] Data 0.003 (0.004) Batch 0.146 (0.144) Remain 00:41:31 loss: -0.7860 Lr: 7.33381e-04 +[2025-02-22 13:57:21,771 INFO hook.py line 109 2775932] Train: [79/100][400/800] Data 0.003 (0.003) Batch 0.145 (0.144) Remain 00:41:11 loss: -0.7758 Lr: 7.29326e-04 +[2025-02-22 13:57:28,827 INFO hook.py line 109 2775932] Train: [79/100][450/800] Data 0.002 (0.003) Batch 0.139 (0.143) Remain 00:40:59 loss: -0.6126 Lr: 7.25280e-04 +[2025-02-22 13:57:36,167 INFO hook.py line 109 2775932] Train: [79/100][500/800] Data 0.005 (0.003) Batch 0.150 (0.144) Remain 00:40:57 loss: -0.6887 Lr: 7.21244e-04 +[2025-02-22 13:57:43,262 INFO hook.py line 109 2775932] Train: [79/100][550/800] Data 0.003 (0.003) Batch 0.131 (0.144) Remain 00:40:47 loss: -0.6866 Lr: 7.17218e-04 +[2025-02-22 13:57:50,477 INFO hook.py line 109 2775932] Train: [79/100][600/800] Data 0.004 (0.003) Batch 0.139 (0.144) Remain 00:40:41 loss: -0.6856 Lr: 7.13201e-04 +[2025-02-22 13:57:57,840 INFO hook.py line 109 2775932] Train: [79/100][650/800] Data 0.003 (0.003) Batch 0.157 (0.144) Remain 00:40:39 loss: -0.6778 Lr: 7.09194e-04 +[2025-02-22 13:58:04,835 INFO hook.py line 109 2775932] Train: [79/100][700/800] Data 0.002 (0.003) Batch 0.135 (0.144) Remain 00:40:27 loss: -0.7648 Lr: 7.05197e-04 +[2025-02-22 13:58:12,148 INFO hook.py line 109 2775932] Train: [79/100][750/800] Data 0.002 (0.003) Batch 0.158 (0.144) Remain 00:40:22 loss: -0.6501 Lr: 7.01210e-04 +[2025-02-22 13:58:19,062 INFO hook.py line 109 2775932] Train: [79/100][800/800] Data 0.002 (0.003) Batch 0.137 (0.143) Remain 00:40:09 loss: -0.6933 Lr: 6.97233e-04 +[2025-02-22 13:58:19,062 INFO misc.py line 135 2775932] Train result: loss: -0.6996 seg_loss: 0.1073 bias_l1_loss: 0.1566 bias_cosine_loss: -0.9634 +[2025-02-22 13:58:19,063 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 13:58:25,716 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8551 +[2025-02-22 13:58:26,223 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6153 +[2025-02-22 13:58:26,296 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6697 +[2025-02-22 13:58:26,372 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6868 +[2025-02-22 13:58:26,456 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7967 +[2025-02-22 13:58:26,533 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.0350 +[2025-02-22 13:58:26,856 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6677 +[2025-02-22 13:58:26,888 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3620 +[2025-02-22 13:58:27,033 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2978 +[2025-02-22 13:58:27,092 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0698 +[2025-02-22 13:58:27,369 INFO evaluator.py line 595 2775932] Test: [11/78] Loss -0.1589 +[2025-02-22 13:58:27,496 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.2400 +[2025-02-22 13:58:27,586 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0270 +[2025-02-22 13:58:27,703 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.1040 +[2025-02-22 13:58:27,802 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0829 +[2025-02-22 13:58:27,885 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6842 +[2025-02-22 13:58:28,023 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6453 +[2025-02-22 13:58:28,142 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4463 +[2025-02-22 13:58:28,311 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.3452 +[2025-02-22 13:58:28,396 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1318 +[2025-02-22 13:58:28,559 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7094 +[2025-02-22 13:58:28,743 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2026 +[2025-02-22 13:58:28,827 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0333 +[2025-02-22 13:58:28,891 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0129 +[2025-02-22 13:58:28,972 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.3091 +[2025-02-22 13:58:29,028 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7108 +[2025-02-22 13:58:29,181 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.2121 +[2025-02-22 13:58:29,315 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6645 +[2025-02-22 13:58:29,393 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7407 +[2025-02-22 13:58:29,462 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6045 +[2025-02-22 13:58:30,351 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5971 +[2025-02-22 13:58:30,533 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 1.0499 +[2025-02-22 13:58:30,581 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6789 +[2025-02-22 13:58:30,731 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4746 +[2025-02-22 13:58:30,775 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5696 +[2025-02-22 13:58:30,891 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5770 +[2025-02-22 13:58:30,979 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6914 +[2025-02-22 13:58:31,118 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7662 +[2025-02-22 13:58:31,302 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4796 +[2025-02-22 13:58:31,522 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7328 +[2025-02-22 13:58:31,693 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5120 +[2025-02-22 13:58:31,744 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4197 +[2025-02-22 13:58:31,788 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8241 +[2025-02-22 13:58:32,047 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7479 +[2025-02-22 13:58:32,094 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6646 +[2025-02-22 13:58:32,138 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4713 +[2025-02-22 13:58:32,244 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4001 +[2025-02-22 13:58:32,376 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2648 +[2025-02-22 13:58:32,510 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1803 +[2025-02-22 13:58:32,619 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2644 +[2025-02-22 13:58:32,714 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0060 +[2025-02-22 13:58:32,882 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.3988 +[2025-02-22 13:58:32,930 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5672 +[2025-02-22 13:58:33,076 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.3715 +[2025-02-22 13:58:33,177 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8809 +[2025-02-22 13:58:33,232 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7754 +[2025-02-22 13:58:33,399 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2345 +[2025-02-22 13:58:33,446 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.5433 +[2025-02-22 13:58:33,704 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.5056 +[2025-02-22 13:58:33,828 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3088 +[2025-02-22 13:58:33,947 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.6026 +[2025-02-22 13:58:34,039 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6846 +[2025-02-22 13:58:34,211 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2737 +[2025-02-22 13:58:34,309 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0432 +[2025-02-22 13:58:34,382 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1025 +[2025-02-22 13:58:34,514 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.4394 +[2025-02-22 13:58:34,686 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7010 +[2025-02-22 13:58:34,783 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.3063 +[2025-02-22 13:58:34,831 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6776 +[2025-02-22 13:58:34,881 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5396 +[2025-02-22 13:58:35,052 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3352 +[2025-02-22 13:58:35,107 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4775 +[2025-02-22 13:58:35,158 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8260 +[2025-02-22 13:58:35,258 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.3476 +[2025-02-22 13:58:35,449 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7256 +[2025-02-22 13:58:35,523 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.2644 +[2025-02-22 13:58:35,681 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6883 +[2025-02-22 13:58:35,773 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5085 +[2025-02-22 13:58:51,482 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 13:58:51,482 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 13:58:51,482 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 13:58:51,482 INFO evaluator.py line 547 2775932] cabinet : 0.2885 0.5137 0.7243 +[2025-02-22 13:58:51,482 INFO evaluator.py line 547 2775932] bed : 0.3661 0.7520 0.8853 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] chair : 0.7595 0.9113 0.9483 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] sofa : 0.3168 0.5332 0.7729 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] table : 0.4605 0.6950 0.8070 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] door : 0.2571 0.4784 0.6092 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] window : 0.2669 0.5142 0.6763 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] bookshelf : 0.3121 0.5920 0.7336 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] picture : 0.3392 0.4913 0.5899 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] counter : 0.0637 0.2486 0.6404 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] desk : 0.1250 0.4050 0.8070 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] curtain : 0.2999 0.5158 0.5946 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] refridgerator : 0.4837 0.6860 0.7226 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] shower curtain : 0.4368 0.5887 0.7998 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] toilet : 0.8685 0.9825 0.9988 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] sink : 0.3925 0.6531 0.8873 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] bathtub : 0.6521 0.7742 0.8710 +[2025-02-22 13:58:51,483 INFO evaluator.py line 547 2775932] otherfurniture : 0.3931 0.5819 0.6903 +[2025-02-22 13:58:51,483 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 13:58:51,483 INFO evaluator.py line 554 2775932] average : 0.3934 0.6065 0.7644 +[2025-02-22 13:58:51,483 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 13:58:51,483 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 13:58:51,517 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.6065 +[2025-02-22 13:58:51,524 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 13:58:51,524 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 13:59:00,797 INFO hook.py line 109 2775932] Train: [80/100][50/800] Data 0.005 (0.009) Batch 0.432 (0.158) Remain 00:44:11 loss: -0.7746 Lr: 6.93265e-04 +[2025-02-22 13:59:07,920 INFO hook.py line 109 2775932] Train: [80/100][100/800] Data 0.003 (0.006) Batch 0.150 (0.150) Remain 00:41:46 loss: -0.6691 Lr: 6.89308e-04 +[2025-02-22 13:59:14,834 INFO hook.py line 109 2775932] Train: [80/100][150/800] Data 0.003 (0.005) Batch 0.128 (0.146) Remain 00:40:32 loss: -0.1272 Lr: 6.85360e-04 +[2025-02-22 13:59:22,077 INFO hook.py line 109 2775932] Train: [80/100][200/800] Data 0.003 (0.004) Batch 0.149 (0.146) Remain 00:40:19 loss: -0.6514 Lr: 6.81422e-04 +[2025-02-22 13:59:29,316 INFO hook.py line 109 2775932] Train: [80/100][250/800] Data 0.003 (0.004) Batch 0.147 (0.146) Remain 00:40:09 loss: -0.6085 Lr: 6.77494e-04 +[2025-02-22 13:59:36,325 INFO hook.py line 109 2775932] Train: [80/100][300/800] Data 0.003 (0.004) Batch 0.125 (0.145) Remain 00:39:47 loss: -0.7516 Lr: 6.73576e-04 +[2025-02-22 13:59:43,388 INFO hook.py line 109 2775932] Train: [80/100][350/800] Data 0.003 (0.004) Batch 0.175 (0.144) Remain 00:39:31 loss: -0.7373 Lr: 6.69668e-04 +[2025-02-22 13:59:50,298 INFO hook.py line 109 2775932] Train: [80/100][400/800] Data 0.003 (0.004) Batch 0.138 (0.143) Remain 00:39:12 loss: -0.6226 Lr: 6.65769e-04 +[2025-02-22 13:59:57,215 INFO hook.py line 109 2775932] Train: [80/100][450/800] Data 0.003 (0.004) Batch 0.127 (0.143) Remain 00:38:55 loss: -0.7913 Lr: 6.61881e-04 +[2025-02-22 14:00:04,195 INFO hook.py line 109 2775932] Train: [80/100][500/800] Data 0.005 (0.004) Batch 0.147 (0.143) Remain 00:38:43 loss: -0.4730 Lr: 6.58003e-04 +[2025-02-22 14:00:11,494 INFO hook.py line 109 2775932] Train: [80/100][550/800] Data 0.003 (0.003) Batch 0.168 (0.143) Remain 00:38:41 loss: -0.7490 Lr: 6.54135e-04 +[2025-02-22 14:00:18,526 INFO hook.py line 109 2775932] Train: [80/100][600/800] Data 0.003 (0.003) Batch 0.146 (0.143) Remain 00:38:31 loss: -0.7252 Lr: 6.50277e-04 +[2025-02-22 14:00:25,967 INFO hook.py line 109 2775932] Train: [80/100][650/800] Data 0.002 (0.003) Batch 0.163 (0.143) Remain 00:38:31 loss: -0.5247 Lr: 6.46505e-04 +[2025-02-22 14:00:33,136 INFO hook.py line 109 2775932] Train: [80/100][700/800] Data 0.003 (0.003) Batch 0.129 (0.143) Remain 00:38:24 loss: -0.6571 Lr: 6.42744e-04 +[2025-02-22 14:00:40,302 INFO hook.py line 109 2775932] Train: [80/100][750/800] Data 0.003 (0.003) Batch 0.157 (0.143) Remain 00:38:17 loss: -0.7288 Lr: 6.38915e-04 +[2025-02-22 14:00:47,191 INFO hook.py line 109 2775932] Train: [80/100][800/800] Data 0.002 (0.003) Batch 0.108 (0.143) Remain 00:38:05 loss: -0.7399 Lr: 6.35097e-04 +[2025-02-22 14:00:47,192 INFO misc.py line 135 2775932] Train result: loss: -0.6995 seg_loss: 0.1083 bias_l1_loss: 0.1563 bias_cosine_loss: -0.9641 +[2025-02-22 14:00:47,192 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:00:53,935 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8730 +[2025-02-22 14:00:54,738 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6794 +[2025-02-22 14:00:54,809 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6472 +[2025-02-22 14:00:54,889 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6028 +[2025-02-22 14:00:54,955 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7200 +[2025-02-22 14:00:55,012 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.2674 +[2025-02-22 14:00:55,329 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5658 +[2025-02-22 14:00:55,364 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6002 +[2025-02-22 14:00:55,524 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2634 +[2025-02-22 14:00:55,599 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0384 +[2025-02-22 14:00:55,874 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2306 +[2025-02-22 14:00:56,002 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0917 +[2025-02-22 14:00:56,089 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0835 +[2025-02-22 14:00:56,206 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.2936 +[2025-02-22 14:00:56,309 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2046 +[2025-02-22 14:00:56,395 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7059 +[2025-02-22 14:00:56,538 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6128 +[2025-02-22 14:00:56,648 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2902 +[2025-02-22 14:00:56,804 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0981 +[2025-02-22 14:00:56,874 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1666 +[2025-02-22 14:00:57,040 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7028 +[2025-02-22 14:00:57,226 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.5309 +[2025-02-22 14:00:57,309 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0663 +[2025-02-22 14:00:57,370 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0726 +[2025-02-22 14:00:57,446 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6266 +[2025-02-22 14:00:57,508 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6175 +[2025-02-22 14:00:57,679 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1265 +[2025-02-22 14:00:57,787 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4930 +[2025-02-22 14:00:57,864 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7923 +[2025-02-22 14:00:57,946 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6477 +[2025-02-22 14:00:58,845 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5805 +[2025-02-22 14:00:59,000 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4738 +[2025-02-22 14:00:59,038 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.4807 +[2025-02-22 14:00:59,138 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3576 +[2025-02-22 14:00:59,173 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5460 +[2025-02-22 14:00:59,285 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.8078 +[2025-02-22 14:00:59,353 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.5664 +[2025-02-22 14:00:59,481 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7917 +[2025-02-22 14:00:59,645 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2244 +[2025-02-22 14:00:59,850 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9871 +[2025-02-22 14:01:00,026 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.7129 +[2025-02-22 14:01:00,078 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4588 +[2025-02-22 14:01:00,118 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8409 +[2025-02-22 14:01:00,366 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7958 +[2025-02-22 14:01:00,412 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6159 +[2025-02-22 14:01:00,453 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4707 +[2025-02-22 14:01:00,569 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3263 +[2025-02-22 14:01:00,720 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6348 +[2025-02-22 14:01:00,860 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2903 +[2025-02-22 14:01:00,962 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0962 +[2025-02-22 14:01:01,055 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3127 +[2025-02-22 14:01:01,218 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4538 +[2025-02-22 14:01:01,263 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5671 +[2025-02-22 14:01:01,383 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.7503 +[2025-02-22 14:01:01,484 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9022 +[2025-02-22 14:01:01,539 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7721 +[2025-02-22 14:01:01,710 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1277 +[2025-02-22 14:01:01,757 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6196 +[2025-02-22 14:01:02,028 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4008 +[2025-02-22 14:01:02,142 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2908 +[2025-02-22 14:01:02,233 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5315 +[2025-02-22 14:01:02,296 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5494 +[2025-02-22 14:01:02,476 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3730 +[2025-02-22 14:01:02,603 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0093 +[2025-02-22 14:01:02,684 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2332 +[2025-02-22 14:01:02,846 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.0309 +[2025-02-22 14:01:03,047 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7613 +[2025-02-22 14:01:03,167 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1645 +[2025-02-22 14:01:03,231 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6956 +[2025-02-22 14:01:03,289 INFO evaluator.py line 595 2775932] Test: [70/78] Loss 0.2186 +[2025-02-22 14:01:03,497 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5005 +[2025-02-22 14:01:03,546 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.7013 +[2025-02-22 14:01:03,614 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8331 +[2025-02-22 14:01:03,762 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7700 +[2025-02-22 14:01:04,027 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7220 +[2025-02-22 14:01:04,122 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.0772 +[2025-02-22 14:01:04,369 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6799 +[2025-02-22 14:01:04,489 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6592 +[2025-02-22 14:01:18,856 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:01:18,856 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:01:18,856 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] cabinet : 0.2855 0.5012 0.7018 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] bed : 0.3658 0.7341 0.8635 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] chair : 0.7486 0.9022 0.9430 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] sofa : 0.3592 0.5926 0.8139 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] table : 0.4287 0.6933 0.8197 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] door : 0.2839 0.5032 0.6458 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] window : 0.2514 0.4437 0.6249 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] bookshelf : 0.2428 0.4959 0.6991 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] picture : 0.3417 0.4888 0.5532 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] counter : 0.0632 0.1836 0.5977 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] desk : 0.1393 0.4244 0.8364 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] curtain : 0.2547 0.4744 0.6378 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] refridgerator : 0.3721 0.4871 0.5769 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] shower curtain : 0.4809 0.6234 0.6919 +[2025-02-22 14:01:18,856 INFO evaluator.py line 547 2775932] toilet : 0.8569 0.9652 0.9822 +[2025-02-22 14:01:18,857 INFO evaluator.py line 547 2775932] sink : 0.4307 0.7071 0.8769 +[2025-02-22 14:01:18,857 INFO evaluator.py line 547 2775932] bathtub : 0.6794 0.7742 0.8710 +[2025-02-22 14:01:18,857 INFO evaluator.py line 547 2775932] otherfurniture : 0.3811 0.5608 0.6698 +[2025-02-22 14:01:18,857 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:01:18,857 INFO evaluator.py line 554 2775932] average : 0.3870 0.5864 0.7447 +[2025-02-22 14:01:18,857 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:01:18,857 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:01:18,887 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 14:01:18,894 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:01:27,618 INFO hook.py line 109 2775932] Train: [81/100][50/800] Data 0.003 (0.004) Batch 0.290 (0.149) Remain 00:39:35 loss: -0.7197 Lr: 6.31289e-04 +[2025-02-22 14:01:34,622 INFO hook.py line 109 2775932] Train: [81/100][100/800] Data 0.003 (0.003) Batch 0.133 (0.144) Remain 00:38:15 loss: -0.7646 Lr: 6.27490e-04 +[2025-02-22 14:01:41,616 INFO hook.py line 109 2775932] Train: [81/100][150/800] Data 0.004 (0.003) Batch 0.165 (0.143) Remain 00:37:44 loss: -0.6896 Lr: 6.23702e-04 +[2025-02-22 14:01:48,783 INFO hook.py line 109 2775932] Train: [81/100][200/800] Data 0.004 (0.003) Batch 0.124 (0.143) Remain 00:37:38 loss: -0.7732 Lr: 6.19925e-04 +[2025-02-22 14:01:56,044 INFO hook.py line 109 2775932] Train: [81/100][250/800] Data 0.004 (0.004) Batch 0.143 (0.143) Remain 00:37:38 loss: -0.7111 Lr: 6.16157e-04 +[2025-02-22 14:02:03,278 INFO hook.py line 109 2775932] Train: [81/100][300/800] Data 0.004 (0.004) Batch 0.151 (0.144) Remain 00:37:35 loss: -0.6708 Lr: 6.12399e-04 +[2025-02-22 14:02:10,389 INFO hook.py line 109 2775932] Train: [81/100][350/800] Data 0.003 (0.004) Batch 0.150 (0.143) Remain 00:37:24 loss: -0.7995 Lr: 6.08652e-04 +[2025-02-22 14:02:17,538 INFO hook.py line 109 2775932] Train: [81/100][400/800] Data 0.003 (0.004) Batch 0.121 (0.143) Remain 00:37:16 loss: -0.6312 Lr: 6.04915e-04 +[2025-02-22 14:02:24,633 INFO hook.py line 109 2775932] Train: [81/100][450/800] Data 0.003 (0.004) Batch 0.143 (0.143) Remain 00:37:06 loss: -0.6429 Lr: 6.01188e-04 +[2025-02-22 14:02:32,015 INFO hook.py line 109 2775932] Train: [81/100][500/800] Data 0.003 (0.003) Batch 0.142 (0.144) Remain 00:37:06 loss: -0.6678 Lr: 5.97472e-04 +[2025-02-22 14:02:38,965 INFO hook.py line 109 2775932] Train: [81/100][550/800] Data 0.003 (0.003) Batch 0.143 (0.143) Remain 00:36:52 loss: -0.7105 Lr: 5.93765e-04 +[2025-02-22 14:02:45,956 INFO hook.py line 109 2775932] Train: [81/100][600/800] Data 0.003 (0.003) Batch 0.153 (0.143) Remain 00:36:41 loss: -0.5832 Lr: 5.90069e-04 +[2025-02-22 14:02:53,182 INFO hook.py line 109 2775932] Train: [81/100][650/800] Data 0.003 (0.003) Batch 0.144 (0.143) Remain 00:36:36 loss: -0.6938 Lr: 5.86383e-04 +[2025-02-22 14:03:00,496 INFO hook.py line 109 2775932] Train: [81/100][700/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 00:36:32 loss: -0.6974 Lr: 5.82708e-04 +[2025-02-22 14:03:07,519 INFO hook.py line 109 2775932] Train: [81/100][750/800] Data 0.003 (0.003) Batch 0.116 (0.143) Remain 00:36:22 loss: -0.8086 Lr: 5.79043e-04 +[2025-02-22 14:03:14,326 INFO hook.py line 109 2775932] Train: [81/100][800/800] Data 0.002 (0.003) Batch 0.136 (0.143) Remain 00:36:08 loss: -0.6089 Lr: 5.75388e-04 +[2025-02-22 14:03:14,327 INFO misc.py line 135 2775932] Train result: loss: -0.7133 seg_loss: 0.0992 bias_l1_loss: 0.1535 bias_cosine_loss: -0.9660 +[2025-02-22 14:03:14,328 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:03:21,178 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8846 +[2025-02-22 14:03:21,517 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7148 +[2025-02-22 14:03:21,602 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6659 +[2025-02-22 14:03:21,684 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6726 +[2025-02-22 14:03:22,261 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7152 +[2025-02-22 14:03:22,318 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.3546 +[2025-02-22 14:03:22,631 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.7009 +[2025-02-22 14:03:22,660 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4919 +[2025-02-22 14:03:22,801 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2469 +[2025-02-22 14:03:22,890 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0815 +[2025-02-22 14:03:23,232 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1316 +[2025-02-22 14:03:23,377 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0324 +[2025-02-22 14:03:23,475 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.2042 +[2025-02-22 14:03:23,598 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.5646 +[2025-02-22 14:03:23,706 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0184 +[2025-02-22 14:03:23,806 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7099 +[2025-02-22 14:03:23,969 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6198 +[2025-02-22 14:03:24,099 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3006 +[2025-02-22 14:03:24,253 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2361 +[2025-02-22 14:03:24,324 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0146 +[2025-02-22 14:03:24,492 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7505 +[2025-02-22 14:03:24,676 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3772 +[2025-02-22 14:03:24,761 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0036 +[2025-02-22 14:03:24,826 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0660 +[2025-02-22 14:03:24,906 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4827 +[2025-02-22 14:03:24,974 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.5339 +[2025-02-22 14:03:25,154 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1547 +[2025-02-22 14:03:25,300 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6257 +[2025-02-22 14:03:25,392 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7973 +[2025-02-22 14:03:25,474 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6681 +[2025-02-22 14:03:26,477 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6183 +[2025-02-22 14:03:26,730 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5266 +[2025-02-22 14:03:26,777 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5780 +[2025-02-22 14:03:26,886 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2404 +[2025-02-22 14:03:26,930 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.4941 +[2025-02-22 14:03:27,053 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6932 +[2025-02-22 14:03:27,131 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6741 +[2025-02-22 14:03:27,289 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7820 +[2025-02-22 14:03:27,467 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4985 +[2025-02-22 14:03:27,692 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9065 +[2025-02-22 14:03:27,904 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5989 +[2025-02-22 14:03:27,967 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4921 +[2025-02-22 14:03:28,016 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8483 +[2025-02-22 14:03:28,308 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6721 +[2025-02-22 14:03:28,362 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6542 +[2025-02-22 14:03:28,414 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4656 +[2025-02-22 14:03:28,503 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0165 +[2025-02-22 14:03:28,658 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6003 +[2025-02-22 14:03:28,802 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1769 +[2025-02-22 14:03:28,927 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2092 +[2025-02-22 14:03:29,032 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0811 +[2025-02-22 14:03:29,237 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5452 +[2025-02-22 14:03:29,278 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5382 +[2025-02-22 14:03:29,396 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.1980 +[2025-02-22 14:03:29,480 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8819 +[2025-02-22 14:03:29,520 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5850 +[2025-02-22 14:03:29,656 INFO evaluator.py line 595 2775932] Test: [57/78] Loss 0.0232 +[2025-02-22 14:03:29,693 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6037 +[2025-02-22 14:03:29,911 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3432 +[2025-02-22 14:03:30,014 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3883 +[2025-02-22 14:03:30,101 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5430 +[2025-02-22 14:03:30,153 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.4894 +[2025-02-22 14:03:30,305 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2349 +[2025-02-22 14:03:30,405 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1702 +[2025-02-22 14:03:30,476 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1323 +[2025-02-22 14:03:30,615 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1527 +[2025-02-22 14:03:30,773 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7641 +[2025-02-22 14:03:30,866 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1373 +[2025-02-22 14:03:30,912 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7093 +[2025-02-22 14:03:30,960 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.1684 +[2025-02-22 14:03:31,127 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4144 +[2025-02-22 14:03:31,156 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4601 +[2025-02-22 14:03:31,204 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8523 +[2025-02-22 14:03:31,313 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.2678 +[2025-02-22 14:03:31,511 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7060 +[2025-02-22 14:03:31,587 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2551 +[2025-02-22 14:03:31,747 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7164 +[2025-02-22 14:03:31,837 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6814 +[2025-02-22 14:03:44,293 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:03:44,293 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:03:44,293 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:03:44,293 INFO evaluator.py line 547 2775932] cabinet : 0.2860 0.4994 0.7286 +[2025-02-22 14:03:44,293 INFO evaluator.py line 547 2775932] bed : 0.3261 0.7098 0.8625 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] chair : 0.7496 0.9096 0.9474 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] sofa : 0.3355 0.5580 0.7549 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] table : 0.4258 0.6389 0.7643 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] door : 0.2774 0.4972 0.6215 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] window : 0.2737 0.4755 0.6728 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] bookshelf : 0.2769 0.5364 0.7622 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] picture : 0.3882 0.5718 0.6505 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] counter : 0.0476 0.1491 0.4819 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] desk : 0.1367 0.4542 0.8431 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] curtain : 0.2969 0.4993 0.6247 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] refridgerator : 0.4290 0.6111 0.6446 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] shower curtain : 0.4666 0.6382 0.7422 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] toilet : 0.8713 0.9733 0.9733 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] sink : 0.4268 0.6763 0.8664 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] bathtub : 0.6874 0.8052 0.9032 +[2025-02-22 14:03:44,294 INFO evaluator.py line 547 2775932] otherfurniture : 0.3930 0.5732 0.6746 +[2025-02-22 14:03:44,294 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:03:44,294 INFO evaluator.py line 554 2775932] average : 0.3942 0.5987 0.7510 +[2025-02-22 14:03:44,294 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:03:44,294 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:03:44,330 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 14:03:44,337 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:03:53,301 INFO hook.py line 109 2775932] Train: [82/100][50/800] Data 0.005 (0.003) Batch 0.177 (0.148) Remain 00:37:19 loss: -0.7698 Lr: 5.71744e-04 +[2025-02-22 14:04:00,905 INFO hook.py line 109 2775932] Train: [82/100][100/800] Data 0.003 (0.005) Batch 0.137 (0.150) Remain 00:37:45 loss: -0.5600 Lr: 5.68110e-04 +[2025-02-22 14:04:07,895 INFO hook.py line 109 2775932] Train: [82/100][150/800] Data 0.004 (0.004) Batch 0.153 (0.147) Remain 00:36:45 loss: -0.7759 Lr: 5.64486e-04 +[2025-02-22 14:04:14,913 INFO hook.py line 109 2775932] Train: [82/100][200/800] Data 0.003 (0.004) Batch 0.127 (0.145) Remain 00:36:14 loss: -0.7433 Lr: 5.60873e-04 +[2025-02-22 14:04:21,941 INFO hook.py line 109 2775932] Train: [82/100][250/800] Data 0.003 (0.004) Batch 0.129 (0.144) Remain 00:35:54 loss: -0.7878 Lr: 5.57270e-04 +[2025-02-22 14:04:29,314 INFO hook.py line 109 2775932] Train: [82/100][300/800] Data 0.003 (0.004) Batch 0.152 (0.145) Remain 00:35:55 loss: -0.8409 Lr: 5.53678e-04 +[2025-02-22 14:04:36,381 INFO hook.py line 109 2775932] Train: [82/100][350/800] Data 0.003 (0.004) Batch 0.135 (0.144) Remain 00:35:40 loss: -0.7704 Lr: 5.50096e-04 +[2025-02-22 14:04:43,326 INFO hook.py line 109 2775932] Train: [82/100][400/800] Data 0.003 (0.004) Batch 0.137 (0.144) Remain 00:35:23 loss: -0.7957 Lr: 5.46524e-04 +[2025-02-22 14:04:50,334 INFO hook.py line 109 2775932] Train: [82/100][450/800] Data 0.003 (0.004) Batch 0.148 (0.143) Remain 00:35:11 loss: -0.7317 Lr: 5.42963e-04 +[2025-02-22 14:04:57,301 INFO hook.py line 109 2775932] Train: [82/100][500/800] Data 0.003 (0.004) Batch 0.132 (0.143) Remain 00:34:58 loss: -0.7954 Lr: 5.39413e-04 +[2025-02-22 14:05:04,220 INFO hook.py line 109 2775932] Train: [82/100][550/800] Data 0.003 (0.004) Batch 0.139 (0.142) Remain 00:34:45 loss: -0.6274 Lr: 5.35873e-04 +[2025-02-22 14:05:11,234 INFO hook.py line 109 2775932] Train: [82/100][600/800] Data 0.004 (0.003) Batch 0.145 (0.142) Remain 00:34:35 loss: -0.8201 Lr: 5.32343e-04 +[2025-02-22 14:05:18,503 INFO hook.py line 109 2775932] Train: [82/100][650/800] Data 0.002 (0.003) Batch 0.140 (0.142) Remain 00:34:32 loss: -0.7384 Lr: 5.28824e-04 +[2025-02-22 14:05:25,580 INFO hook.py line 109 2775932] Train: [82/100][700/800] Data 0.004 (0.003) Batch 0.126 (0.142) Remain 00:34:24 loss: -0.7554 Lr: 5.25316e-04 +[2025-02-22 14:05:32,795 INFO hook.py line 109 2775932] Train: [82/100][750/800] Data 0.003 (0.003) Batch 0.132 (0.142) Remain 00:34:19 loss: -0.8010 Lr: 5.21818e-04 +[2025-02-22 14:05:39,571 INFO hook.py line 109 2775932] Train: [82/100][800/800] Data 0.002 (0.003) Batch 0.158 (0.142) Remain 00:34:05 loss: -0.7696 Lr: 5.18331e-04 +[2025-02-22 14:05:39,572 INFO misc.py line 135 2775932] Train result: loss: -0.7223 seg_loss: 0.0965 bias_l1_loss: 0.1480 bias_cosine_loss: -0.9668 +[2025-02-22 14:05:39,572 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:05:46,352 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8774 +[2025-02-22 14:05:46,832 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6639 +[2025-02-22 14:05:46,915 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6569 +[2025-02-22 14:05:46,989 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6452 +[2025-02-22 14:05:47,057 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7687 +[2025-02-22 14:05:47,136 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.2389 +[2025-02-22 14:05:47,466 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5445 +[2025-02-22 14:05:47,500 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6611 +[2025-02-22 14:05:47,648 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.2352 +[2025-02-22 14:05:47,709 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0063 +[2025-02-22 14:05:47,977 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1117 +[2025-02-22 14:05:48,100 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0676 +[2025-02-22 14:05:48,183 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.4715 +[2025-02-22 14:05:48,287 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.9462 +[2025-02-22 14:05:48,378 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.5147 +[2025-02-22 14:05:48,461 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6967 +[2025-02-22 14:05:48,605 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6152 +[2025-02-22 14:05:48,712 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3935 +[2025-02-22 14:05:48,866 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0462 +[2025-02-22 14:05:48,936 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0202 +[2025-02-22 14:05:49,099 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7486 +[2025-02-22 14:05:49,291 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2605 +[2025-02-22 14:05:49,388 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1295 +[2025-02-22 14:05:49,446 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0710 +[2025-02-22 14:05:49,528 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6729 +[2025-02-22 14:05:49,589 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6316 +[2025-02-22 14:05:49,732 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0345 +[2025-02-22 14:05:49,849 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5713 +[2025-02-22 14:05:49,934 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7953 +[2025-02-22 14:05:50,018 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6772 +[2025-02-22 14:05:51,080 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5857 +[2025-02-22 14:05:51,271 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3427 +[2025-02-22 14:05:51,321 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6174 +[2025-02-22 14:05:51,432 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3226 +[2025-02-22 14:05:51,475 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5925 +[2025-02-22 14:05:51,605 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6774 +[2025-02-22 14:05:51,682 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7209 +[2025-02-22 14:05:51,856 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7629 +[2025-02-22 14:05:52,069 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.2879 +[2025-02-22 14:05:52,341 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.7225 +[2025-02-22 14:05:52,575 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5758 +[2025-02-22 14:05:52,643 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4702 +[2025-02-22 14:05:52,734 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8429 +[2025-02-22 14:05:53,054 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7833 +[2025-02-22 14:05:53,107 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.5761 +[2025-02-22 14:05:53,189 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5251 +[2025-02-22 14:05:53,305 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2036 +[2025-02-22 14:05:53,480 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.2455 +[2025-02-22 14:05:53,641 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.0468 +[2025-02-22 14:05:53,778 INFO evaluator.py line 595 2775932] Test: [50/78] Loss -0.0361 +[2025-02-22 14:05:53,885 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3172 +[2025-02-22 14:05:54,089 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4598 +[2025-02-22 14:05:54,159 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5328 +[2025-02-22 14:05:54,287 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0519 +[2025-02-22 14:05:54,412 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8874 +[2025-02-22 14:05:54,477 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6360 +[2025-02-22 14:05:54,671 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1864 +[2025-02-22 14:05:54,728 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6242 +[2025-02-22 14:05:54,989 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3799 +[2025-02-22 14:05:55,114 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3044 +[2025-02-22 14:05:55,227 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5972 +[2025-02-22 14:05:55,289 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5383 +[2025-02-22 14:05:55,459 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1415 +[2025-02-22 14:05:55,588 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0222 +[2025-02-22 14:05:55,670 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2446 +[2025-02-22 14:05:55,852 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1914 +[2025-02-22 14:05:56,074 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7292 +[2025-02-22 14:05:56,210 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0180 +[2025-02-22 14:05:56,275 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7601 +[2025-02-22 14:05:56,340 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.3230 +[2025-02-22 14:05:56,542 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3840 +[2025-02-22 14:05:56,580 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5591 +[2025-02-22 14:05:56,636 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8640 +[2025-02-22 14:05:56,773 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.2350 +[2025-02-22 14:05:57,039 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7347 +[2025-02-22 14:05:57,136 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0823 +[2025-02-22 14:05:57,321 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7522 +[2025-02-22 14:05:57,429 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6877 +[2025-02-22 14:06:10,531 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:06:10,531 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:06:10,531 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] cabinet : 0.2885 0.5389 0.7187 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] bed : 0.3472 0.7272 0.8395 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] chair : 0.7576 0.9168 0.9490 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] sofa : 0.3413 0.5709 0.7929 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] table : 0.4432 0.6898 0.8015 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] door : 0.2986 0.5062 0.6351 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] window : 0.2404 0.4007 0.6151 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] bookshelf : 0.2780 0.5847 0.7220 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] picture : 0.3150 0.4507 0.5384 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] counter : 0.0451 0.1733 0.5669 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] desk : 0.1054 0.3306 0.7183 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] curtain : 0.3330 0.5403 0.6757 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] refridgerator : 0.3940 0.5670 0.6320 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] shower curtain : 0.4815 0.6346 0.7742 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] toilet : 0.8549 0.9828 0.9828 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] sink : 0.4121 0.7086 0.8744 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] bathtub : 0.6270 0.7598 0.8646 +[2025-02-22 14:06:10,531 INFO evaluator.py line 547 2775932] otherfurniture : 0.4075 0.5791 0.6665 +[2025-02-22 14:06:10,531 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:06:10,531 INFO evaluator.py line 554 2775932] average : 0.3872 0.5923 0.7426 +[2025-02-22 14:06:10,531 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:06:10,532 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:06:10,562 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 14:06:10,569 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:06:19,153 INFO hook.py line 109 2775932] Train: [83/100][50/800] Data 0.003 (0.003) Batch 0.127 (0.146) Remain 00:34:58 loss: -0.7385 Lr: 5.14854e-04 +[2025-02-22 14:06:26,123 INFO hook.py line 109 2775932] Train: [83/100][100/800] Data 0.003 (0.003) Batch 0.117 (0.143) Remain 00:34:00 loss: -0.8140 Lr: 5.11389e-04 +[2025-02-22 14:06:33,117 INFO hook.py line 109 2775932] Train: [83/100][150/800] Data 0.003 (0.003) Batch 0.160 (0.142) Remain 00:33:39 loss: -0.7500 Lr: 5.07933e-04 +[2025-02-22 14:06:40,331 INFO hook.py line 109 2775932] Train: [83/100][200/800] Data 0.004 (0.003) Batch 0.160 (0.142) Remain 00:33:42 loss: -0.5783 Lr: 5.04488e-04 +[2025-02-22 14:06:47,392 INFO hook.py line 109 2775932] Train: [83/100][250/800] Data 0.003 (0.003) Batch 0.150 (0.142) Remain 00:33:31 loss: -0.5838 Lr: 5.01054e-04 +[2025-02-22 14:06:54,723 INFO hook.py line 109 2775932] Train: [83/100][300/800] Data 0.003 (0.004) Batch 0.131 (0.143) Remain 00:33:34 loss: -0.7903 Lr: 4.97631e-04 +[2025-02-22 14:07:02,000 INFO hook.py line 109 2775932] Train: [83/100][350/800] Data 0.003 (0.003) Batch 0.131 (0.143) Remain 00:33:33 loss: -0.7668 Lr: 4.94218e-04 +[2025-02-22 14:07:09,086 INFO hook.py line 109 2775932] Train: [83/100][400/800] Data 0.002 (0.003) Batch 0.148 (0.143) Remain 00:33:23 loss: -0.7863 Lr: 4.90816e-04 +[2025-02-22 14:07:16,029 INFO hook.py line 109 2775932] Train: [83/100][450/800] Data 0.002 (0.003) Batch 0.131 (0.143) Remain 00:33:09 loss: -0.7565 Lr: 4.87425e-04 +[2025-02-22 14:07:23,000 INFO hook.py line 109 2775932] Train: [83/100][500/800] Data 0.004 (0.003) Batch 0.155 (0.142) Remain 00:32:57 loss: -0.6827 Lr: 4.84045e-04 +[2025-02-22 14:07:30,121 INFO hook.py line 109 2775932] Train: [83/100][550/800] Data 0.002 (0.003) Batch 0.128 (0.142) Remain 00:32:50 loss: -0.7379 Lr: 4.80675e-04 +[2025-02-22 14:07:37,414 INFO hook.py line 109 2775932] Train: [83/100][600/800] Data 0.003 (0.003) Batch 0.239 (0.143) Remain 00:32:47 loss: -0.6897 Lr: 4.77316e-04 +[2025-02-22 14:07:44,521 INFO hook.py line 109 2775932] Train: [83/100][650/800] Data 0.004 (0.003) Batch 0.135 (0.143) Remain 00:32:40 loss: -0.6069 Lr: 4.73968e-04 +[2025-02-22 14:07:51,559 INFO hook.py line 109 2775932] Train: [83/100][700/800] Data 0.003 (0.003) Batch 0.130 (0.142) Remain 00:32:31 loss: -0.6816 Lr: 4.70630e-04 +[2025-02-22 14:07:58,521 INFO hook.py line 109 2775932] Train: [83/100][750/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:32:21 loss: -0.7521 Lr: 4.67304e-04 +[2025-02-22 14:08:05,065 INFO hook.py line 109 2775932] Train: [83/100][800/800] Data 0.002 (0.003) Batch 0.124 (0.142) Remain 00:32:04 loss: -0.7478 Lr: 4.63988e-04 +[2025-02-22 14:08:05,066 INFO misc.py line 135 2775932] Train result: loss: -0.7331 seg_loss: 0.0909 bias_l1_loss: 0.1442 bias_cosine_loss: -0.9683 +[2025-02-22 14:08:05,066 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:08:11,940 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8751 +[2025-02-22 14:08:12,408 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6897 +[2025-02-22 14:08:12,481 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6710 +[2025-02-22 14:08:12,552 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6503 +[2025-02-22 14:08:12,621 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7573 +[2025-02-22 14:08:12,678 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.4689 +[2025-02-22 14:08:12,988 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6648 +[2025-02-22 14:08:13,019 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4305 +[2025-02-22 14:08:13,168 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.1702 +[2025-02-22 14:08:13,235 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2548 +[2025-02-22 14:08:13,510 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2056 +[2025-02-22 14:08:13,636 INFO evaluator.py line 595 2775932] Test: [12/78] Loss -0.0378 +[2025-02-22 14:08:13,719 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.0518 +[2025-02-22 14:08:13,822 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6658 +[2025-02-22 14:08:13,921 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.3877 +[2025-02-22 14:08:14,000 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6815 +[2025-02-22 14:08:14,152 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.5680 +[2025-02-22 14:08:14,256 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.1989 +[2025-02-22 14:08:14,416 INFO evaluator.py line 595 2775932] Test: [19/78] Loss 0.1144 +[2025-02-22 14:08:14,530 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1616 +[2025-02-22 14:08:14,719 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7178 +[2025-02-22 14:08:14,911 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4221 +[2025-02-22 14:08:15,002 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0847 +[2025-02-22 14:08:15,078 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1330 +[2025-02-22 14:08:15,166 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6341 +[2025-02-22 14:08:15,268 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7453 +[2025-02-22 14:08:15,464 INFO evaluator.py line 595 2775932] Test: [27/78] Loss -0.0386 +[2025-02-22 14:08:15,599 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5096 +[2025-02-22 14:08:15,689 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7682 +[2025-02-22 14:08:15,792 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.6679 +[2025-02-22 14:08:16,814 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5830 +[2025-02-22 14:08:17,091 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3183 +[2025-02-22 14:08:17,143 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7488 +[2025-02-22 14:08:17,250 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4138 +[2025-02-22 14:08:17,309 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5738 +[2025-02-22 14:08:17,441 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.7955 +[2025-02-22 14:08:17,521 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6143 +[2025-02-22 14:08:17,680 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7772 +[2025-02-22 14:08:17,863 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.3647 +[2025-02-22 14:08:18,086 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.2883 +[2025-02-22 14:08:18,289 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5931 +[2025-02-22 14:08:18,352 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3885 +[2025-02-22 14:08:18,429 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8469 +[2025-02-22 14:08:18,728 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7616 +[2025-02-22 14:08:18,785 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6647 +[2025-02-22 14:08:18,848 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4810 +[2025-02-22 14:08:18,964 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.0061 +[2025-02-22 14:08:19,114 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5435 +[2025-02-22 14:08:19,269 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3326 +[2025-02-22 14:08:19,388 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0984 +[2025-02-22 14:08:19,511 INFO evaluator.py line 595 2775932] Test: [51/78] Loss 0.0589 +[2025-02-22 14:08:19,714 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5576 +[2025-02-22 14:08:19,764 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5600 +[2025-02-22 14:08:19,926 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.3851 +[2025-02-22 14:08:20,070 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8936 +[2025-02-22 14:08:20,137 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6835 +[2025-02-22 14:08:20,311 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.3334 +[2025-02-22 14:08:20,360 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6344 +[2025-02-22 14:08:20,617 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3858 +[2025-02-22 14:08:20,736 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1287 +[2025-02-22 14:08:20,846 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5651 +[2025-02-22 14:08:20,917 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.7133 +[2025-02-22 14:08:21,142 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1444 +[2025-02-22 14:08:21,289 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.1105 +[2025-02-22 14:08:21,392 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1956 +[2025-02-22 14:08:21,558 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.4458 +[2025-02-22 14:08:21,748 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7255 +[2025-02-22 14:08:21,852 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1468 +[2025-02-22 14:08:21,912 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7326 +[2025-02-22 14:08:21,970 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4667 +[2025-02-22 14:08:22,169 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5049 +[2025-02-22 14:08:22,213 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.3762 +[2025-02-22 14:08:22,269 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8544 +[2025-02-22 14:08:22,401 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.2079 +[2025-02-22 14:08:22,633 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7228 +[2025-02-22 14:08:22,727 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.3065 +[2025-02-22 14:08:22,906 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6980 +[2025-02-22 14:08:23,023 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6286 +[2025-02-22 14:08:36,449 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:08:36,449 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:08:36,449 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] cabinet : 0.2887 0.5242 0.7252 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] bed : 0.3566 0.7152 0.8517 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] chair : 0.7485 0.8984 0.9404 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] sofa : 0.3578 0.5705 0.8284 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] table : 0.4323 0.6726 0.7724 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] door : 0.2826 0.5109 0.6360 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] window : 0.2420 0.4268 0.6086 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] bookshelf : 0.2497 0.4834 0.6765 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] picture : 0.3734 0.5456 0.6116 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] counter : 0.0565 0.2008 0.5402 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] desk : 0.1127 0.3607 0.7979 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] curtain : 0.3459 0.5189 0.6967 +[2025-02-22 14:08:36,449 INFO evaluator.py line 547 2775932] refridgerator : 0.3823 0.5381 0.5689 +[2025-02-22 14:08:36,450 INFO evaluator.py line 547 2775932] shower curtain : 0.4501 0.6444 0.7868 +[2025-02-22 14:08:36,450 INFO evaluator.py line 547 2775932] toilet : 0.8971 0.9997 0.9997 +[2025-02-22 14:08:36,450 INFO evaluator.py line 547 2775932] sink : 0.4534 0.7458 0.8902 +[2025-02-22 14:08:36,450 INFO evaluator.py line 547 2775932] bathtub : 0.6645 0.7742 0.8710 +[2025-02-22 14:08:36,450 INFO evaluator.py line 547 2775932] otherfurniture : 0.3980 0.5548 0.6454 +[2025-02-22 14:08:36,450 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:08:36,450 INFO evaluator.py line 554 2775932] average : 0.3940 0.5936 0.7471 +[2025-02-22 14:08:36,450 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:08:36,450 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:08:36,479 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 14:08:36,488 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:08:45,296 INFO hook.py line 109 2775932] Train: [84/100][50/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:32:09 loss: -0.7540 Lr: 4.60683e-04 +[2025-02-22 14:08:52,292 INFO hook.py line 109 2775932] Train: [84/100][100/800] Data 0.002 (0.003) Batch 0.149 (0.141) Remain 00:31:45 loss: -0.6572 Lr: 4.57389e-04 +[2025-02-22 14:08:59,536 INFO hook.py line 109 2775932] Train: [84/100][150/800] Data 0.002 (0.005) Batch 0.132 (0.142) Remain 00:31:55 loss: -0.7708 Lr: 4.54106e-04 +[2025-02-22 14:09:06,674 INFO hook.py line 109 2775932] Train: [84/100][200/800] Data 0.004 (0.004) Batch 0.145 (0.142) Remain 00:31:49 loss: -0.7778 Lr: 4.50833e-04 +[2025-02-22 14:09:13,725 INFO hook.py line 109 2775932] Train: [84/100][250/800] Data 0.002 (0.004) Batch 0.149 (0.142) Remain 00:31:38 loss: -0.7526 Lr: 4.47572e-04 +[2025-02-22 14:09:20,806 INFO hook.py line 109 2775932] Train: [84/100][300/800] Data 0.003 (0.004) Batch 0.132 (0.142) Remain 00:31:29 loss: -0.7578 Lr: 4.44321e-04 +[2025-02-22 14:09:27,792 INFO hook.py line 109 2775932] Train: [84/100][350/800] Data 0.003 (0.004) Batch 0.143 (0.142) Remain 00:31:18 loss: -0.7310 Lr: 4.41082e-04 +[2025-02-22 14:09:34,762 INFO hook.py line 109 2775932] Train: [84/100][400/800] Data 0.003 (0.004) Batch 0.158 (0.141) Remain 00:31:07 loss: -0.5841 Lr: 4.37853e-04 +[2025-02-22 14:09:41,794 INFO hook.py line 109 2775932] Train: [84/100][450/800] Data 0.003 (0.003) Batch 0.143 (0.141) Remain 00:30:58 loss: -0.7538 Lr: 4.34635e-04 +[2025-02-22 14:09:49,021 INFO hook.py line 109 2775932] Train: [84/100][500/800] Data 0.003 (0.003) Batch 0.149 (0.142) Remain 00:30:56 loss: -0.8239 Lr: 4.31428e-04 +[2025-02-22 14:09:55,925 INFO hook.py line 109 2775932] Train: [84/100][550/800] Data 0.003 (0.003) Batch 0.127 (0.141) Remain 00:30:44 loss: -0.7637 Lr: 4.28232e-04 +[2025-02-22 14:10:03,164 INFO hook.py line 109 2775932] Train: [84/100][600/800] Data 0.003 (0.003) Batch 0.164 (0.142) Remain 00:30:41 loss: -0.7968 Lr: 4.25048e-04 +[2025-02-22 14:10:10,517 INFO hook.py line 109 2775932] Train: [84/100][650/800] Data 0.002 (0.003) Batch 0.138 (0.142) Remain 00:30:39 loss: -0.6826 Lr: 4.21874e-04 +[2025-02-22 14:10:17,623 INFO hook.py line 109 2775932] Train: [84/100][700/800] Data 0.003 (0.003) Batch 0.143 (0.142) Remain 00:30:32 loss: -0.8102 Lr: 4.18711e-04 +[2025-02-22 14:10:24,847 INFO hook.py line 109 2775932] Train: [84/100][750/800] Data 0.004 (0.003) Batch 0.140 (0.142) Remain 00:30:27 loss: -0.7353 Lr: 4.15559e-04 +[2025-02-22 14:10:31,852 INFO hook.py line 109 2775932] Train: [84/100][800/800] Data 0.001 (0.003) Batch 0.114 (0.142) Remain 00:30:18 loss: -0.7754 Lr: 4.12418e-04 +[2025-02-22 14:10:31,853 INFO misc.py line 135 2775932] Train result: loss: -0.7349 seg_loss: 0.0926 bias_l1_loss: 0.1416 bias_cosine_loss: -0.9691 +[2025-02-22 14:10:31,853 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:10:39,184 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8719 +[2025-02-22 14:10:39,473 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6790 +[2025-02-22 14:10:39,544 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6939 +[2025-02-22 14:10:39,620 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6668 +[2025-02-22 14:10:39,700 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8205 +[2025-02-22 14:10:39,765 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5954 +[2025-02-22 14:10:40,070 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6128 +[2025-02-22 14:10:40,107 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5698 +[2025-02-22 14:10:40,252 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3212 +[2025-02-22 14:10:40,322 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0405 +[2025-02-22 14:10:40,609 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1312 +[2025-02-22 14:10:40,741 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1196 +[2025-02-22 14:10:40,829 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.7928 +[2025-02-22 14:10:40,957 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.4601 +[2025-02-22 14:10:41,069 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0588 +[2025-02-22 14:10:41,158 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6765 +[2025-02-22 14:10:41,324 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6125 +[2025-02-22 14:10:41,445 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.4185 +[2025-02-22 14:10:41,613 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.0129 +[2025-02-22 14:10:41,694 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.2811 +[2025-02-22 14:10:41,885 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7113 +[2025-02-22 14:10:42,088 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.1596 +[2025-02-22 14:10:42,187 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1866 +[2025-02-22 14:10:42,261 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0791 +[2025-02-22 14:10:42,367 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.1810 +[2025-02-22 14:10:42,457 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6291 +[2025-02-22 14:10:42,647 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.4495 +[2025-02-22 14:10:42,780 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4954 +[2025-02-22 14:10:42,874 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7615 +[2025-02-22 14:10:42,954 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7580 +[2025-02-22 14:10:44,011 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6051 +[2025-02-22 14:10:44,209 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.7021 +[2025-02-22 14:10:44,276 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7352 +[2025-02-22 14:10:44,395 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4241 +[2025-02-22 14:10:44,446 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5473 +[2025-02-22 14:10:44,577 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6112 +[2025-02-22 14:10:44,644 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.6740 +[2025-02-22 14:10:44,775 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7352 +[2025-02-22 14:10:44,942 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 1.0938 +[2025-02-22 14:10:45,144 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9506 +[2025-02-22 14:10:45,312 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6411 +[2025-02-22 14:10:45,366 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.3955 +[2025-02-22 14:10:45,412 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8522 +[2025-02-22 14:10:45,668 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7819 +[2025-02-22 14:10:45,710 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6816 +[2025-02-22 14:10:45,754 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5186 +[2025-02-22 14:10:45,845 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.2908 +[2025-02-22 14:10:45,973 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5235 +[2025-02-22 14:10:46,091 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.2287 +[2025-02-22 14:10:46,184 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1927 +[2025-02-22 14:10:46,266 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2017 +[2025-02-22 14:10:46,416 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4909 +[2025-02-22 14:10:46,453 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6127 +[2025-02-22 14:10:46,573 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9478 +[2025-02-22 14:10:46,667 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8923 +[2025-02-22 14:10:46,718 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6474 +[2025-02-22 14:10:46,865 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2301 +[2025-02-22 14:10:46,925 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6392 +[2025-02-22 14:10:47,162 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4330 +[2025-02-22 14:10:47,264 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4220 +[2025-02-22 14:10:47,348 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4075 +[2025-02-22 14:10:47,404 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6034 +[2025-02-22 14:10:47,557 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.0110 +[2025-02-22 14:10:47,664 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0464 +[2025-02-22 14:10:47,739 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1135 +[2025-02-22 14:10:47,874 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2362 +[2025-02-22 14:10:48,049 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7113 +[2025-02-22 14:10:48,146 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1685 +[2025-02-22 14:10:48,195 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7007 +[2025-02-22 14:10:48,244 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.0189 +[2025-02-22 14:10:48,418 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.2427 +[2025-02-22 14:10:48,453 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.5529 +[2025-02-22 14:10:48,503 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8770 +[2025-02-22 14:10:48,606 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.9740 +[2025-02-22 14:10:48,793 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7173 +[2025-02-22 14:10:48,871 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1245 +[2025-02-22 14:10:49,027 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6986 +[2025-02-22 14:10:49,130 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6650 +[2025-02-22 14:11:02,235 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:11:02,236 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:11:02,236 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] cabinet : 0.2880 0.5100 0.7147 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] bed : 0.3321 0.7157 0.8633 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] chair : 0.7449 0.8984 0.9425 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] sofa : 0.3687 0.5853 0.8042 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] table : 0.4495 0.7286 0.8230 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] door : 0.2807 0.5068 0.6158 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] window : 0.2353 0.4343 0.6389 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] bookshelf : 0.2822 0.5758 0.7474 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] picture : 0.3642 0.5215 0.5841 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] counter : 0.0432 0.1440 0.5876 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] desk : 0.1282 0.3749 0.7592 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] curtain : 0.3016 0.5208 0.6197 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] refridgerator : 0.4613 0.6059 0.6914 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] shower curtain : 0.4210 0.6013 0.6953 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] toilet : 0.8887 1.0000 1.0000 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] sink : 0.3964 0.7026 0.8808 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] bathtub : 0.6768 0.7742 0.8710 +[2025-02-22 14:11:02,236 INFO evaluator.py line 547 2775932] otherfurniture : 0.3953 0.5722 0.6689 +[2025-02-22 14:11:02,236 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:11:02,236 INFO evaluator.py line 554 2775932] average : 0.3921 0.5985 0.7504 +[2025-02-22 14:11:02,236 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:11:02,236 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:11:02,264 INFO misc.py line 164 2775932] Currently Best AP50: 0.6065 +[2025-02-22 14:11:02,271 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:11:10,758 INFO hook.py line 109 2775932] Train: [85/100][50/800] Data 0.003 (0.003) Batch 0.124 (0.147) Remain 00:31:15 loss: -0.6685 Lr: 4.09289e-04 +[2025-02-22 14:11:17,740 INFO hook.py line 109 2775932] Train: [85/100][100/800] Data 0.003 (0.003) Batch 0.140 (0.143) Remain 00:30:19 loss: -0.5265 Lr: 4.06170e-04 +[2025-02-22 14:11:24,780 INFO hook.py line 109 2775932] Train: [85/100][150/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 00:30:01 loss: -0.8118 Lr: 4.03062e-04 +[2025-02-22 14:11:31,876 INFO hook.py line 109 2775932] Train: [85/100][200/800] Data 0.003 (0.003) Batch 0.131 (0.142) Remain 00:29:53 loss: -0.6640 Lr: 3.99966e-04 +[2025-02-22 14:11:38,888 INFO hook.py line 109 2775932] Train: [85/100][250/800] Data 0.003 (0.003) Batch 0.134 (0.142) Remain 00:29:40 loss: -0.7881 Lr: 3.96881e-04 +[2025-02-22 14:11:45,940 INFO hook.py line 109 2775932] Train: [85/100][300/800] Data 0.003 (0.003) Batch 0.141 (0.142) Remain 00:29:31 loss: -0.7730 Lr: 3.93806e-04 +[2025-02-22 14:11:53,315 INFO hook.py line 109 2775932] Train: [85/100][350/800] Data 0.003 (0.003) Batch 0.139 (0.143) Remain 00:29:34 loss: -0.7742 Lr: 3.90743e-04 +[2025-02-22 14:12:00,270 INFO hook.py line 109 2775932] Train: [85/100][400/800] Data 0.003 (0.003) Batch 0.136 (0.142) Remain 00:29:22 loss: -0.6953 Lr: 3.87691e-04 +[2025-02-22 14:12:07,401 INFO hook.py line 109 2775932] Train: [85/100][450/800] Data 0.003 (0.003) Batch 0.155 (0.142) Remain 00:29:16 loss: -0.7533 Lr: 3.84651e-04 +[2025-02-22 14:12:14,334 INFO hook.py line 109 2775932] Train: [85/100][500/800] Data 0.003 (0.003) Batch 0.117 (0.142) Remain 00:29:04 loss: -0.7716 Lr: 3.81621e-04 +[2025-02-22 14:12:21,427 INFO hook.py line 109 2775932] Train: [85/100][550/800] Data 0.005 (0.003) Batch 0.137 (0.142) Remain 00:28:57 loss: -0.7922 Lr: 3.78602e-04 +[2025-02-22 14:12:28,485 INFO hook.py line 109 2775932] Train: [85/100][600/800] Data 0.002 (0.003) Batch 0.125 (0.142) Remain 00:28:49 loss: -0.7460 Lr: 3.75595e-04 +[2025-02-22 14:12:35,626 INFO hook.py line 109 2775932] Train: [85/100][650/800] Data 0.004 (0.003) Batch 0.131 (0.142) Remain 00:28:43 loss: -0.5467 Lr: 3.72599e-04 +[2025-02-22 14:12:42,887 INFO hook.py line 109 2775932] Train: [85/100][700/800] Data 0.003 (0.003) Batch 0.142 (0.142) Remain 00:28:39 loss: -0.8282 Lr: 3.69674e-04 +[2025-02-22 14:12:50,038 INFO hook.py line 109 2775932] Train: [85/100][750/800] Data 0.003 (0.003) Batch 0.138 (0.142) Remain 00:28:33 loss: -0.6898 Lr: 3.66700e-04 +[2025-02-22 14:12:56,892 INFO hook.py line 109 2775932] Train: [85/100][800/800] Data 0.001 (0.003) Batch 0.105 (0.142) Remain 00:28:22 loss: -0.6425 Lr: 3.63738e-04 +[2025-02-22 14:12:56,893 INFO misc.py line 135 2775932] Train result: loss: -0.7410 seg_loss: 0.0900 bias_l1_loss: 0.1388 bias_cosine_loss: -0.9698 +[2025-02-22 14:12:56,893 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:13:03,537 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8739 +[2025-02-22 14:13:04,398 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6558 +[2025-02-22 14:13:04,478 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6622 +[2025-02-22 14:13:04,767 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6280 +[2025-02-22 14:13:04,843 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8117 +[2025-02-22 14:13:04,929 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.4881 +[2025-02-22 14:13:05,237 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5735 +[2025-02-22 14:13:05,272 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5771 +[2025-02-22 14:13:05,436 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3393 +[2025-02-22 14:13:05,500 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0651 +[2025-02-22 14:13:05,785 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2006 +[2025-02-22 14:13:05,914 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0413 +[2025-02-22 14:13:06,005 INFO evaluator.py line 595 2775932] Test: [13/78] Loss 0.3488 +[2025-02-22 14:13:06,115 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 2.0376 +[2025-02-22 14:13:06,212 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1095 +[2025-02-22 14:13:06,298 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7248 +[2025-02-22 14:13:06,445 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6266 +[2025-02-22 14:13:06,552 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3949 +[2025-02-22 14:13:06,715 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1378 +[2025-02-22 14:13:06,789 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1816 +[2025-02-22 14:13:06,958 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7398 +[2025-02-22 14:13:07,145 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4654 +[2025-02-22 14:13:07,235 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0808 +[2025-02-22 14:13:07,304 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0250 +[2025-02-22 14:13:07,376 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6590 +[2025-02-22 14:13:07,436 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6685 +[2025-02-22 14:13:07,600 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0539 +[2025-02-22 14:13:07,719 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4728 +[2025-02-22 14:13:07,806 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7895 +[2025-02-22 14:13:07,883 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.8003 +[2025-02-22 14:13:08,712 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.5995 +[2025-02-22 14:13:08,940 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.4524 +[2025-02-22 14:13:08,987 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7218 +[2025-02-22 14:13:09,100 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4479 +[2025-02-22 14:13:09,141 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6717 +[2025-02-22 14:13:09,261 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6230 +[2025-02-22 14:13:09,327 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7921 +[2025-02-22 14:13:09,474 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7470 +[2025-02-22 14:13:09,642 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.4155 +[2025-02-22 14:13:09,866 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9687 +[2025-02-22 14:13:10,075 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.5641 +[2025-02-22 14:13:10,146 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4026 +[2025-02-22 14:13:10,201 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8505 +[2025-02-22 14:13:10,501 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7312 +[2025-02-22 14:13:10,555 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6514 +[2025-02-22 14:13:10,608 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5421 +[2025-02-22 14:13:10,746 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5805 +[2025-02-22 14:13:10,910 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5037 +[2025-02-22 14:13:11,063 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1101 +[2025-02-22 14:13:11,173 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2334 +[2025-02-22 14:13:11,269 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.4596 +[2025-02-22 14:13:11,454 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4681 +[2025-02-22 14:13:11,501 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6250 +[2025-02-22 14:13:11,625 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.8445 +[2025-02-22 14:13:11,730 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9039 +[2025-02-22 14:13:11,778 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6389 +[2025-02-22 14:13:11,946 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.3678 +[2025-02-22 14:13:11,998 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6096 +[2025-02-22 14:13:12,272 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3749 +[2025-02-22 14:13:12,390 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4782 +[2025-02-22 14:13:12,492 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3122 +[2025-02-22 14:13:12,568 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5654 +[2025-02-22 14:13:12,782 INFO evaluator.py line 595 2775932] Test: [63/78] Loss 0.3335 +[2025-02-22 14:13:12,911 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0248 +[2025-02-22 14:13:13,005 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1471 +[2025-02-22 14:13:13,175 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2664 +[2025-02-22 14:13:13,394 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7664 +[2025-02-22 14:13:13,518 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.2351 +[2025-02-22 14:13:13,575 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7411 +[2025-02-22 14:13:13,635 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.2751 +[2025-02-22 14:13:13,842 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3701 +[2025-02-22 14:13:13,880 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4353 +[2025-02-22 14:13:13,942 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8671 +[2025-02-22 14:13:14,063 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.9761 +[2025-02-22 14:13:14,303 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7210 +[2025-02-22 14:13:14,425 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1032 +[2025-02-22 14:13:14,626 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.5427 +[2025-02-22 14:13:14,769 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.7239 +[2025-02-22 14:13:26,829 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:13:26,829 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:13:26,829 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] cabinet : 0.2926 0.5266 0.7026 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] bed : 0.3350 0.7383 0.8395 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] chair : 0.7575 0.9063 0.9465 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] sofa : 0.3911 0.6489 0.8478 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] table : 0.4459 0.7040 0.8329 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] door : 0.2901 0.5203 0.6445 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] window : 0.2472 0.4328 0.6312 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] bookshelf : 0.2598 0.5642 0.7532 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] picture : 0.3461 0.4850 0.5731 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] counter : 0.0673 0.3027 0.6311 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] desk : 0.1251 0.4296 0.8002 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] curtain : 0.2928 0.5178 0.6761 +[2025-02-22 14:13:26,829 INFO evaluator.py line 547 2775932] refridgerator : 0.4086 0.5834 0.6519 +[2025-02-22 14:13:26,830 INFO evaluator.py line 547 2775932] shower curtain : 0.4699 0.6041 0.7041 +[2025-02-22 14:13:26,830 INFO evaluator.py line 547 2775932] toilet : 0.8858 1.0000 1.0000 +[2025-02-22 14:13:26,830 INFO evaluator.py line 547 2775932] sink : 0.3960 0.6528 0.8489 +[2025-02-22 14:13:26,830 INFO evaluator.py line 547 2775932] bathtub : 0.6621 0.7742 0.9032 +[2025-02-22 14:13:26,830 INFO evaluator.py line 547 2775932] otherfurniture : 0.4083 0.5730 0.6829 +[2025-02-22 14:13:26,830 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:13:26,830 INFO evaluator.py line 554 2775932] average : 0.3934 0.6091 0.7594 +[2025-02-22 14:13:26,830 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:13:26,830 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:13:26,858 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.6091 +[2025-02-22 14:13:26,867 INFO misc.py line 164 2775932] Currently Best AP50: 0.6091 +[2025-02-22 14:13:26,867 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:13:36,637 INFO hook.py line 109 2775932] Train: [86/100][50/800] Data 0.003 (0.004) Batch 0.149 (0.155) Remain 00:30:50 loss: -0.7811 Lr: 3.60786e-04 +[2025-02-22 14:13:43,709 INFO hook.py line 109 2775932] Train: [86/100][100/800] Data 0.003 (0.003) Batch 0.139 (0.148) Remain 00:29:20 loss: -0.8120 Lr: 3.57846e-04 +[2025-02-22 14:13:51,012 INFO hook.py line 109 2775932] Train: [86/100][150/800] Data 0.005 (0.003) Batch 0.268 (0.147) Remain 00:29:05 loss: -0.7903 Lr: 3.54918e-04 +[2025-02-22 14:13:58,308 INFO hook.py line 109 2775932] Train: [86/100][200/800] Data 0.003 (0.004) Batch 0.146 (0.147) Remain 00:28:54 loss: -0.8468 Lr: 3.52000e-04 +[2025-02-22 14:14:05,298 INFO hook.py line 109 2775932] Train: [86/100][250/800] Data 0.002 (0.004) Batch 0.127 (0.145) Remain 00:28:29 loss: -0.7445 Lr: 3.49094e-04 +[2025-02-22 14:14:12,417 INFO hook.py line 109 2775932] Train: [86/100][300/800] Data 0.003 (0.004) Batch 0.129 (0.145) Remain 00:28:16 loss: -0.8055 Lr: 3.46199e-04 +[2025-02-22 14:14:19,435 INFO hook.py line 109 2775932] Train: [86/100][350/800] Data 0.003 (0.004) Batch 0.128 (0.144) Remain 00:28:01 loss: -0.7801 Lr: 3.43316e-04 +[2025-02-22 14:14:26,630 INFO hook.py line 109 2775932] Train: [86/100][400/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 00:27:53 loss: -0.7547 Lr: 3.40444e-04 +[2025-02-22 14:14:33,765 INFO hook.py line 109 2775932] Train: [86/100][450/800] Data 0.003 (0.003) Batch 0.139 (0.144) Remain 00:27:44 loss: -0.7834 Lr: 3.37583e-04 +[2025-02-22 14:14:40,894 INFO hook.py line 109 2775932] Train: [86/100][500/800] Data 0.003 (0.003) Batch 0.133 (0.144) Remain 00:27:35 loss: -0.7638 Lr: 3.34734e-04 +[2025-02-22 14:14:47,835 INFO hook.py line 109 2775932] Train: [86/100][550/800] Data 0.003 (0.003) Batch 0.131 (0.143) Remain 00:27:22 loss: -0.7744 Lr: 3.31896e-04 +[2025-02-22 14:14:55,043 INFO hook.py line 109 2775932] Train: [86/100][600/800] Data 0.002 (0.003) Batch 0.134 (0.144) Remain 00:27:16 loss: -0.7661 Lr: 3.29069e-04 +[2025-02-22 14:15:02,253 INFO hook.py line 109 2775932] Train: [86/100][650/800] Data 0.003 (0.003) Batch 0.128 (0.144) Remain 00:27:09 loss: -0.7385 Lr: 3.26254e-04 +[2025-02-22 14:15:09,200 INFO hook.py line 109 2775932] Train: [86/100][700/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 00:26:58 loss: -0.8136 Lr: 3.23450e-04 +[2025-02-22 14:15:16,565 INFO hook.py line 109 2775932] Train: [86/100][750/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 00:26:54 loss: -0.7739 Lr: 3.20658e-04 +[2025-02-22 14:15:23,415 INFO hook.py line 109 2775932] Train: [86/100][800/800] Data 0.001 (0.003) Batch 0.119 (0.143) Remain 00:26:42 loss: -0.7842 Lr: 3.17877e-04 +[2025-02-22 14:15:23,416 INFO misc.py line 135 2775932] Train result: loss: -0.7502 seg_loss: 0.0847 bias_l1_loss: 0.1357 bias_cosine_loss: -0.9705 +[2025-02-22 14:15:23,417 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:15:30,226 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8846 +[2025-02-22 14:15:30,668 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6789 +[2025-02-22 14:15:30,747 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6772 +[2025-02-22 14:15:30,825 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6523 +[2025-02-22 14:15:30,915 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8096 +[2025-02-22 14:15:30,981 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.4967 +[2025-02-22 14:15:31,306 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5356 +[2025-02-22 14:15:31,355 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5602 +[2025-02-22 14:15:31,539 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3995 +[2025-02-22 14:15:31,624 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.2400 +[2025-02-22 14:15:31,969 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2241 +[2025-02-22 14:15:32,116 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0418 +[2025-02-22 14:15:32,215 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.0779 +[2025-02-22 14:15:32,324 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 2.0504 +[2025-02-22 14:15:32,422 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1157 +[2025-02-22 14:15:32,507 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7161 +[2025-02-22 14:15:32,651 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6806 +[2025-02-22 14:15:32,758 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3772 +[2025-02-22 14:15:32,903 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2857 +[2025-02-22 14:15:32,975 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1576 +[2025-02-22 14:15:33,139 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7509 +[2025-02-22 14:15:33,315 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2282 +[2025-02-22 14:15:33,402 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1081 +[2025-02-22 14:15:33,462 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0415 +[2025-02-22 14:15:33,529 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6490 +[2025-02-22 14:15:33,588 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7124 +[2025-02-22 14:15:33,743 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2803 +[2025-02-22 14:15:33,857 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5618 +[2025-02-22 14:15:33,939 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7849 +[2025-02-22 14:15:34,010 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7177 +[2025-02-22 14:15:34,787 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6104 +[2025-02-22 14:15:35,011 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.5311 +[2025-02-22 14:15:35,059 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6962 +[2025-02-22 14:15:35,169 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3683 +[2025-02-22 14:15:35,203 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6275 +[2025-02-22 14:15:35,324 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.6800 +[2025-02-22 14:15:35,407 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7326 +[2025-02-22 14:15:35,562 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7515 +[2025-02-22 14:15:35,744 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6678 +[2025-02-22 14:15:35,987 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.2132 +[2025-02-22 14:15:36,191 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6006 +[2025-02-22 14:15:36,257 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4740 +[2025-02-22 14:15:36,307 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8646 +[2025-02-22 14:15:36,591 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7804 +[2025-02-22 14:15:36,642 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6345 +[2025-02-22 14:15:36,700 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.5133 +[2025-02-22 14:15:36,812 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.5471 +[2025-02-22 14:15:36,962 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.6105 +[2025-02-22 14:15:37,109 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2773 +[2025-02-22 14:15:37,214 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1978 +[2025-02-22 14:15:37,313 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.4694 +[2025-02-22 14:15:37,488 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5075 +[2025-02-22 14:15:37,535 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6095 +[2025-02-22 14:15:37,660 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0283 +[2025-02-22 14:15:37,761 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9056 +[2025-02-22 14:15:37,812 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.7172 +[2025-02-22 14:15:37,988 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2414 +[2025-02-22 14:15:38,035 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6349 +[2025-02-22 14:15:38,308 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3698 +[2025-02-22 14:15:38,425 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1774 +[2025-02-22 14:15:38,517 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.2641 +[2025-02-22 14:15:38,576 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5770 +[2025-02-22 14:15:38,749 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2295 +[2025-02-22 14:15:38,871 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1211 +[2025-02-22 14:15:38,954 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2948 +[2025-02-22 14:15:39,108 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3711 +[2025-02-22 14:15:39,287 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7325 +[2025-02-22 14:15:39,392 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1619 +[2025-02-22 14:15:39,448 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7082 +[2025-02-22 14:15:39,503 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4673 +[2025-02-22 14:15:39,697 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4057 +[2025-02-22 14:15:39,733 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4634 +[2025-02-22 14:15:39,788 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8775 +[2025-02-22 14:15:39,904 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 2.1858 +[2025-02-22 14:15:40,135 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7127 +[2025-02-22 14:15:40,225 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0125 +[2025-02-22 14:15:40,420 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7191 +[2025-02-22 14:15:40,537 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6806 +[2025-02-22 14:15:55,418 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:15:55,418 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:15:55,418 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:15:55,418 INFO evaluator.py line 547 2775932] cabinet : 0.3061 0.5319 0.7228 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] bed : 0.3450 0.7132 0.8512 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] chair : 0.7575 0.9061 0.9499 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] sofa : 0.3173 0.5329 0.7677 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] table : 0.4602 0.7020 0.8204 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] door : 0.2840 0.4951 0.6142 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] window : 0.2533 0.4382 0.6327 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] bookshelf : 0.2658 0.5654 0.6814 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] picture : 0.3682 0.5166 0.5905 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] counter : 0.0626 0.2190 0.6153 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] desk : 0.1226 0.3909 0.7997 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] curtain : 0.3287 0.5280 0.6293 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] refridgerator : 0.4275 0.5914 0.6439 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] shower curtain : 0.4497 0.6230 0.7257 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] toilet : 0.8632 0.9812 0.9979 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] sink : 0.4599 0.7552 0.8909 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] bathtub : 0.6722 0.7742 0.8710 +[2025-02-22 14:15:55,419 INFO evaluator.py line 547 2775932] otherfurniture : 0.4015 0.5793 0.6743 +[2025-02-22 14:15:55,419 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:15:55,419 INFO evaluator.py line 554 2775932] average : 0.3970 0.6024 0.7488 +[2025-02-22 14:15:55,419 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:15:55,419 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:15:55,456 INFO misc.py line 164 2775932] Currently Best AP50: 0.6091 +[2025-02-22 14:15:55,464 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:16:04,434 INFO hook.py line 109 2775932] Train: [87/100][50/800] Data 0.003 (0.003) Batch 0.125 (0.148) Remain 00:27:33 loss: -0.7410 Lr: 3.15108e-04 +[2025-02-22 14:16:11,850 INFO hook.py line 109 2775932] Train: [87/100][100/800] Data 0.003 (0.006) Batch 0.133 (0.148) Remain 00:27:26 loss: -0.8500 Lr: 3.12350e-04 +[2025-02-22 14:16:19,223 INFO hook.py line 109 2775932] Train: [87/100][150/800] Data 0.005 (0.005) Batch 0.158 (0.148) Remain 00:27:15 loss: -0.7598 Lr: 3.09604e-04 +[2025-02-22 14:16:26,334 INFO hook.py line 109 2775932] Train: [87/100][200/800] Data 0.003 (0.005) Batch 0.137 (0.147) Remain 00:26:52 loss: -0.8542 Lr: 3.06869e-04 +[2025-02-22 14:16:33,366 INFO hook.py line 109 2775932] Train: [87/100][250/800] Data 0.004 (0.004) Batch 0.138 (0.145) Remain 00:26:31 loss: -0.7838 Lr: 3.04145e-04 +[2025-02-22 14:16:40,714 INFO hook.py line 109 2775932] Train: [87/100][300/800] Data 0.004 (0.004) Batch 0.138 (0.146) Remain 00:26:27 loss: -0.7798 Lr: 3.01433e-04 +[2025-02-22 14:16:47,574 INFO hook.py line 109 2775932] Train: [87/100][350/800] Data 0.003 (0.004) Batch 0.162 (0.144) Remain 00:26:06 loss: -0.6029 Lr: 2.98733e-04 +[2025-02-22 14:16:54,712 INFO hook.py line 109 2775932] Train: [87/100][400/800] Data 0.003 (0.004) Batch 0.134 (0.144) Remain 00:25:57 loss: -0.7713 Lr: 2.96044e-04 +[2025-02-22 14:17:01,887 INFO hook.py line 109 2775932] Train: [87/100][450/800] Data 0.004 (0.004) Batch 0.125 (0.144) Remain 00:25:49 loss: -0.6893 Lr: 2.93367e-04 +[2025-02-22 14:17:08,802 INFO hook.py line 109 2775932] Train: [87/100][500/800] Data 0.003 (0.004) Batch 0.137 (0.144) Remain 00:25:35 loss: -0.6853 Lr: 2.90701e-04 +[2025-02-22 14:17:15,724 INFO hook.py line 109 2775932] Train: [87/100][550/800] Data 0.003 (0.004) Batch 0.122 (0.143) Remain 00:25:23 loss: -0.6803 Lr: 2.88047e-04 +[2025-02-22 14:17:23,097 INFO hook.py line 109 2775932] Train: [87/100][600/800] Data 0.002 (0.004) Batch 0.141 (0.143) Remain 00:25:20 loss: -0.6788 Lr: 2.85404e-04 +[2025-02-22 14:17:30,266 INFO hook.py line 109 2775932] Train: [87/100][650/800] Data 0.002 (0.004) Batch 0.134 (0.143) Remain 00:25:13 loss: -0.7999 Lr: 2.82773e-04 +[2025-02-22 14:17:37,256 INFO hook.py line 109 2775932] Train: [87/100][700/800] Data 0.003 (0.004) Batch 0.164 (0.143) Remain 00:25:03 loss: -0.4820 Lr: 2.80154e-04 +[2025-02-22 14:17:44,302 INFO hook.py line 109 2775932] Train: [87/100][750/800] Data 0.003 (0.004) Batch 0.134 (0.143) Remain 00:24:54 loss: -0.8044 Lr: 2.77546e-04 +[2025-02-22 14:17:51,179 INFO hook.py line 109 2775932] Train: [87/100][800/800] Data 0.002 (0.004) Batch 0.110 (0.143) Remain 00:24:43 loss: -0.6787 Lr: 2.74950e-04 +[2025-02-22 14:17:51,180 INFO misc.py line 135 2775932] Train result: loss: -0.7542 seg_loss: 0.0847 bias_l1_loss: 0.1325 bias_cosine_loss: -0.9715 +[2025-02-22 14:17:51,181 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:17:57,992 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8813 +[2025-02-22 14:17:58,462 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7130 +[2025-02-22 14:17:58,548 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6838 +[2025-02-22 14:17:58,634 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6268 +[2025-02-22 14:17:58,829 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7993 +[2025-02-22 14:17:58,901 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.2288 +[2025-02-22 14:17:59,224 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6513 +[2025-02-22 14:17:59,259 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.3868 +[2025-02-22 14:17:59,410 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3867 +[2025-02-22 14:17:59,470 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0159 +[2025-02-22 14:17:59,768 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.0871 +[2025-02-22 14:17:59,895 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.2519 +[2025-02-22 14:17:59,990 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1565 +[2025-02-22 14:18:00,105 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.8431 +[2025-02-22 14:18:00,213 INFO evaluator.py line 595 2775932] Test: [15/78] Loss -0.0103 +[2025-02-22 14:18:00,291 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7058 +[2025-02-22 14:18:00,463 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6528 +[2025-02-22 14:18:00,587 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2872 +[2025-02-22 14:18:00,763 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1173 +[2025-02-22 14:18:00,840 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.1646 +[2025-02-22 14:18:01,013 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7244 +[2025-02-22 14:18:01,207 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3614 +[2025-02-22 14:18:01,291 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0976 +[2025-02-22 14:18:01,366 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0530 +[2025-02-22 14:18:01,458 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.5798 +[2025-02-22 14:18:01,527 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7648 +[2025-02-22 14:18:01,710 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2265 +[2025-02-22 14:18:01,856 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4412 +[2025-02-22 14:18:01,951 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7846 +[2025-02-22 14:18:02,049 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7864 +[2025-02-22 14:18:02,954 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6423 +[2025-02-22 14:18:03,125 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1687 +[2025-02-22 14:18:03,172 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6754 +[2025-02-22 14:18:03,287 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.2976 +[2025-02-22 14:18:03,334 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.6013 +[2025-02-22 14:18:03,470 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.4758 +[2025-02-22 14:18:03,550 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7733 +[2025-02-22 14:18:03,725 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7600 +[2025-02-22 14:18:03,938 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6159 +[2025-02-22 14:18:04,167 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 0.9929 +[2025-02-22 14:18:04,368 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.7046 +[2025-02-22 14:18:04,433 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4938 +[2025-02-22 14:18:04,492 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8387 +[2025-02-22 14:18:04,791 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.6780 +[2025-02-22 14:18:04,850 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6884 +[2025-02-22 14:18:04,916 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4808 +[2025-02-22 14:18:05,027 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3150 +[2025-02-22 14:18:05,197 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4901 +[2025-02-22 14:18:05,352 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2512 +[2025-02-22 14:18:05,454 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1303 +[2025-02-22 14:18:05,559 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2494 +[2025-02-22 14:18:05,742 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4564 +[2025-02-22 14:18:05,786 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5569 +[2025-02-22 14:18:05,912 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.7995 +[2025-02-22 14:18:06,018 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9107 +[2025-02-22 14:18:06,070 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6533 +[2025-02-22 14:18:06,245 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2933 +[2025-02-22 14:18:06,295 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6298 +[2025-02-22 14:18:06,566 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4175 +[2025-02-22 14:18:06,698 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2216 +[2025-02-22 14:18:06,799 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5360 +[2025-02-22 14:18:06,875 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.7097 +[2025-02-22 14:18:07,070 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.0393 +[2025-02-22 14:18:07,197 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0370 +[2025-02-22 14:18:07,285 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2008 +[2025-02-22 14:18:07,455 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.3187 +[2025-02-22 14:18:07,652 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7963 +[2025-02-22 14:18:07,761 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.1070 +[2025-02-22 14:18:07,825 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7172 +[2025-02-22 14:18:07,895 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5142 +[2025-02-22 14:18:08,098 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.3917 +[2025-02-22 14:18:08,140 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4131 +[2025-02-22 14:18:08,197 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8588 +[2025-02-22 14:18:08,323 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6231 +[2025-02-22 14:18:08,574 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6794 +[2025-02-22 14:18:08,668 INFO evaluator.py line 595 2775932] Test: [76/78] Loss -0.1373 +[2025-02-22 14:18:08,888 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6318 +[2025-02-22 14:18:09,001 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.7065 +[2025-02-22 14:18:21,924 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:18:21,924 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:18:21,925 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] cabinet : 0.2973 0.5291 0.7251 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] bed : 0.3430 0.7403 0.8639 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] chair : 0.7559 0.9173 0.9514 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] sofa : 0.3013 0.5140 0.7715 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] table : 0.4283 0.6829 0.8127 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] door : 0.2721 0.4916 0.6175 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] window : 0.2703 0.4786 0.6681 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] bookshelf : 0.2608 0.5440 0.7592 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] picture : 0.3833 0.5331 0.6470 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] counter : 0.0468 0.1537 0.5534 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] desk : 0.1135 0.3613 0.7765 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] curtain : 0.3647 0.5558 0.6599 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] refridgerator : 0.4368 0.5924 0.6725 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] shower curtain : 0.4390 0.6400 0.7924 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] toilet : 0.8886 1.0000 1.0000 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] sink : 0.4177 0.6823 0.8655 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] bathtub : 0.6732 0.7742 0.8710 +[2025-02-22 14:18:21,925 INFO evaluator.py line 547 2775932] otherfurniture : 0.4009 0.5716 0.6684 +[2025-02-22 14:18:21,925 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:18:21,925 INFO evaluator.py line 554 2775932] average : 0.3941 0.5979 0.7598 +[2025-02-22 14:18:21,925 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:18:21,925 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:18:21,955 INFO misc.py line 164 2775932] Currently Best AP50: 0.6091 +[2025-02-22 14:18:21,963 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:18:30,731 INFO hook.py line 109 2775932] Train: [88/100][50/800] Data 0.003 (0.003) Batch 0.137 (0.142) Remain 00:24:24 loss: -0.7969 Lr: 2.72366e-04 +[2025-02-22 14:18:37,665 INFO hook.py line 109 2775932] Train: [88/100][100/800] Data 0.002 (0.003) Batch 0.128 (0.140) Remain 00:24:02 loss: -0.7343 Lr: 2.69793e-04 +[2025-02-22 14:18:44,752 INFO hook.py line 109 2775932] Train: [88/100][150/800] Data 0.003 (0.003) Batch 0.141 (0.141) Remain 00:24:01 loss: -0.7053 Lr: 2.67232e-04 +[2025-02-22 14:18:51,832 INFO hook.py line 109 2775932] Train: [88/100][200/800] Data 0.003 (0.003) Batch 0.112 (0.141) Remain 00:23:56 loss: -0.7410 Lr: 2.64682e-04 +[2025-02-22 14:18:58,868 INFO hook.py line 109 2775932] Train: [88/100][250/800] Data 0.003 (0.003) Batch 0.136 (0.141) Remain 00:23:49 loss: -0.7042 Lr: 2.62144e-04 +[2025-02-22 14:19:06,161 INFO hook.py line 109 2775932] Train: [88/100][300/800] Data 0.003 (0.004) Batch 0.130 (0.142) Remain 00:23:51 loss: -0.7472 Lr: 2.59669e-04 +[2025-02-22 14:19:13,248 INFO hook.py line 109 2775932] Train: [88/100][350/800] Data 0.004 (0.004) Batch 0.152 (0.142) Remain 00:23:44 loss: -0.8703 Lr: 2.57154e-04 +[2025-02-22 14:19:20,310 INFO hook.py line 109 2775932] Train: [88/100][400/800] Data 0.003 (0.004) Batch 0.158 (0.142) Remain 00:23:36 loss: -0.7396 Lr: 2.54651e-04 +[2025-02-22 14:19:27,517 INFO hook.py line 109 2775932] Train: [88/100][450/800] Data 0.003 (0.003) Batch 0.155 (0.142) Remain 00:23:32 loss: -0.7547 Lr: 2.52160e-04 +[2025-02-22 14:19:34,460 INFO hook.py line 109 2775932] Train: [88/100][500/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:23:21 loss: -0.8161 Lr: 2.49681e-04 +[2025-02-22 14:19:41,415 INFO hook.py line 109 2775932] Train: [88/100][550/800] Data 0.004 (0.003) Batch 0.156 (0.141) Remain 00:23:12 loss: -0.8014 Lr: 2.47213e-04 +[2025-02-22 14:19:48,686 INFO hook.py line 109 2775932] Train: [88/100][600/800] Data 0.002 (0.003) Batch 0.157 (0.142) Remain 00:23:08 loss: -0.7208 Lr: 2.44757e-04 +[2025-02-22 14:19:55,907 INFO hook.py line 109 2775932] Train: [88/100][650/800] Data 0.003 (0.003) Batch 0.240 (0.142) Remain 00:23:03 loss: -0.7444 Lr: 2.42313e-04 +[2025-02-22 14:20:03,151 INFO hook.py line 109 2775932] Train: [88/100][700/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 00:22:58 loss: -0.7373 Lr: 2.39881e-04 +[2025-02-22 14:20:10,324 INFO hook.py line 109 2775932] Train: [88/100][750/800] Data 0.003 (0.003) Batch 0.138 (0.142) Remain 00:22:52 loss: -0.8220 Lr: 2.37460e-04 +[2025-02-22 14:20:17,255 INFO hook.py line 109 2775932] Train: [88/100][800/800] Data 0.002 (0.003) Batch 0.106 (0.142) Remain 00:22:43 loss: -0.7216 Lr: 2.35051e-04 +[2025-02-22 14:20:17,255 INFO misc.py line 135 2775932] Train result: loss: -0.7625 seg_loss: 0.0814 bias_l1_loss: 0.1288 bias_cosine_loss: -0.9727 +[2025-02-22 14:20:17,256 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:20:24,403 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8818 +[2025-02-22 14:20:24,689 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7088 +[2025-02-22 14:20:24,763 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6699 +[2025-02-22 14:20:24,838 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6726 +[2025-02-22 14:20:24,904 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7946 +[2025-02-22 14:20:24,968 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.3985 +[2025-02-22 14:20:25,303 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6699 +[2025-02-22 14:20:25,338 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6393 +[2025-02-22 14:20:25,488 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.3689 +[2025-02-22 14:20:25,560 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0045 +[2025-02-22 14:20:25,846 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2107 +[2025-02-22 14:20:25,972 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0266 +[2025-02-22 14:20:26,070 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1015 +[2025-02-22 14:20:26,180 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.8768 +[2025-02-22 14:20:26,277 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1230 +[2025-02-22 14:20:26,358 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7136 +[2025-02-22 14:20:26,507 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6464 +[2025-02-22 14:20:26,618 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2500 +[2025-02-22 14:20:26,770 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.3346 +[2025-02-22 14:20:26,848 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0085 +[2025-02-22 14:20:27,010 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7534 +[2025-02-22 14:20:27,182 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4573 +[2025-02-22 14:20:27,268 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1374 +[2025-02-22 14:20:27,332 INFO evaluator.py line 595 2775932] Test: [24/78] Loss -0.0104 +[2025-02-22 14:20:27,412 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4048 +[2025-02-22 14:20:27,475 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7081 +[2025-02-22 14:20:27,637 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1694 +[2025-02-22 14:20:27,768 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4530 +[2025-02-22 14:20:27,846 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7851 +[2025-02-22 14:20:27,923 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.8009 +[2025-02-22 14:20:28,748 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6318 +[2025-02-22 14:20:28,984 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3502 +[2025-02-22 14:20:29,028 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5904 +[2025-02-22 14:20:29,156 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4100 +[2025-02-22 14:20:29,193 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5291 +[2025-02-22 14:20:29,320 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5935 +[2025-02-22 14:20:29,385 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7733 +[2025-02-22 14:20:29,512 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7674 +[2025-02-22 14:20:29,673 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7752 +[2025-02-22 14:20:29,878 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1226 +[2025-02-22 14:20:30,053 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.7444 +[2025-02-22 14:20:30,111 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.4665 +[2025-02-22 14:20:30,154 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8412 +[2025-02-22 14:20:30,402 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7208 +[2025-02-22 14:20:30,445 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6888 +[2025-02-22 14:20:30,489 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4535 +[2025-02-22 14:20:30,578 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.1695 +[2025-02-22 14:20:30,708 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4581 +[2025-02-22 14:20:30,850 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2587 +[2025-02-22 14:20:30,954 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2307 +[2025-02-22 14:20:31,050 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2101 +[2025-02-22 14:20:31,227 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.5074 +[2025-02-22 14:20:31,272 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5885 +[2025-02-22 14:20:31,399 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.8935 +[2025-02-22 14:20:31,498 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.8995 +[2025-02-22 14:20:31,560 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6312 +[2025-02-22 14:20:31,743 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1805 +[2025-02-22 14:20:31,800 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6409 +[2025-02-22 14:20:32,049 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4145 +[2025-02-22 14:20:32,168 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.1134 +[2025-02-22 14:20:32,276 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.5450 +[2025-02-22 14:20:32,342 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6865 +[2025-02-22 14:20:32,539 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.5057 +[2025-02-22 14:20:32,661 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0102 +[2025-02-22 14:20:32,742 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2157 +[2025-02-22 14:20:32,902 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2543 +[2025-02-22 14:20:33,090 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7482 +[2025-02-22 14:20:33,200 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0441 +[2025-02-22 14:20:33,257 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6969 +[2025-02-22 14:20:33,315 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5263 +[2025-02-22 14:20:33,512 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5066 +[2025-02-22 14:20:33,552 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.6353 +[2025-02-22 14:20:33,610 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8708 +[2025-02-22 14:20:33,745 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7936 +[2025-02-22 14:20:33,981 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6952 +[2025-02-22 14:20:34,077 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2397 +[2025-02-22 14:20:34,298 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7627 +[2025-02-22 14:20:34,417 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.5995 +[2025-02-22 14:20:47,591 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:20:47,591 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:20:47,591 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] cabinet : 0.2795 0.5109 0.7078 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] bed : 0.3441 0.7447 0.8869 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] chair : 0.7556 0.9146 0.9495 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] sofa : 0.3307 0.5302 0.7615 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] table : 0.4569 0.6908 0.8122 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] door : 0.2830 0.5227 0.6371 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] window : 0.2700 0.4649 0.6534 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] bookshelf : 0.2375 0.4926 0.6985 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] picture : 0.3408 0.4625 0.5608 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] counter : 0.0453 0.1520 0.6017 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] desk : 0.1396 0.4591 0.8619 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] curtain : 0.3434 0.5416 0.6786 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] refridgerator : 0.4845 0.6910 0.7438 +[2025-02-22 14:20:47,591 INFO evaluator.py line 547 2775932] shower curtain : 0.4333 0.6050 0.7841 +[2025-02-22 14:20:47,592 INFO evaluator.py line 547 2775932] toilet : 0.8929 1.0000 1.0000 +[2025-02-22 14:20:47,592 INFO evaluator.py line 547 2775932] sink : 0.4274 0.6822 0.8546 +[2025-02-22 14:20:47,592 INFO evaluator.py line 547 2775932] bathtub : 0.6739 0.7742 0.9032 +[2025-02-22 14:20:47,592 INFO evaluator.py line 547 2775932] otherfurniture : 0.3931 0.5647 0.6734 +[2025-02-22 14:20:47,592 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:20:47,592 INFO evaluator.py line 554 2775932] average : 0.3962 0.6002 0.7649 +[2025-02-22 14:20:47,592 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:20:47,592 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:20:47,618 INFO misc.py line 164 2775932] Currently Best AP50: 0.6091 +[2025-02-22 14:20:47,626 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:20:56,638 INFO hook.py line 109 2775932] Train: [89/100][50/800] Data 0.004 (0.005) Batch 0.271 (0.153) Remain 00:24:21 loss: -0.4733 Lr: 2.32654e-04 +[2025-02-22 14:21:03,769 INFO hook.py line 109 2775932] Train: [89/100][100/800] Data 0.003 (0.004) Batch 0.128 (0.148) Remain 00:23:22 loss: -0.7819 Lr: 2.30269e-04 +[2025-02-22 14:21:10,918 INFO hook.py line 109 2775932] Train: [89/100][150/800] Data 0.003 (0.005) Batch 0.126 (0.146) Remain 00:23:00 loss: -0.7463 Lr: 2.27896e-04 +[2025-02-22 14:21:17,906 INFO hook.py line 109 2775932] Train: [89/100][200/800] Data 0.003 (0.005) Batch 0.154 (0.144) Remain 00:22:38 loss: -0.8002 Lr: 2.25534e-04 +[2025-02-22 14:21:24,834 INFO hook.py line 109 2775932] Train: [89/100][250/800] Data 0.003 (0.004) Batch 0.134 (0.143) Remain 00:22:19 loss: -0.7479 Lr: 2.23185e-04 +[2025-02-22 14:21:31,736 INFO hook.py line 109 2775932] Train: [89/100][300/800] Data 0.003 (0.004) Batch 0.138 (0.142) Remain 00:22:04 loss: -0.7288 Lr: 2.20847e-04 +[2025-02-22 14:21:38,904 INFO hook.py line 109 2775932] Train: [89/100][350/800] Data 0.002 (0.004) Batch 0.125 (0.143) Remain 00:21:58 loss: -0.7797 Lr: 2.18521e-04 +[2025-02-22 14:21:45,827 INFO hook.py line 109 2775932] Train: [89/100][400/800] Data 0.003 (0.004) Batch 0.144 (0.142) Remain 00:21:46 loss: -0.7898 Lr: 2.16207e-04 +[2025-02-22 14:21:53,136 INFO hook.py line 109 2775932] Train: [89/100][450/800] Data 0.003 (0.004) Batch 0.173 (0.142) Remain 00:21:43 loss: -0.7186 Lr: 2.13905e-04 +[2025-02-22 14:22:00,053 INFO hook.py line 109 2775932] Train: [89/100][500/800] Data 0.003 (0.004) Batch 0.141 (0.142) Remain 00:21:32 loss: -0.7052 Lr: 2.11615e-04 +[2025-02-22 14:22:07,370 INFO hook.py line 109 2775932] Train: [89/100][550/800] Data 0.003 (0.004) Batch 0.159 (0.142) Remain 00:21:29 loss: -0.7717 Lr: 2.09337e-04 +[2025-02-22 14:22:14,585 INFO hook.py line 109 2775932] Train: [89/100][600/800] Data 0.003 (0.004) Batch 0.151 (0.143) Remain 00:21:23 loss: -0.8387 Lr: 2.07070e-04 +[2025-02-22 14:22:21,958 INFO hook.py line 109 2775932] Train: [89/100][650/800] Data 0.003 (0.004) Batch 0.138 (0.143) Remain 00:21:19 loss: -0.8218 Lr: 2.04816e-04 +[2025-02-22 14:22:28,860 INFO hook.py line 109 2775932] Train: [89/100][700/800] Data 0.003 (0.004) Batch 0.133 (0.143) Remain 00:21:09 loss: -0.7947 Lr: 2.02573e-04 +[2025-02-22 14:22:36,001 INFO hook.py line 109 2775932] Train: [89/100][750/800] Data 0.004 (0.004) Batch 0.127 (0.143) Remain 00:21:02 loss: -0.8509 Lr: 2.00343e-04 +[2025-02-22 14:22:42,831 INFO hook.py line 109 2775932] Train: [89/100][800/800] Data 0.002 (0.004) Batch 0.113 (0.142) Remain 00:20:51 loss: -0.7890 Lr: 1.98124e-04 +[2025-02-22 14:22:42,831 INFO misc.py line 135 2775932] Train result: loss: -0.7666 seg_loss: 0.0796 bias_l1_loss: 0.1266 bias_cosine_loss: -0.9729 +[2025-02-22 14:22:42,832 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:22:49,757 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8928 +[2025-02-22 14:22:50,247 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7147 +[2025-02-22 14:22:50,328 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6708 +[2025-02-22 14:22:50,424 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6119 +[2025-02-22 14:22:50,488 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7918 +[2025-02-22 14:22:50,555 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.4187 +[2025-02-22 14:22:50,886 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6072 +[2025-02-22 14:22:50,934 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.4927 +[2025-02-22 14:22:51,130 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.4064 +[2025-02-22 14:22:51,205 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.1259 +[2025-02-22 14:22:51,563 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1255 +[2025-02-22 14:22:51,715 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0086 +[2025-02-22 14:22:51,828 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.1737 +[2025-02-22 14:22:51,954 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6360 +[2025-02-22 14:22:52,049 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0285 +[2025-02-22 14:22:52,134 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7242 +[2025-02-22 14:22:52,292 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6351 +[2025-02-22 14:22:52,416 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3196 +[2025-02-22 14:22:52,609 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.3496 +[2025-02-22 14:22:52,688 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0515 +[2025-02-22 14:22:52,889 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7455 +[2025-02-22 14:22:53,112 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2173 +[2025-02-22 14:22:53,227 INFO evaluator.py line 595 2775932] Test: [23/78] Loss -0.0038 +[2025-02-22 14:22:53,310 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0691 +[2025-02-22 14:22:53,428 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.2918 +[2025-02-22 14:22:53,516 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7531 +[2025-02-22 14:22:53,697 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0075 +[2025-02-22 14:22:53,848 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.4577 +[2025-02-22 14:22:53,940 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7755 +[2025-02-22 14:22:54,037 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7938 +[2025-02-22 14:22:55,098 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6172 +[2025-02-22 14:22:55,383 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1354 +[2025-02-22 14:22:55,433 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5465 +[2025-02-22 14:22:55,554 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4398 +[2025-02-22 14:22:55,600 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5533 +[2025-02-22 14:22:55,733 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5356 +[2025-02-22 14:22:55,812 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7765 +[2025-02-22 14:22:55,978 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7636 +[2025-02-22 14:22:56,178 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7390 +[2025-02-22 14:22:56,420 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0189 +[2025-02-22 14:22:56,634 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6029 +[2025-02-22 14:22:56,699 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5100 +[2025-02-22 14:22:56,752 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8383 +[2025-02-22 14:22:57,036 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.7493 +[2025-02-22 14:22:57,088 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6706 +[2025-02-22 14:22:57,141 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4460 +[2025-02-22 14:22:57,253 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 1.0897 +[2025-02-22 14:22:57,417 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4921 +[2025-02-22 14:22:57,563 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.1269 +[2025-02-22 14:22:57,671 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1671 +[2025-02-22 14:22:57,779 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3019 +[2025-02-22 14:22:57,951 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4038 +[2025-02-22 14:22:57,995 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6251 +[2025-02-22 14:22:58,119 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9957 +[2025-02-22 14:22:58,224 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9006 +[2025-02-22 14:22:58,278 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6447 +[2025-02-22 14:22:58,446 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2253 +[2025-02-22 14:22:58,497 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6339 +[2025-02-22 14:22:58,770 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4669 +[2025-02-22 14:22:58,890 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.2959 +[2025-02-22 14:22:58,995 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4383 +[2025-02-22 14:22:59,062 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6682 +[2025-02-22 14:22:59,268 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3300 +[2025-02-22 14:22:59,396 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0193 +[2025-02-22 14:22:59,484 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2270 +[2025-02-22 14:22:59,650 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2163 +[2025-02-22 14:22:59,838 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7670 +[2025-02-22 14:22:59,966 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0863 +[2025-02-22 14:23:00,024 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7529 +[2025-02-22 14:23:00,085 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5494 +[2025-02-22 14:23:00,294 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4516 +[2025-02-22 14:23:00,331 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4874 +[2025-02-22 14:23:00,388 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8527 +[2025-02-22 14:23:00,513 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7638 +[2025-02-22 14:23:00,752 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7179 +[2025-02-22 14:23:00,843 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.0925 +[2025-02-22 14:23:01,036 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.6632 +[2025-02-22 14:23:01,152 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6399 +[2025-02-22 14:23:12,817 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:23:12,817 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:23:12,817 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] cabinet : 0.3054 0.5480 0.7229 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] bed : 0.3392 0.7751 0.8758 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] chair : 0.7579 0.9103 0.9447 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] sofa : 0.3304 0.5472 0.7736 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] table : 0.4565 0.7077 0.8231 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] door : 0.2851 0.5082 0.6366 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] window : 0.2706 0.4630 0.6592 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] bookshelf : 0.2583 0.5709 0.7415 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] picture : 0.3496 0.4695 0.5446 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] counter : 0.0486 0.2065 0.6205 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] desk : 0.1164 0.4020 0.7697 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] curtain : 0.3294 0.5600 0.6392 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] refridgerator : 0.4787 0.6919 0.7419 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] shower curtain : 0.4575 0.6247 0.7323 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] toilet : 0.8894 1.0000 1.0000 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] sink : 0.4367 0.7306 0.8554 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] bathtub : 0.6763 0.7742 0.8710 +[2025-02-22 14:23:12,817 INFO evaluator.py line 547 2775932] otherfurniture : 0.4139 0.5877 0.6868 +[2025-02-22 14:23:12,817 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:23:12,817 INFO evaluator.py line 554 2775932] average : 0.4000 0.6154 0.7577 +[2025-02-22 14:23:12,817 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:23:12,818 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:23:12,851 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.6154 +[2025-02-22 14:23:12,859 INFO misc.py line 164 2775932] Currently Best AP50: 0.6154 +[2025-02-22 14:23:12,859 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:23:22,302 INFO hook.py line 109 2775932] Train: [90/100][50/800] Data 0.003 (0.004) Batch 0.142 (0.152) Remain 00:22:07 loss: -0.8001 Lr: 1.95918e-04 +[2025-02-22 14:23:29,177 INFO hook.py line 109 2775932] Train: [90/100][100/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 00:20:56 loss: -0.8341 Lr: 1.93723e-04 +[2025-02-22 14:23:36,245 INFO hook.py line 109 2775932] Train: [90/100][150/800] Data 0.002 (0.003) Batch 0.145 (0.143) Remain 00:20:40 loss: -0.7923 Lr: 1.91540e-04 +[2025-02-22 14:23:43,118 INFO hook.py line 109 2775932] Train: [90/100][200/800] Data 0.003 (0.003) Batch 0.131 (0.142) Remain 00:20:19 loss: -0.7785 Lr: 1.89370e-04 +[2025-02-22 14:23:50,294 INFO hook.py line 109 2775932] Train: [90/100][250/800] Data 0.003 (0.003) Batch 0.151 (0.142) Remain 00:20:15 loss: -0.7697 Lr: 1.87211e-04 +[2025-02-22 14:23:57,271 INFO hook.py line 109 2775932] Train: [90/100][300/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 00:20:04 loss: -0.7818 Lr: 1.85064e-04 +[2025-02-22 14:24:04,449 INFO hook.py line 109 2775932] Train: [90/100][350/800] Data 0.002 (0.004) Batch 0.138 (0.142) Remain 00:19:59 loss: -0.7616 Lr: 1.82930e-04 +[2025-02-22 14:24:11,496 INFO hook.py line 109 2775932] Train: [90/100][400/800] Data 0.004 (0.004) Batch 0.142 (0.142) Remain 00:19:51 loss: -0.7884 Lr: 1.80807e-04 +[2025-02-22 14:24:18,415 INFO hook.py line 109 2775932] Train: [90/100][450/800] Data 0.003 (0.004) Batch 0.138 (0.141) Remain 00:19:41 loss: -0.7989 Lr: 1.78697e-04 +[2025-02-22 14:24:25,441 INFO hook.py line 109 2775932] Train: [90/100][500/800] Data 0.003 (0.004) Batch 0.132 (0.141) Remain 00:19:33 loss: -0.7900 Lr: 1.76598e-04 +[2025-02-22 14:24:32,689 INFO hook.py line 109 2775932] Train: [90/100][550/800] Data 0.004 (0.004) Batch 0.136 (0.142) Remain 00:19:29 loss: -0.8436 Lr: 1.74512e-04 +[2025-02-22 14:24:39,896 INFO hook.py line 109 2775932] Train: [90/100][600/800] Data 0.003 (0.004) Batch 0.128 (0.142) Remain 00:19:23 loss: -0.7649 Lr: 1.72438e-04 +[2025-02-22 14:24:47,026 INFO hook.py line 109 2775932] Train: [90/100][650/800] Data 0.003 (0.004) Batch 0.171 (0.142) Remain 00:19:17 loss: -0.7200 Lr: 1.70375e-04 +[2025-02-22 14:24:54,219 INFO hook.py line 109 2775932] Train: [90/100][700/800] Data 0.003 (0.004) Batch 0.144 (0.142) Remain 00:19:11 loss: -0.7307 Lr: 1.68366e-04 +[2025-02-22 14:25:01,160 INFO hook.py line 109 2775932] Train: [90/100][750/800] Data 0.003 (0.004) Batch 0.146 (0.142) Remain 00:19:02 loss: -0.7235 Lr: 1.66328e-04 +[2025-02-22 14:25:07,956 INFO hook.py line 109 2775932] Train: [90/100][800/800] Data 0.002 (0.004) Batch 0.118 (0.142) Remain 00:18:52 loss: -0.7340 Lr: 1.64302e-04 +[2025-02-22 14:25:07,957 INFO misc.py line 135 2775932] Train result: loss: -0.7705 seg_loss: 0.0783 bias_l1_loss: 0.1244 bias_cosine_loss: -0.9732 +[2025-02-22 14:25:07,957 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:25:14,812 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8874 +[2025-02-22 14:25:15,459 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7186 +[2025-02-22 14:25:15,539 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6791 +[2025-02-22 14:25:15,616 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6507 +[2025-02-22 14:25:15,687 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8087 +[2025-02-22 14:25:15,755 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5920 +[2025-02-22 14:25:16,061 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6786 +[2025-02-22 14:25:16,097 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5165 +[2025-02-22 14:25:16,247 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5539 +[2025-02-22 14:25:16,311 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0515 +[2025-02-22 14:25:16,597 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.1443 +[2025-02-22 14:25:16,727 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0250 +[2025-02-22 14:25:16,822 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4721 +[2025-02-22 14:25:16,936 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.8074 +[2025-02-22 14:25:17,032 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.2173 +[2025-02-22 14:25:17,117 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7178 +[2025-02-22 14:25:17,266 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6638 +[2025-02-22 14:25:17,381 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2964 +[2025-02-22 14:25:17,537 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2398 +[2025-02-22 14:25:17,606 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0647 +[2025-02-22 14:25:17,808 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7458 +[2025-02-22 14:25:18,000 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4059 +[2025-02-22 14:25:18,104 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0617 +[2025-02-22 14:25:18,209 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0854 +[2025-02-22 14:25:18,306 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6137 +[2025-02-22 14:25:18,376 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6615 +[2025-02-22 14:25:18,548 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1164 +[2025-02-22 14:25:18,719 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5065 +[2025-02-22 14:25:18,821 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7805 +[2025-02-22 14:25:18,914 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.8015 +[2025-02-22 14:25:20,003 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6525 +[2025-02-22 14:25:20,197 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2239 +[2025-02-22 14:25:20,249 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5651 +[2025-02-22 14:25:20,384 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4281 +[2025-02-22 14:25:20,440 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5363 +[2025-02-22 14:25:20,572 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5569 +[2025-02-22 14:25:20,651 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7443 +[2025-02-22 14:25:20,813 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7978 +[2025-02-22 14:25:21,007 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.8053 +[2025-02-22 14:25:21,253 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1209 +[2025-02-22 14:25:21,467 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.7478 +[2025-02-22 14:25:21,532 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5440 +[2025-02-22 14:25:21,582 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8453 +[2025-02-22 14:25:21,869 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8169 +[2025-02-22 14:25:21,921 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7239 +[2025-02-22 14:25:21,974 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4553 +[2025-02-22 14:25:22,081 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3436 +[2025-02-22 14:25:22,245 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.3625 +[2025-02-22 14:25:22,385 INFO evaluator.py line 595 2775932] Test: [49/78] Loss 0.0006 +[2025-02-22 14:25:22,491 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1048 +[2025-02-22 14:25:22,599 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2573 +[2025-02-22 14:25:22,781 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4820 +[2025-02-22 14:25:22,825 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.6064 +[2025-02-22 14:25:22,961 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9741 +[2025-02-22 14:25:23,071 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9145 +[2025-02-22 14:25:23,126 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6052 +[2025-02-22 14:25:23,300 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1829 +[2025-02-22 14:25:23,355 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6400 +[2025-02-22 14:25:23,634 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4223 +[2025-02-22 14:25:23,769 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3835 +[2025-02-22 14:25:23,874 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4384 +[2025-02-22 14:25:23,954 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.5443 +[2025-02-22 14:25:24,157 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.4276 +[2025-02-22 14:25:24,294 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0188 +[2025-02-22 14:25:24,392 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1094 +[2025-02-22 14:25:24,562 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2583 +[2025-02-22 14:25:24,771 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7814 +[2025-02-22 14:25:24,891 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0299 +[2025-02-22 14:25:24,950 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7086 +[2025-02-22 14:25:25,010 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5995 +[2025-02-22 14:25:25,273 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4633 +[2025-02-22 14:25:25,312 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4284 +[2025-02-22 14:25:25,371 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8880 +[2025-02-22 14:25:25,496 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6948 +[2025-02-22 14:25:25,736 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6708 +[2025-02-22 14:25:25,831 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2836 +[2025-02-22 14:25:26,032 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7072 +[2025-02-22 14:25:26,161 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6802 +[2025-02-22 14:25:39,095 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:25:39,095 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:25:39,095 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] cabinet : 0.2972 0.5185 0.7149 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] bed : 0.3234 0.7614 0.8879 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] chair : 0.7588 0.9116 0.9468 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] sofa : 0.3412 0.5507 0.8100 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] table : 0.4527 0.7161 0.8159 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] door : 0.2849 0.5050 0.6100 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] window : 0.2670 0.4564 0.6567 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] bookshelf : 0.2660 0.5565 0.7328 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] picture : 0.3616 0.4980 0.5713 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] counter : 0.0657 0.2632 0.6548 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] desk : 0.1274 0.4082 0.7901 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] curtain : 0.3554 0.5458 0.6204 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] refridgerator : 0.4189 0.5382 0.5896 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] shower curtain : 0.4323 0.6151 0.7156 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] toilet : 0.9006 1.0000 1.0000 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] sink : 0.4267 0.7149 0.8508 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] bathtub : 0.6801 0.7742 0.8710 +[2025-02-22 14:25:39,095 INFO evaluator.py line 547 2775932] otherfurniture : 0.4103 0.5833 0.6668 +[2025-02-22 14:25:39,095 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:25:39,095 INFO evaluator.py line 554 2775932] average : 0.3983 0.6065 0.7503 +[2025-02-22 14:25:39,096 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:25:39,096 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:25:39,124 INFO misc.py line 164 2775932] Currently Best AP50: 0.6154 +[2025-02-22 14:25:39,132 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:25:47,692 INFO hook.py line 109 2775932] Train: [91/100][50/800] Data 0.003 (0.003) Batch 0.149 (0.146) Remain 00:19:19 loss: -0.7429 Lr: 1.62288e-04 +[2025-02-22 14:25:54,703 INFO hook.py line 109 2775932] Train: [91/100][100/800] Data 0.003 (0.003) Batch 0.130 (0.143) Remain 00:18:49 loss: -0.7933 Lr: 1.60286e-04 +[2025-02-22 14:26:01,557 INFO hook.py line 109 2775932] Train: [91/100][150/800] Data 0.003 (0.003) Batch 0.132 (0.141) Remain 00:18:26 loss: -0.8315 Lr: 1.58296e-04 +[2025-02-22 14:26:08,864 INFO hook.py line 109 2775932] Train: [91/100][200/800] Data 0.003 (0.004) Batch 0.179 (0.142) Remain 00:18:29 loss: -0.7744 Lr: 1.56318e-04 +[2025-02-22 14:26:15,979 INFO hook.py line 109 2775932] Train: [91/100][250/800] Data 0.003 (0.004) Batch 0.146 (0.142) Remain 00:18:22 loss: -0.7989 Lr: 1.54353e-04 +[2025-02-22 14:26:22,951 INFO hook.py line 109 2775932] Train: [91/100][300/800] Data 0.002 (0.004) Batch 0.139 (0.142) Remain 00:18:11 loss: -0.7899 Lr: 1.52399e-04 +[2025-02-22 14:26:29,750 INFO hook.py line 109 2775932] Train: [91/100][350/800] Data 0.003 (0.004) Batch 0.133 (0.141) Remain 00:17:58 loss: -0.7665 Lr: 1.50458e-04 +[2025-02-22 14:26:36,816 INFO hook.py line 109 2775932] Train: [91/100][400/800] Data 0.003 (0.003) Batch 0.134 (0.141) Remain 00:17:51 loss: -0.7243 Lr: 1.48529e-04 +[2025-02-22 14:26:43,999 INFO hook.py line 109 2775932] Train: [91/100][450/800] Data 0.003 (0.003) Batch 0.136 (0.141) Remain 00:17:46 loss: -0.8289 Lr: 1.46612e-04 +[2025-02-22 14:26:50,828 INFO hook.py line 109 2775932] Train: [91/100][500/800] Data 0.002 (0.003) Batch 0.118 (0.141) Remain 00:17:36 loss: -0.7357 Lr: 1.44708e-04 +[2025-02-22 14:26:57,783 INFO hook.py line 109 2775932] Train: [91/100][550/800] Data 0.003 (0.003) Batch 0.178 (0.141) Remain 00:17:27 loss: -0.7427 Lr: 1.42815e-04 +[2025-02-22 14:27:04,972 INFO hook.py line 109 2775932] Train: [91/100][600/800] Data 0.002 (0.003) Batch 0.159 (0.141) Remain 00:17:22 loss: -0.8547 Lr: 1.40935e-04 +[2025-02-22 14:27:11,975 INFO hook.py line 109 2775932] Train: [91/100][650/800] Data 0.003 (0.003) Batch 0.136 (0.141) Remain 00:17:15 loss: -0.6931 Lr: 1.39067e-04 +[2025-02-22 14:27:19,162 INFO hook.py line 109 2775932] Train: [91/100][700/800] Data 0.003 (0.003) Batch 0.138 (0.141) Remain 00:17:09 loss: -0.6174 Lr: 1.37211e-04 +[2025-02-22 14:27:26,446 INFO hook.py line 109 2775932] Train: [91/100][750/800] Data 0.003 (0.003) Batch 0.176 (0.141) Remain 00:17:04 loss: -0.7789 Lr: 1.35367e-04 +[2025-02-22 14:27:33,153 INFO hook.py line 109 2775932] Train: [91/100][800/800] Data 0.002 (0.003) Batch 0.119 (0.141) Remain 00:16:54 loss: -0.7603 Lr: 1.33536e-04 +[2025-02-22 14:27:33,153 INFO misc.py line 135 2775932] Train result: loss: -0.7715 seg_loss: 0.0769 bias_l1_loss: 0.1248 bias_cosine_loss: -0.9732 +[2025-02-22 14:27:33,154 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:27:40,065 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9036 +[2025-02-22 14:27:40,871 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7239 +[2025-02-22 14:27:40,947 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6642 +[2025-02-22 14:27:41,028 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6439 +[2025-02-22 14:27:41,103 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8016 +[2025-02-22 14:27:41,190 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.6014 +[2025-02-22 14:27:41,488 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6185 +[2025-02-22 14:27:41,524 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5170 +[2025-02-22 14:27:41,687 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5231 +[2025-02-22 14:27:41,754 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0751 +[2025-02-22 14:27:42,049 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2007 +[2025-02-22 14:27:42,185 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.0917 +[2025-02-22 14:27:42,283 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.3954 +[2025-02-22 14:27:42,394 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.7811 +[2025-02-22 14:27:42,492 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1376 +[2025-02-22 14:27:42,590 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.6962 +[2025-02-22 14:27:42,744 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6337 +[2025-02-22 14:27:42,856 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2801 +[2025-02-22 14:27:43,006 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.3178 +[2025-02-22 14:27:43,078 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0211 +[2025-02-22 14:27:43,251 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7535 +[2025-02-22 14:27:43,432 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.4200 +[2025-02-22 14:27:43,520 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1308 +[2025-02-22 14:27:43,586 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0313 +[2025-02-22 14:27:43,661 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6717 +[2025-02-22 14:27:43,725 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7257 +[2025-02-22 14:27:43,876 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1661 +[2025-02-22 14:27:44,004 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5572 +[2025-02-22 14:27:44,086 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.7986 +[2025-02-22 14:27:44,163 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.8060 +[2025-02-22 14:27:45,016 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6335 +[2025-02-22 14:27:45,275 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2191 +[2025-02-22 14:27:45,321 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.5994 +[2025-02-22 14:27:45,451 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3764 +[2025-02-22 14:27:45,498 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5446 +[2025-02-22 14:27:45,633 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.4998 +[2025-02-22 14:27:45,733 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.8040 +[2025-02-22 14:27:45,922 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7859 +[2025-02-22 14:27:46,136 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6101 +[2025-02-22 14:27:46,389 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0771 +[2025-02-22 14:27:46,653 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6707 +[2025-02-22 14:27:46,718 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5203 +[2025-02-22 14:27:46,778 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8615 +[2025-02-22 14:27:47,101 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8110 +[2025-02-22 14:27:47,159 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6847 +[2025-02-22 14:27:47,215 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4707 +[2025-02-22 14:27:47,316 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.7412 +[2025-02-22 14:27:47,492 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4512 +[2025-02-22 14:27:47,651 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2821 +[2025-02-22 14:27:47,774 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0605 +[2025-02-22 14:27:47,887 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.3238 +[2025-02-22 14:27:48,073 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4478 +[2025-02-22 14:27:48,129 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5021 +[2025-02-22 14:27:48,266 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9323 +[2025-02-22 14:27:48,375 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9121 +[2025-02-22 14:27:48,447 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6596 +[2025-02-22 14:27:48,617 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1892 +[2025-02-22 14:27:48,667 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6377 +[2025-02-22 14:27:48,944 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3964 +[2025-02-22 14:27:49,063 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3677 +[2025-02-22 14:27:49,169 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4054 +[2025-02-22 14:27:49,260 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6650 +[2025-02-22 14:27:49,447 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.4536 +[2025-02-22 14:27:49,576 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0921 +[2025-02-22 14:27:49,665 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1489 +[2025-02-22 14:27:49,835 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2075 +[2025-02-22 14:27:50,027 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7618 +[2025-02-22 14:27:50,141 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.2028 +[2025-02-22 14:27:50,197 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7030 +[2025-02-22 14:27:50,260 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.4633 +[2025-02-22 14:27:50,467 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4857 +[2025-02-22 14:27:50,512 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4388 +[2025-02-22 14:27:50,571 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8688 +[2025-02-22 14:27:50,693 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.6878 +[2025-02-22 14:27:50,924 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7136 +[2025-02-22 14:27:51,018 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1916 +[2025-02-22 14:27:51,219 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7104 +[2025-02-22 14:27:51,330 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6556 +[2025-02-22 14:28:03,760 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:28:03,760 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:28:03,760 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] cabinet : 0.3022 0.5355 0.7296 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] bed : 0.3408 0.7864 0.8851 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] chair : 0.7506 0.9056 0.9436 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] sofa : 0.3600 0.5800 0.7971 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] table : 0.4545 0.7121 0.8112 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] door : 0.2757 0.5103 0.6340 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] window : 0.2882 0.4893 0.6826 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] bookshelf : 0.2502 0.5103 0.7166 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] picture : 0.3759 0.5174 0.5969 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] counter : 0.0794 0.2955 0.7025 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] desk : 0.1349 0.4515 0.8532 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] curtain : 0.3510 0.5473 0.6427 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] refridgerator : 0.4498 0.6420 0.6724 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] shower curtain : 0.4247 0.6233 0.7899 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] toilet : 0.8861 1.0000 1.0000 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] sink : 0.4222 0.7016 0.8794 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] bathtub : 0.6785 0.7742 0.8710 +[2025-02-22 14:28:03,760 INFO evaluator.py line 547 2775932] otherfurniture : 0.3962 0.5714 0.6716 +[2025-02-22 14:28:03,760 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:28:03,760 INFO evaluator.py line 554 2775932] average : 0.4012 0.6197 0.7711 +[2025-02-22 14:28:03,760 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:28:03,760 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:28:03,791 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.6197 +[2025-02-22 14:28:03,799 INFO misc.py line 164 2775932] Currently Best AP50: 0.6197 +[2025-02-22 14:28:03,799 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:28:12,913 INFO hook.py line 109 2775932] Train: [92/100][50/800] Data 0.003 (0.003) Batch 0.168 (0.146) Remain 00:17:23 loss: -0.7433 Lr: 1.31717e-04 +[2025-02-22 14:28:20,533 INFO hook.py line 109 2775932] Train: [92/100][100/800] Data 0.003 (0.005) Batch 0.162 (0.149) Remain 00:17:39 loss: -0.7875 Lr: 1.29910e-04 +[2025-02-22 14:28:27,638 INFO hook.py line 109 2775932] Train: [92/100][150/800] Data 0.003 (0.005) Batch 0.143 (0.147) Remain 00:17:15 loss: -0.7833 Lr: 1.28116e-04 +[2025-02-22 14:28:34,806 INFO hook.py line 109 2775932] Train: [92/100][200/800] Data 0.005 (0.004) Batch 0.130 (0.146) Remain 00:17:01 loss: -0.8137 Lr: 1.26333e-04 +[2025-02-22 14:28:41,713 INFO hook.py line 109 2775932] Train: [92/100][250/800] Data 0.002 (0.004) Batch 0.121 (0.144) Remain 00:16:43 loss: -0.7649 Lr: 1.24563e-04 +[2025-02-22 14:28:48,600 INFO hook.py line 109 2775932] Train: [92/100][300/800] Data 0.004 (0.004) Batch 0.137 (0.143) Remain 00:16:28 loss: -0.8494 Lr: 1.22805e-04 +[2025-02-22 14:28:55,707 INFO hook.py line 109 2775932] Train: [92/100][350/800] Data 0.003 (0.004) Batch 0.132 (0.143) Remain 00:16:20 loss: -0.8218 Lr: 1.21060e-04 +[2025-02-22 14:29:02,731 INFO hook.py line 109 2775932] Train: [92/100][400/800] Data 0.002 (0.004) Batch 0.140 (0.143) Remain 00:16:10 loss: -0.7634 Lr: 1.19327e-04 +[2025-02-22 14:29:09,836 INFO hook.py line 109 2775932] Train: [92/100][450/800] Data 0.004 (0.004) Batch 0.142 (0.143) Remain 00:16:03 loss: -0.7891 Lr: 1.17606e-04 +[2025-02-22 14:29:16,882 INFO hook.py line 109 2775932] Train: [92/100][500/800] Data 0.002 (0.004) Batch 0.126 (0.143) Remain 00:15:54 loss: -0.7389 Lr: 1.15897e-04 +[2025-02-22 14:29:23,887 INFO hook.py line 109 2775932] Train: [92/100][550/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 00:15:46 loss: -0.7333 Lr: 1.14201e-04 +[2025-02-22 14:29:31,109 INFO hook.py line 109 2775932] Train: [92/100][600/800] Data 0.002 (0.003) Batch 0.140 (0.142) Remain 00:15:40 loss: -0.7742 Lr: 1.12517e-04 +[2025-02-22 14:29:38,376 INFO hook.py line 109 2775932] Train: [92/100][650/800] Data 0.005 (0.003) Batch 0.167 (0.143) Remain 00:15:34 loss: -0.7641 Lr: 1.10846e-04 +[2025-02-22 14:29:45,209 INFO hook.py line 109 2775932] Train: [92/100][700/800] Data 0.003 (0.003) Batch 0.160 (0.142) Remain 00:15:24 loss: -0.6235 Lr: 1.09187e-04 +[2025-02-22 14:29:52,156 INFO hook.py line 109 2775932] Train: [92/100][750/800] Data 0.004 (0.003) Batch 0.141 (0.142) Remain 00:15:16 loss: -0.7279 Lr: 1.07540e-04 +[2025-02-22 14:29:59,109 INFO hook.py line 109 2775932] Train: [92/100][800/800] Data 0.002 (0.003) Batch 0.111 (0.142) Remain 00:15:07 loss: -0.7861 Lr: 1.05905e-04 +[2025-02-22 14:29:59,110 INFO misc.py line 135 2775932] Train result: loss: -0.7753 seg_loss: 0.0764 bias_l1_loss: 0.1223 bias_cosine_loss: -0.9740 +[2025-02-22 14:29:59,110 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:30:05,955 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9001 +[2025-02-22 14:30:06,520 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7141 +[2025-02-22 14:30:06,599 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6805 +[2025-02-22 14:30:06,678 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6442 +[2025-02-22 14:30:06,746 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7886 +[2025-02-22 14:30:06,814 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5857 +[2025-02-22 14:30:07,119 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6079 +[2025-02-22 14:30:07,155 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.5248 +[2025-02-22 14:30:07,314 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5493 +[2025-02-22 14:30:07,383 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0385 +[2025-02-22 14:30:07,682 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2150 +[2025-02-22 14:30:07,810 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1948 +[2025-02-22 14:30:07,904 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4516 +[2025-02-22 14:30:08,019 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6406 +[2025-02-22 14:30:08,113 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1444 +[2025-02-22 14:30:08,199 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7150 +[2025-02-22 14:30:08,350 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6654 +[2025-02-22 14:30:08,467 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3266 +[2025-02-22 14:30:08,629 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2829 +[2025-02-22 14:30:08,703 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.1525 +[2025-02-22 14:30:08,867 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7484 +[2025-02-22 14:30:09,055 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2496 +[2025-02-22 14:30:09,142 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0914 +[2025-02-22 14:30:09,212 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1186 +[2025-02-22 14:30:09,290 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6193 +[2025-02-22 14:30:09,353 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7348 +[2025-02-22 14:30:09,506 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.2672 +[2025-02-22 14:30:09,631 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5143 +[2025-02-22 14:30:09,711 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8089 +[2025-02-22 14:30:09,784 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7764 +[2025-02-22 14:30:10,616 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6298 +[2025-02-22 14:30:10,865 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.3688 +[2025-02-22 14:30:10,908 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7099 +[2025-02-22 14:30:11,013 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4155 +[2025-02-22 14:30:11,051 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5197 +[2025-02-22 14:30:11,167 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5654 +[2025-02-22 14:30:11,233 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7699 +[2025-02-22 14:30:11,366 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7702 +[2025-02-22 14:30:11,531 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7513 +[2025-02-22 14:30:11,763 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1114 +[2025-02-22 14:30:11,958 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6918 +[2025-02-22 14:30:12,016 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5077 +[2025-02-22 14:30:12,061 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8588 +[2025-02-22 14:30:12,347 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8087 +[2025-02-22 14:30:12,400 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6960 +[2025-02-22 14:30:12,461 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4418 +[2025-02-22 14:30:12,566 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.6101 +[2025-02-22 14:30:12,735 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.4951 +[2025-02-22 14:30:12,903 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3449 +[2025-02-22 14:30:13,004 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.0890 +[2025-02-22 14:30:13,113 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2875 +[2025-02-22 14:30:13,303 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4394 +[2025-02-22 14:30:13,349 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5169 +[2025-02-22 14:30:13,477 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9240 +[2025-02-22 14:30:13,591 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9138 +[2025-02-22 14:30:13,643 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6607 +[2025-02-22 14:30:13,815 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2060 +[2025-02-22 14:30:13,862 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6465 +[2025-02-22 14:30:14,120 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4325 +[2025-02-22 14:30:14,242 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3848 +[2025-02-22 14:30:14,352 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4395 +[2025-02-22 14:30:14,419 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6285 +[2025-02-22 14:30:14,611 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2340 +[2025-02-22 14:30:14,740 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.2183 +[2025-02-22 14:30:14,830 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.2224 +[2025-02-22 14:30:14,996 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2494 +[2025-02-22 14:30:15,199 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7839 +[2025-02-22 14:30:15,312 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.1454 +[2025-02-22 14:30:15,370 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.6831 +[2025-02-22 14:30:15,431 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.6193 +[2025-02-22 14:30:15,640 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5451 +[2025-02-22 14:30:15,678 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4441 +[2025-02-22 14:30:15,741 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8744 +[2025-02-22 14:30:15,865 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7443 +[2025-02-22 14:30:16,092 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7293 +[2025-02-22 14:30:16,180 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2511 +[2025-02-22 14:30:16,367 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7460 +[2025-02-22 14:30:16,474 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6500 +[2025-02-22 14:30:29,694 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:30:29,694 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:30:29,694 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] cabinet : 0.2971 0.5438 0.7282 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] bed : 0.3283 0.7649 0.8759 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] chair : 0.7557 0.9103 0.9499 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] sofa : 0.3473 0.5668 0.7920 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] table : 0.4572 0.7132 0.8248 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] door : 0.2802 0.5048 0.6206 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] window : 0.2800 0.4870 0.6859 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] bookshelf : 0.2655 0.5618 0.7526 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] picture : 0.3725 0.5171 0.5954 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] counter : 0.0644 0.2406 0.6655 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] desk : 0.1064 0.3661 0.8386 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] curtain : 0.3483 0.5386 0.6308 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] refridgerator : 0.4518 0.5934 0.6401 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] shower curtain : 0.4486 0.6144 0.7554 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] toilet : 0.8886 1.0000 1.0000 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] sink : 0.4399 0.7248 0.8753 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] bathtub : 0.6762 0.7742 0.8710 +[2025-02-22 14:30:29,694 INFO evaluator.py line 547 2775932] otherfurniture : 0.3966 0.5590 0.6540 +[2025-02-22 14:30:29,694 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:30:29,694 INFO evaluator.py line 554 2775932] average : 0.4003 0.6100 0.7642 +[2025-02-22 14:30:29,694 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:30:29,695 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:30:29,723 INFO misc.py line 164 2775932] Currently Best AP50: 0.6197 +[2025-02-22 14:30:29,730 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:30:38,147 INFO hook.py line 109 2775932] Train: [93/100][50/800] Data 0.004 (0.003) Batch 0.140 (0.147) Remain 00:15:35 loss: -0.8126 Lr: 1.04283e-04 +[2025-02-22 14:30:45,166 INFO hook.py line 109 2775932] Train: [93/100][100/800] Data 0.003 (0.003) Batch 0.148 (0.144) Remain 00:15:05 loss: -0.8327 Lr: 1.02673e-04 +[2025-02-22 14:30:52,316 INFO hook.py line 109 2775932] Train: [93/100][150/800] Data 0.013 (0.003) Batch 0.196 (0.144) Remain 00:14:56 loss: -0.7512 Lr: 1.01076e-04 +[2025-02-22 14:30:59,240 INFO hook.py line 109 2775932] Train: [93/100][200/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 00:14:41 loss: -0.7646 Lr: 9.94909e-05 +[2025-02-22 14:31:06,339 INFO hook.py line 109 2775932] Train: [93/100][250/800] Data 0.003 (0.003) Batch 0.132 (0.142) Remain 00:14:34 loss: -0.7688 Lr: 9.79183e-05 +[2025-02-22 14:31:13,536 INFO hook.py line 109 2775932] Train: [93/100][300/800] Data 0.003 (0.004) Batch 0.136 (0.142) Remain 00:14:29 loss: -0.8197 Lr: 9.63891e-05 +[2025-02-22 14:31:20,659 INFO hook.py line 109 2775932] Train: [93/100][350/800] Data 0.002 (0.003) Batch 0.150 (0.142) Remain 00:14:21 loss: -0.8018 Lr: 9.48411e-05 +[2025-02-22 14:31:27,767 INFO hook.py line 109 2775932] Train: [93/100][400/800] Data 0.002 (0.003) Batch 0.142 (0.142) Remain 00:14:14 loss: -0.7376 Lr: 9.33054e-05 +[2025-02-22 14:31:34,738 INFO hook.py line 109 2775932] Train: [93/100][450/800] Data 0.003 (0.003) Batch 0.123 (0.142) Remain 00:14:05 loss: -0.7917 Lr: 9.17822e-05 +[2025-02-22 14:31:41,649 INFO hook.py line 109 2775932] Train: [93/100][500/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 00:13:56 loss: -0.7640 Lr: 9.02714e-05 +[2025-02-22 14:31:48,680 INFO hook.py line 109 2775932] Train: [93/100][550/800] Data 0.003 (0.003) Batch 0.153 (0.142) Remain 00:13:48 loss: -0.8353 Lr: 8.87731e-05 +[2025-02-22 14:31:55,931 INFO hook.py line 109 2775932] Train: [93/100][600/800] Data 0.003 (0.003) Batch 0.130 (0.142) Remain 00:13:42 loss: -0.7645 Lr: 8.72871e-05 +[2025-02-22 14:32:03,103 INFO hook.py line 109 2775932] Train: [93/100][650/800] Data 0.003 (0.003) Batch 0.131 (0.142) Remain 00:13:36 loss: -0.7571 Lr: 8.58136e-05 +[2025-02-22 14:32:10,289 INFO hook.py line 109 2775932] Train: [93/100][700/800] Data 0.005 (0.003) Batch 0.138 (0.142) Remain 00:13:30 loss: -0.9047 Lr: 8.43526e-05 +[2025-02-22 14:32:17,319 INFO hook.py line 109 2775932] Train: [93/100][750/800] Data 0.003 (0.003) Batch 0.164 (0.142) Remain 00:13:22 loss: -0.8115 Lr: 8.29040e-05 +[2025-02-22 14:32:24,099 INFO hook.py line 109 2775932] Train: [93/100][800/800] Data 0.002 (0.003) Batch 0.110 (0.142) Remain 00:13:13 loss: -0.7641 Lr: 8.14679e-05 +[2025-02-22 14:32:24,100 INFO misc.py line 135 2775932] Train result: loss: -0.7817 seg_loss: 0.0743 bias_l1_loss: 0.1190 bias_cosine_loss: -0.9749 +[2025-02-22 14:32:24,100 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:32:30,917 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9027 +[2025-02-22 14:32:31,283 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7151 +[2025-02-22 14:32:31,373 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6732 +[2025-02-22 14:32:31,476 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6567 +[2025-02-22 14:32:31,562 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7954 +[2025-02-22 14:32:31,641 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5824 +[2025-02-22 14:32:31,958 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5796 +[2025-02-22 14:32:31,999 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6024 +[2025-02-22 14:32:32,169 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5591 +[2025-02-22 14:32:32,238 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.1422 +[2025-02-22 14:32:32,538 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2559 +[2025-02-22 14:32:32,680 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1836 +[2025-02-22 14:32:32,787 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.5691 +[2025-02-22 14:32:32,910 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.7293 +[2025-02-22 14:32:33,014 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1588 +[2025-02-22 14:32:33,103 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7094 +[2025-02-22 14:32:33,260 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6649 +[2025-02-22 14:32:33,388 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2836 +[2025-02-22 14:32:33,565 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.1945 +[2025-02-22 14:32:33,640 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0139 +[2025-02-22 14:32:33,823 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7744 +[2025-02-22 14:32:34,017 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.2606 +[2025-02-22 14:32:34,117 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.1126 +[2025-02-22 14:32:34,187 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0770 +[2025-02-22 14:32:34,274 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4968 +[2025-02-22 14:32:34,343 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6586 +[2025-02-22 14:32:34,514 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1906 +[2025-02-22 14:32:34,671 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.5951 +[2025-02-22 14:32:34,763 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8066 +[2025-02-22 14:32:34,842 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7748 +[2025-02-22 14:32:35,854 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6508 +[2025-02-22 14:32:36,155 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.0985 +[2025-02-22 14:32:36,208 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7047 +[2025-02-22 14:32:36,326 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4203 +[2025-02-22 14:32:36,373 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5543 +[2025-02-22 14:32:36,501 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5516 +[2025-02-22 14:32:36,579 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7572 +[2025-02-22 14:32:36,746 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7892 +[2025-02-22 14:32:36,937 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7220 +[2025-02-22 14:32:37,169 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1333 +[2025-02-22 14:32:37,378 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6481 +[2025-02-22 14:32:37,446 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5611 +[2025-02-22 14:32:37,507 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8729 +[2025-02-22 14:32:37,834 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8189 +[2025-02-22 14:32:37,892 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7082 +[2025-02-22 14:32:37,950 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4385 +[2025-02-22 14:32:38,076 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4356 +[2025-02-22 14:32:38,260 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5868 +[2025-02-22 14:32:38,432 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.1904 +[2025-02-22 14:32:38,561 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1053 +[2025-02-22 14:32:38,685 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2909 +[2025-02-22 14:32:38,874 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4433 +[2025-02-22 14:32:38,924 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5745 +[2025-02-22 14:32:39,079 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9298 +[2025-02-22 14:32:39,219 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9157 +[2025-02-22 14:32:39,281 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6670 +[2025-02-22 14:32:39,484 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2051 +[2025-02-22 14:32:39,545 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6638 +[2025-02-22 14:32:39,867 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4373 +[2025-02-22 14:32:39,993 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4154 +[2025-02-22 14:32:40,104 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4379 +[2025-02-22 14:32:40,168 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6010 +[2025-02-22 14:32:40,387 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2414 +[2025-02-22 14:32:40,535 INFO evaluator.py line 595 2775932] Test: [64/78] Loss 0.0109 +[2025-02-22 14:32:40,630 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.0906 +[2025-02-22 14:32:40,830 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1965 +[2025-02-22 14:32:41,029 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7717 +[2025-02-22 14:32:41,142 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.2773 +[2025-02-22 14:32:41,208 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7308 +[2025-02-22 14:32:41,272 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5627 +[2025-02-22 14:32:41,503 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4399 +[2025-02-22 14:32:41,543 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4735 +[2025-02-22 14:32:41,608 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8867 +[2025-02-22 14:32:41,765 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7085 +[2025-02-22 14:32:42,106 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7125 +[2025-02-22 14:32:42,211 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1259 +[2025-02-22 14:32:42,421 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7270 +[2025-02-22 14:32:42,543 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6805 +[2025-02-22 14:32:58,031 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:32:58,031 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:32:58,031 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] cabinet : 0.2857 0.5118 0.7261 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] bed : 0.3212 0.7531 0.8880 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] chair : 0.7512 0.9066 0.9476 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] sofa : 0.3678 0.5931 0.8037 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] table : 0.4620 0.7214 0.8198 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] door : 0.2865 0.5085 0.6151 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] window : 0.2904 0.4982 0.6858 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] bookshelf : 0.2713 0.5881 0.7340 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] picture : 0.3605 0.4917 0.5654 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] counter : 0.0649 0.2465 0.5859 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] desk : 0.1314 0.4482 0.8242 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] curtain : 0.3535 0.5498 0.6254 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] refridgerator : 0.4416 0.5912 0.6596 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] shower curtain : 0.4266 0.5968 0.7070 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] toilet : 0.8937 1.0000 1.0000 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] sink : 0.4470 0.7389 0.8892 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] bathtub : 0.6790 0.7742 0.8710 +[2025-02-22 14:32:58,031 INFO evaluator.py line 547 2775932] otherfurniture : 0.4104 0.5893 0.6731 +[2025-02-22 14:32:58,031 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:32:58,032 INFO evaluator.py line 554 2775932] average : 0.4025 0.6171 0.7567 +[2025-02-22 14:32:58,032 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:32:58,032 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:32:58,059 INFO misc.py line 164 2775932] Currently Best AP50: 0.6197 +[2025-02-22 14:32:58,067 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:33:06,693 INFO hook.py line 109 2775932] Train: [94/100][50/800] Data 0.003 (0.003) Batch 0.138 (0.147) Remain 00:13:36 loss: -0.7847 Lr: 8.00442e-05 +[2025-02-22 14:33:13,787 INFO hook.py line 109 2775932] Train: [94/100][100/800] Data 0.003 (0.003) Batch 0.136 (0.144) Remain 00:13:14 loss: -0.7289 Lr: 7.86331e-05 +[2025-02-22 14:33:20,901 INFO hook.py line 109 2775932] Train: [94/100][150/800] Data 0.003 (0.004) Batch 0.139 (0.144) Remain 00:13:03 loss: -0.7542 Lr: 7.72344e-05 +[2025-02-22 14:33:28,034 INFO hook.py line 109 2775932] Train: [94/100][200/800] Data 0.003 (0.004) Batch 0.139 (0.143) Remain 00:12:54 loss: -0.8669 Lr: 7.58482e-05 +[2025-02-22 14:33:34,984 INFO hook.py line 109 2775932] Train: [94/100][250/800] Data 0.003 (0.004) Batch 0.136 (0.143) Remain 00:12:42 loss: -0.6988 Lr: 7.44744e-05 +[2025-02-22 14:33:42,011 INFO hook.py line 109 2775932] Train: [94/100][300/800] Data 0.003 (0.004) Batch 0.135 (0.142) Remain 00:12:33 loss: -0.8041 Lr: 7.31132e-05 +[2025-02-22 14:33:49,030 INFO hook.py line 109 2775932] Train: [94/100][350/800] Data 0.003 (0.003) Batch 0.139 (0.142) Remain 00:12:25 loss: -0.7738 Lr: 7.17645e-05 +[2025-02-22 14:33:56,050 INFO hook.py line 109 2775932] Train: [94/100][400/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:12:17 loss: -0.8469 Lr: 7.04283e-05 +[2025-02-22 14:34:03,311 INFO hook.py line 109 2775932] Train: [94/100][450/800] Data 0.006 (0.003) Batch 0.147 (0.142) Remain 00:12:11 loss: -0.7327 Lr: 6.91046e-05 +[2025-02-22 14:34:10,292 INFO hook.py line 109 2775932] Train: [94/100][500/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:12:03 loss: -0.8627 Lr: 6.77935e-05 +[2025-02-22 14:34:17,508 INFO hook.py line 109 2775932] Train: [94/100][550/800] Data 0.003 (0.003) Batch 0.141 (0.142) Remain 00:11:57 loss: -0.6981 Lr: 6.64948e-05 +[2025-02-22 14:34:24,657 INFO hook.py line 109 2775932] Train: [94/100][600/800] Data 0.003 (0.003) Batch 0.123 (0.142) Remain 00:11:50 loss: -0.8200 Lr: 6.52087e-05 +[2025-02-22 14:34:31,661 INFO hook.py line 109 2775932] Train: [94/100][650/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 00:11:42 loss: -0.7546 Lr: 6.39352e-05 +[2025-02-22 14:34:39,033 INFO hook.py line 109 2775932] Train: [94/100][700/800] Data 0.005 (0.003) Batch 0.137 (0.142) Remain 00:11:37 loss: -0.8420 Lr: 6.26741e-05 +[2025-02-22 14:34:46,126 INFO hook.py line 109 2775932] Train: [94/100][750/800] Data 0.004 (0.003) Batch 0.131 (0.142) Remain 00:11:30 loss: -0.8557 Lr: 6.14257e-05 +[2025-02-22 14:34:53,208 INFO hook.py line 109 2775932] Train: [94/100][800/800] Data 0.002 (0.003) Batch 0.143 (0.142) Remain 00:11:23 loss: -0.7089 Lr: 6.01897e-05 +[2025-02-22 14:34:53,209 INFO misc.py line 135 2775932] Train result: loss: -0.7803 seg_loss: 0.0747 bias_l1_loss: 0.1197 bias_cosine_loss: -0.9747 +[2025-02-22 14:34:53,209 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:35:00,124 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8978 +[2025-02-22 14:35:00,528 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7152 +[2025-02-22 14:35:00,612 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6794 +[2025-02-22 14:35:00,691 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6420 +[2025-02-22 14:35:00,764 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7769 +[2025-02-22 14:35:00,831 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.6435 +[2025-02-22 14:35:01,134 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6191 +[2025-02-22 14:35:01,171 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6244 +[2025-02-22 14:35:01,328 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5210 +[2025-02-22 14:35:01,393 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0850 +[2025-02-22 14:35:01,681 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2159 +[2025-02-22 14:35:01,806 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1520 +[2025-02-22 14:35:01,902 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.5407 +[2025-02-22 14:35:02,028 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6755 +[2025-02-22 14:35:02,129 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0041 +[2025-02-22 14:35:02,213 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7211 +[2025-02-22 14:35:02,363 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6486 +[2025-02-22 14:35:02,475 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.2948 +[2025-02-22 14:35:02,642 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2181 +[2025-02-22 14:35:02,711 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0473 +[2025-02-22 14:35:02,886 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7751 +[2025-02-22 14:35:03,072 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3607 +[2025-02-22 14:35:03,158 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0374 +[2025-02-22 14:35:03,222 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0643 +[2025-02-22 14:35:03,301 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.5651 +[2025-02-22 14:35:03,375 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6951 +[2025-02-22 14:35:03,568 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1334 +[2025-02-22 14:35:03,745 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6067 +[2025-02-22 14:35:03,839 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8084 +[2025-02-22 14:35:03,920 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.8031 +[2025-02-22 14:35:04,999 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6449 +[2025-02-22 14:35:05,312 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2480 +[2025-02-22 14:35:05,368 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7008 +[2025-02-22 14:35:05,492 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4181 +[2025-02-22 14:35:05,540 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5612 +[2025-02-22 14:35:05,673 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5121 +[2025-02-22 14:35:05,765 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7881 +[2025-02-22 14:35:05,937 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7946 +[2025-02-22 14:35:06,134 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7087 +[2025-02-22 14:35:06,387 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0998 +[2025-02-22 14:35:06,619 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6639 +[2025-02-22 14:35:06,691 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5343 +[2025-02-22 14:35:06,749 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8639 +[2025-02-22 14:35:07,097 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8170 +[2025-02-22 14:35:07,157 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7071 +[2025-02-22 14:35:07,223 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4520 +[2025-02-22 14:35:07,343 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4747 +[2025-02-22 14:35:07,521 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5650 +[2025-02-22 14:35:07,692 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2188 +[2025-02-22 14:35:07,814 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.1479 +[2025-02-22 14:35:07,941 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1880 +[2025-02-22 14:35:08,124 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4789 +[2025-02-22 14:35:08,172 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5700 +[2025-02-22 14:35:08,334 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0037 +[2025-02-22 14:35:08,459 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9267 +[2025-02-22 14:35:08,529 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.5963 +[2025-02-22 14:35:08,754 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2376 +[2025-02-22 14:35:08,815 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6633 +[2025-02-22 14:35:09,177 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4560 +[2025-02-22 14:35:09,291 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3496 +[2025-02-22 14:35:09,399 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4328 +[2025-02-22 14:35:09,465 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6600 +[2025-02-22 14:35:09,661 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3390 +[2025-02-22 14:35:09,782 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0580 +[2025-02-22 14:35:09,881 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1294 +[2025-02-22 14:35:10,060 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1677 +[2025-02-22 14:35:10,256 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7978 +[2025-02-22 14:35:10,371 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.1211 +[2025-02-22 14:35:10,432 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7060 +[2025-02-22 14:35:10,491 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5668 +[2025-02-22 14:35:10,708 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4671 +[2025-02-22 14:35:10,745 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4479 +[2025-02-22 14:35:10,806 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8871 +[2025-02-22 14:35:10,942 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.8330 +[2025-02-22 14:35:11,176 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7171 +[2025-02-22 14:35:11,271 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2414 +[2025-02-22 14:35:11,458 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7306 +[2025-02-22 14:35:11,569 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6592 +[2025-02-22 14:35:25,854 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:35:25,854 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:35:25,854 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] cabinet : 0.2907 0.5256 0.7270 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] bed : 0.3146 0.7743 0.8882 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] chair : 0.7543 0.9106 0.9485 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] sofa : 0.3629 0.5895 0.8059 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] table : 0.4735 0.7231 0.8332 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] door : 0.2903 0.5214 0.6238 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] window : 0.2911 0.5144 0.7013 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] bookshelf : 0.2606 0.5576 0.7280 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] picture : 0.3754 0.5200 0.6015 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] counter : 0.0751 0.3015 0.6135 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] desk : 0.1384 0.4423 0.8635 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] curtain : 0.3578 0.5508 0.6511 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] refridgerator : 0.5053 0.6615 0.7129 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] shower curtain : 0.4490 0.6180 0.7527 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] toilet : 0.8919 1.0000 1.0000 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] sink : 0.4371 0.7268 0.8795 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] bathtub : 0.6730 0.7742 0.8710 +[2025-02-22 14:35:25,854 INFO evaluator.py line 547 2775932] otherfurniture : 0.4076 0.5769 0.6641 +[2025-02-22 14:35:25,854 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:35:25,854 INFO evaluator.py line 554 2775932] average : 0.4083 0.6271 0.7703 +[2025-02-22 14:35:25,854 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:35:25,854 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:35:25,882 INFO misc.py line 159 2775932] Best validation AP50 updated to: 0.6271 +[2025-02-22 14:35:25,890 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:35:25,890 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:35:35,056 INFO hook.py line 109 2775932] Train: [95/100][50/800] Data 0.005 (0.003) Batch 0.151 (0.147) Remain 00:11:39 loss: -0.7949 Lr: 5.89664e-05 +[2025-02-22 14:35:42,215 INFO hook.py line 109 2775932] Train: [95/100][100/800] Data 0.002 (0.003) Batch 0.130 (0.145) Remain 00:11:22 loss: -0.6145 Lr: 5.77556e-05 +[2025-02-22 14:35:49,476 INFO hook.py line 109 2775932] Train: [95/100][150/800] Data 0.003 (0.003) Batch 0.152 (0.145) Remain 00:11:14 loss: -0.7399 Lr: 5.65574e-05 +[2025-02-22 14:35:56,597 INFO hook.py line 109 2775932] Train: [95/100][200/800] Data 0.003 (0.003) Batch 0.130 (0.144) Remain 00:11:04 loss: -0.8579 Lr: 5.53717e-05 +[2025-02-22 14:36:03,533 INFO hook.py line 109 2775932] Train: [95/100][250/800] Data 0.003 (0.003) Batch 0.130 (0.143) Remain 00:10:51 loss: -0.7952 Lr: 5.41986e-05 +[2025-02-22 14:36:10,659 INFO hook.py line 109 2775932] Train: [95/100][300/800] Data 0.003 (0.003) Batch 0.129 (0.143) Remain 00:10:44 loss: -0.7689 Lr: 5.30382e-05 +[2025-02-22 14:36:17,805 INFO hook.py line 109 2775932] Train: [95/100][350/800] Data 0.003 (0.004) Batch 0.117 (0.143) Remain 00:10:36 loss: -0.7935 Lr: 5.18903e-05 +[2025-02-22 14:36:24,879 INFO hook.py line 109 2775932] Train: [95/100][400/800] Data 0.003 (0.004) Batch 0.142 (0.143) Remain 00:10:28 loss: -0.7889 Lr: 5.07550e-05 +[2025-02-22 14:36:31,730 INFO hook.py line 109 2775932] Train: [95/100][450/800] Data 0.002 (0.003) Batch 0.141 (0.142) Remain 00:10:18 loss: -0.7500 Lr: 4.96323e-05 +[2025-02-22 14:36:38,509 INFO hook.py line 109 2775932] Train: [95/100][500/800] Data 0.003 (0.003) Batch 0.135 (0.142) Remain 00:10:08 loss: -0.7615 Lr: 4.85222e-05 +[2025-02-22 14:36:45,408 INFO hook.py line 109 2775932] Train: [95/100][550/800] Data 0.003 (0.003) Batch 0.149 (0.141) Remain 00:10:00 loss: -0.8007 Lr: 4.74247e-05 +[2025-02-22 14:36:52,487 INFO hook.py line 109 2775932] Train: [95/100][600/800] Data 0.003 (0.003) Batch 0.152 (0.141) Remain 00:09:53 loss: -0.7249 Lr: 4.63398e-05 +[2025-02-22 14:36:59,767 INFO hook.py line 109 2775932] Train: [95/100][650/800] Data 0.005 (0.003) Batch 0.129 (0.142) Remain 00:09:47 loss: -0.7280 Lr: 4.52676e-05 +[2025-02-22 14:37:07,007 INFO hook.py line 109 2775932] Train: [95/100][700/800] Data 0.003 (0.003) Batch 0.133 (0.142) Remain 00:09:41 loss: -0.7434 Lr: 4.42079e-05 +[2025-02-22 14:37:14,132 INFO hook.py line 109 2775932] Train: [95/100][750/800] Data 0.003 (0.003) Batch 0.158 (0.142) Remain 00:09:34 loss: -0.8329 Lr: 4.31817e-05 +[2025-02-22 14:37:21,074 INFO hook.py line 109 2775932] Train: [95/100][800/800] Data 0.002 (0.003) Batch 0.115 (0.142) Remain 00:09:26 loss: -0.8075 Lr: 4.21471e-05 +[2025-02-22 14:37:21,075 INFO misc.py line 135 2775932] Train result: loss: -0.7851 seg_loss: 0.0728 bias_l1_loss: 0.1176 bias_cosine_loss: -0.9754 +[2025-02-22 14:37:21,076 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:37:27,978 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9004 +[2025-02-22 14:37:28,375 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.6949 +[2025-02-22 14:37:28,462 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6889 +[2025-02-22 14:37:28,605 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6288 +[2025-02-22 14:37:28,685 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7927 +[2025-02-22 14:37:28,748 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5393 +[2025-02-22 14:37:29,125 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5628 +[2025-02-22 14:37:29,158 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6336 +[2025-02-22 14:37:29,320 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5714 +[2025-02-22 14:37:29,376 INFO evaluator.py line 595 2775932] Test: [10/78] Loss 0.0299 +[2025-02-22 14:37:29,660 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2524 +[2025-02-22 14:37:29,792 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1496 +[2025-02-22 14:37:29,888 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4613 +[2025-02-22 14:37:30,006 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.7107 +[2025-02-22 14:37:30,099 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1204 +[2025-02-22 14:37:30,185 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7132 +[2025-02-22 14:37:30,333 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6525 +[2025-02-22 14:37:30,447 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3573 +[2025-02-22 14:37:30,600 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2270 +[2025-02-22 14:37:30,670 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0076 +[2025-02-22 14:37:30,833 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7704 +[2025-02-22 14:37:31,025 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3469 +[2025-02-22 14:37:31,114 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0609 +[2025-02-22 14:37:31,178 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0632 +[2025-02-22 14:37:31,255 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.4845 +[2025-02-22 14:37:31,318 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7016 +[2025-02-22 14:37:31,477 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1791 +[2025-02-22 14:37:31,602 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6144 +[2025-02-22 14:37:31,688 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8191 +[2025-02-22 14:37:31,759 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7673 +[2025-02-22 14:37:32,626 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6460 +[2025-02-22 14:37:32,866 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1240 +[2025-02-22 14:37:32,923 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7244 +[2025-02-22 14:37:33,055 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4178 +[2025-02-22 14:37:33,103 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5803 +[2025-02-22 14:37:33,231 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5406 +[2025-02-22 14:37:33,306 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7546 +[2025-02-22 14:37:33,465 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7926 +[2025-02-22 14:37:33,650 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.5578 +[2025-02-22 14:37:33,884 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0801 +[2025-02-22 14:37:34,096 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6904 +[2025-02-22 14:37:34,163 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5670 +[2025-02-22 14:37:34,217 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8661 +[2025-02-22 14:37:34,509 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8308 +[2025-02-22 14:37:34,561 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.6934 +[2025-02-22 14:37:34,614 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4673 +[2025-02-22 14:37:34,720 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4653 +[2025-02-22 14:37:34,875 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5484 +[2025-02-22 14:37:35,023 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2439 +[2025-02-22 14:37:35,126 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2234 +[2025-02-22 14:37:35,244 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2455 +[2025-02-22 14:37:35,419 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4650 +[2025-02-22 14:37:35,463 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5968 +[2025-02-22 14:37:35,585 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 2.0353 +[2025-02-22 14:37:35,701 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9284 +[2025-02-22 14:37:35,755 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6676 +[2025-02-22 14:37:35,923 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2037 +[2025-02-22 14:37:35,969 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6508 +[2025-02-22 14:37:36,235 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.3955 +[2025-02-22 14:37:36,367 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3602 +[2025-02-22 14:37:36,483 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.4259 +[2025-02-22 14:37:36,549 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6127 +[2025-02-22 14:37:36,763 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3084 +[2025-02-22 14:37:36,886 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1396 +[2025-02-22 14:37:36,986 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1288 +[2025-02-22 14:37:37,208 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1758 +[2025-02-22 14:37:37,426 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7926 +[2025-02-22 14:37:37,544 INFO evaluator.py line 595 2775932] Test: [68/78] Loss 0.0038 +[2025-02-22 14:37:37,605 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7219 +[2025-02-22 14:37:37,664 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5341 +[2025-02-22 14:37:37,883 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4849 +[2025-02-22 14:37:37,919 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4248 +[2025-02-22 14:37:37,989 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8916 +[2025-02-22 14:37:38,117 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7959 +[2025-02-22 14:37:38,353 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6983 +[2025-02-22 14:37:38,448 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1327 +[2025-02-22 14:37:38,643 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7446 +[2025-02-22 14:37:38,754 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6628 +[2025-02-22 14:37:53,377 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:37:53,377 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:37:53,377 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:37:53,377 INFO evaluator.py line 547 2775932] cabinet : 0.2848 0.5147 0.7214 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] bed : 0.3174 0.7498 0.8879 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] chair : 0.7583 0.9153 0.9503 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] sofa : 0.3606 0.5910 0.8024 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] table : 0.4623 0.7245 0.8347 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] door : 0.2893 0.5174 0.6280 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] window : 0.2747 0.4777 0.6811 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] bookshelf : 0.2839 0.6052 0.7526 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] picture : 0.3619 0.4961 0.5701 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] counter : 0.0564 0.2206 0.6041 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] desk : 0.1290 0.4173 0.8550 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] curtain : 0.3819 0.5736 0.6347 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] refridgerator : 0.4602 0.6063 0.7070 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] shower curtain : 0.4213 0.6014 0.7444 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] toilet : 0.8967 1.0000 1.0000 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] sink : 0.4228 0.7231 0.8780 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] bathtub : 0.6723 0.7742 0.8710 +[2025-02-22 14:37:53,378 INFO evaluator.py line 547 2775932] otherfurniture : 0.3972 0.5678 0.6683 +[2025-02-22 14:37:53,378 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:37:53,378 INFO evaluator.py line 554 2775932] average : 0.4017 0.6153 0.7662 +[2025-02-22 14:37:53,378 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:37:53,378 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:37:53,403 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:37:53,411 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:38:02,122 INFO hook.py line 109 2775932] Train: [96/100][50/800] Data 0.004 (0.003) Batch 0.139 (0.146) Remain 00:09:36 loss: -0.7582 Lr: 4.11251e-05 +[2025-02-22 14:38:09,314 INFO hook.py line 109 2775932] Train: [96/100][100/800] Data 0.003 (0.003) Batch 0.140 (0.145) Remain 00:09:24 loss: -0.7624 Lr: 4.01158e-05 +[2025-02-22 14:38:16,505 INFO hook.py line 109 2775932] Train: [96/100][150/800] Data 0.003 (0.003) Batch 0.155 (0.145) Remain 00:09:16 loss: -0.6710 Lr: 3.91191e-05 +[2025-02-22 14:38:24,155 INFO hook.py line 109 2775932] Train: [96/100][200/800] Data 0.002 (0.004) Batch 0.125 (0.147) Remain 00:09:17 loss: -0.7932 Lr: 3.81350e-05 +[2025-02-22 14:38:31,125 INFO hook.py line 109 2775932] Train: [96/100][250/800] Data 0.003 (0.004) Batch 0.129 (0.145) Remain 00:09:04 loss: -0.8250 Lr: 3.71636e-05 +[2025-02-22 14:38:38,016 INFO hook.py line 109 2775932] Train: [96/100][300/800] Data 0.003 (0.004) Batch 0.134 (0.144) Remain 00:08:52 loss: -0.8184 Lr: 3.62049e-05 +[2025-02-22 14:38:45,138 INFO hook.py line 109 2775932] Train: [96/100][350/800] Data 0.003 (0.003) Batch 0.140 (0.144) Remain 00:08:44 loss: -0.7083 Lr: 3.52588e-05 +[2025-02-22 14:38:52,268 INFO hook.py line 109 2775932] Train: [96/100][400/800] Data 0.003 (0.003) Batch 0.142 (0.144) Remain 00:08:36 loss: -0.8268 Lr: 3.43254e-05 +[2025-02-22 14:38:59,452 INFO hook.py line 109 2775932] Train: [96/100][450/800] Data 0.003 (0.003) Batch 0.137 (0.144) Remain 00:08:29 loss: -0.8542 Lr: 3.34047e-05 +[2025-02-22 14:39:06,546 INFO hook.py line 109 2775932] Train: [96/100][500/800] Data 0.003 (0.003) Batch 0.147 (0.143) Remain 00:08:21 loss: -0.7409 Lr: 3.24966e-05 +[2025-02-22 14:39:13,570 INFO hook.py line 109 2775932] Train: [96/100][550/800] Data 0.003 (0.003) Batch 0.170 (0.143) Remain 00:08:13 loss: -0.6555 Lr: 3.16012e-05 +[2025-02-22 14:39:20,843 INFO hook.py line 109 2775932] Train: [96/100][600/800] Data 0.003 (0.003) Batch 0.128 (0.143) Remain 00:08:07 loss: -0.8049 Lr: 3.07185e-05 +[2025-02-22 14:39:27,926 INFO hook.py line 109 2775932] Train: [96/100][650/800] Data 0.002 (0.003) Batch 0.148 (0.143) Remain 00:07:59 loss: -0.8274 Lr: 2.98485e-05 +[2025-02-22 14:39:35,093 INFO hook.py line 109 2775932] Train: [96/100][700/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 00:07:52 loss: -0.7792 Lr: 2.89912e-05 +[2025-02-22 14:39:42,070 INFO hook.py line 109 2775932] Train: [96/100][750/800] Data 0.002 (0.003) Batch 0.129 (0.143) Remain 00:07:44 loss: -0.8401 Lr: 2.81465e-05 +[2025-02-22 14:39:48,970 INFO hook.py line 109 2775932] Train: [96/100][800/800] Data 0.001 (0.003) Batch 0.106 (0.143) Remain 00:07:36 loss: -0.8576 Lr: 2.73146e-05 +[2025-02-22 14:39:48,971 INFO misc.py line 135 2775932] Train result: loss: -0.7834 seg_loss: 0.0715 bias_l1_loss: 0.1202 bias_cosine_loss: -0.9751 +[2025-02-22 14:39:48,971 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:39:56,041 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8995 +[2025-02-22 14:39:56,387 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7109 +[2025-02-22 14:39:56,470 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6886 +[2025-02-22 14:39:56,549 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6382 +[2025-02-22 14:39:56,621 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7853 +[2025-02-22 14:39:56,688 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5644 +[2025-02-22 14:39:56,994 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.6202 +[2025-02-22 14:39:57,084 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6018 +[2025-02-22 14:39:57,240 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5738 +[2025-02-22 14:39:57,296 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0342 +[2025-02-22 14:39:57,590 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2554 +[2025-02-22 14:39:57,722 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1600 +[2025-02-22 14:39:57,822 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4526 +[2025-02-22 14:39:57,949 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6535 +[2025-02-22 14:39:58,047 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1082 +[2025-02-22 14:39:58,133 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7114 +[2025-02-22 14:39:58,300 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6457 +[2025-02-22 14:39:58,419 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3394 +[2025-02-22 14:39:58,586 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2042 +[2025-02-22 14:39:58,656 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0318 +[2025-02-22 14:39:58,844 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7791 +[2025-02-22 14:39:59,063 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3206 +[2025-02-22 14:39:59,183 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0787 +[2025-02-22 14:39:59,274 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0793 +[2025-02-22 14:39:59,372 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.5010 +[2025-02-22 14:39:59,495 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7087 +[2025-02-22 14:39:59,671 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1468 +[2025-02-22 14:39:59,839 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6288 +[2025-02-22 14:39:59,943 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8109 +[2025-02-22 14:40:00,027 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7824 +[2025-02-22 14:40:00,971 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6469 +[2025-02-22 14:40:01,257 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2568 +[2025-02-22 14:40:01,307 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.6909 +[2025-02-22 14:40:01,413 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.3796 +[2025-02-22 14:40:01,463 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5360 +[2025-02-22 14:40:01,574 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5268 +[2025-02-22 14:40:01,665 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7543 +[2025-02-22 14:40:01,840 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7940 +[2025-02-22 14:40:02,032 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6358 +[2025-02-22 14:40:02,262 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0999 +[2025-02-22 14:40:02,467 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6747 +[2025-02-22 14:40:02,534 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5404 +[2025-02-22 14:40:02,596 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8686 +[2025-02-22 14:40:02,882 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8228 +[2025-02-22 14:40:02,935 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7082 +[2025-02-22 14:40:02,988 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4605 +[2025-02-22 14:40:03,090 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.6205 +[2025-02-22 14:40:03,241 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5875 +[2025-02-22 14:40:03,393 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3409 +[2025-02-22 14:40:03,497 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2092 +[2025-02-22 14:40:03,602 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.1713 +[2025-02-22 14:40:03,780 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4786 +[2025-02-22 14:40:03,827 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5750 +[2025-02-22 14:40:03,954 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9580 +[2025-02-22 14:40:04,063 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9193 +[2025-02-22 14:40:04,113 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6388 +[2025-02-22 14:40:04,275 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1897 +[2025-02-22 14:40:04,321 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6566 +[2025-02-22 14:40:04,587 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4334 +[2025-02-22 14:40:04,713 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4056 +[2025-02-22 14:40:04,819 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3722 +[2025-02-22 14:40:04,884 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6445 +[2025-02-22 14:40:05,094 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.1973 +[2025-02-22 14:40:05,224 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1327 +[2025-02-22 14:40:05,318 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1375 +[2025-02-22 14:40:05,486 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.2148 +[2025-02-22 14:40:05,697 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.8000 +[2025-02-22 14:40:05,829 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0770 +[2025-02-22 14:40:05,897 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7282 +[2025-02-22 14:40:05,966 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5440 +[2025-02-22 14:40:06,192 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5219 +[2025-02-22 14:40:06,233 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4117 +[2025-02-22 14:40:06,294 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8933 +[2025-02-22 14:40:06,439 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7553 +[2025-02-22 14:40:06,645 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6832 +[2025-02-22 14:40:06,729 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2036 +[2025-02-22 14:40:06,886 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7615 +[2025-02-22 14:40:06,982 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6611 +[2025-02-22 14:40:21,266 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:40:21,266 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:40:21,266 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] cabinet : 0.2850 0.5190 0.7125 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] bed : 0.3162 0.7475 0.8751 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] chair : 0.7549 0.9075 0.9474 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] sofa : 0.3606 0.5942 0.7935 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] table : 0.4770 0.7212 0.8318 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] door : 0.2825 0.5091 0.6243 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] window : 0.2881 0.4813 0.6865 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] bookshelf : 0.2700 0.5681 0.7265 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] picture : 0.3701 0.5055 0.6016 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] counter : 0.0621 0.2819 0.6136 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] desk : 0.1356 0.4547 0.8614 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] curtain : 0.3712 0.5496 0.6501 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] refridgerator : 0.4508 0.6050 0.6581 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] shower curtain : 0.4326 0.6038 0.7404 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] toilet : 0.8909 1.0000 1.0000 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] sink : 0.4448 0.7244 0.8681 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] bathtub : 0.6715 0.7742 0.8710 +[2025-02-22 14:40:21,266 INFO evaluator.py line 547 2775932] otherfurniture : 0.3965 0.5599 0.6577 +[2025-02-22 14:40:21,266 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:40:21,266 INFO evaluator.py line 554 2775932] average : 0.4034 0.6170 0.7622 +[2025-02-22 14:40:21,266 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:40:21,266 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:40:21,294 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:40:21,301 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:40:30,215 INFO hook.py line 109 2775932] Train: [97/100][50/800] Data 0.002 (0.006) Batch 0.134 (0.149) Remain 00:07:50 loss: -0.7656 Lr: 2.64954e-05 +[2025-02-22 14:40:37,344 INFO hook.py line 109 2775932] Train: [97/100][100/800] Data 0.003 (0.005) Batch 0.152 (0.146) Remain 00:07:32 loss: -0.7227 Lr: 2.56888e-05 +[2025-02-22 14:40:44,387 INFO hook.py line 109 2775932] Train: [97/100][150/800] Data 0.004 (0.004) Batch 0.135 (0.144) Remain 00:07:19 loss: -0.7963 Lr: 2.48950e-05 +[2025-02-22 14:40:51,452 INFO hook.py line 109 2775932] Train: [97/100][200/800] Data 0.003 (0.004) Batch 0.122 (0.143) Remain 00:07:10 loss: -0.7387 Lr: 2.41139e-05 +[2025-02-22 14:40:58,529 INFO hook.py line 109 2775932] Train: [97/100][250/800] Data 0.003 (0.004) Batch 0.138 (0.143) Remain 00:07:01 loss: -0.7956 Lr: 2.33455e-05 +[2025-02-22 14:41:05,589 INFO hook.py line 109 2775932] Train: [97/100][300/800] Data 0.003 (0.004) Batch 0.144 (0.143) Remain 00:06:53 loss: -0.7461 Lr: 2.25898e-05 +[2025-02-22 14:41:12,733 INFO hook.py line 109 2775932] Train: [97/100][350/800] Data 0.003 (0.003) Batch 0.131 (0.143) Remain 00:06:46 loss: -0.7241 Lr: 2.18468e-05 +[2025-02-22 14:41:19,883 INFO hook.py line 109 2775932] Train: [97/100][400/800] Data 0.003 (0.003) Batch 0.148 (0.143) Remain 00:06:39 loss: -0.8403 Lr: 2.11166e-05 +[2025-02-22 14:41:26,901 INFO hook.py line 109 2775932] Train: [97/100][450/800] Data 0.003 (0.003) Batch 0.134 (0.143) Remain 00:06:31 loss: -0.8296 Lr: 2.03990e-05 +[2025-02-22 14:41:33,864 INFO hook.py line 109 2775932] Train: [97/100][500/800] Data 0.003 (0.003) Batch 0.152 (0.142) Remain 00:06:23 loss: -0.7967 Lr: 1.96942e-05 +[2025-02-22 14:41:41,316 INFO hook.py line 109 2775932] Train: [97/100][550/800] Data 0.004 (0.003) Batch 0.133 (0.143) Remain 00:06:18 loss: -0.8339 Lr: 1.90022e-05 +[2025-02-22 14:41:48,563 INFO hook.py line 109 2775932] Train: [97/100][600/800] Data 0.002 (0.003) Batch 0.151 (0.143) Remain 00:06:11 loss: -0.7974 Lr: 1.83229e-05 +[2025-02-22 14:41:55,940 INFO hook.py line 109 2775932] Train: [97/100][650/800] Data 0.003 (0.003) Batch 0.149 (0.143) Remain 00:06:05 loss: -0.8266 Lr: 1.76563e-05 +[2025-02-22 14:42:03,131 INFO hook.py line 109 2775932] Train: [97/100][700/800] Data 0.003 (0.003) Batch 0.152 (0.143) Remain 00:05:58 loss: -0.8344 Lr: 1.70024e-05 +[2025-02-22 14:42:10,316 INFO hook.py line 109 2775932] Train: [97/100][750/800] Data 0.003 (0.003) Batch 0.267 (0.143) Remain 00:05:51 loss: -0.8444 Lr: 1.63613e-05 +[2025-02-22 14:42:17,110 INFO hook.py line 109 2775932] Train: [97/100][800/800] Data 0.002 (0.003) Batch 0.124 (0.143) Remain 00:05:43 loss: -0.7991 Lr: 1.57330e-05 +[2025-02-22 14:42:17,111 INFO misc.py line 135 2775932] Train result: loss: -0.7884 seg_loss: 0.0717 bias_l1_loss: 0.1159 bias_cosine_loss: -0.9760 +[2025-02-22 14:42:17,112 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:42:24,454 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9022 +[2025-02-22 14:42:24,761 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7096 +[2025-02-22 14:42:24,853 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6847 +[2025-02-22 14:42:24,931 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6376 +[2025-02-22 14:42:25,000 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8013 +[2025-02-22 14:42:25,069 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5365 +[2025-02-22 14:42:25,377 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5877 +[2025-02-22 14:42:25,414 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6149 +[2025-02-22 14:42:25,571 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5388 +[2025-02-22 14:42:25,634 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0476 +[2025-02-22 14:42:25,926 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2613 +[2025-02-22 14:42:26,057 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1408 +[2025-02-22 14:42:26,152 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4039 +[2025-02-22 14:42:26,280 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6029 +[2025-02-22 14:42:26,372 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0822 +[2025-02-22 14:42:26,461 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7164 +[2025-02-22 14:42:26,612 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6693 +[2025-02-22 14:42:26,738 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3525 +[2025-02-22 14:42:26,902 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2422 +[2025-02-22 14:42:26,978 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0293 +[2025-02-22 14:42:27,147 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7737 +[2025-02-22 14:42:27,342 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3107 +[2025-02-22 14:42:27,430 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0632 +[2025-02-22 14:42:27,494 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0861 +[2025-02-22 14:42:27,574 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6207 +[2025-02-22 14:42:27,636 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7230 +[2025-02-22 14:42:27,785 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0890 +[2025-02-22 14:42:27,916 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6029 +[2025-02-22 14:42:27,997 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8099 +[2025-02-22 14:42:28,068 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7759 +[2025-02-22 14:42:28,925 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6449 +[2025-02-22 14:42:29,173 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2130 +[2025-02-22 14:42:29,223 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7343 +[2025-02-22 14:42:29,330 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4095 +[2025-02-22 14:42:29,370 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5447 +[2025-02-22 14:42:29,485 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5325 +[2025-02-22 14:42:29,555 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7644 +[2025-02-22 14:42:29,695 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7903 +[2025-02-22 14:42:29,857 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.6839 +[2025-02-22 14:42:30,064 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1051 +[2025-02-22 14:42:30,244 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6760 +[2025-02-22 14:42:30,301 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5344 +[2025-02-22 14:42:30,346 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8709 +[2025-02-22 14:42:30,608 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8231 +[2025-02-22 14:42:30,652 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7083 +[2025-02-22 14:42:30,700 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4705 +[2025-02-22 14:42:30,811 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.4531 +[2025-02-22 14:42:30,960 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5905 +[2025-02-22 14:42:31,110 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3308 +[2025-02-22 14:42:31,213 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2027 +[2025-02-22 14:42:31,325 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2179 +[2025-02-22 14:42:31,513 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4629 +[2025-02-22 14:42:31,561 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5784 +[2025-02-22 14:42:31,688 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9579 +[2025-02-22 14:42:31,793 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9235 +[2025-02-22 14:42:31,841 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6767 +[2025-02-22 14:42:32,003 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2096 +[2025-02-22 14:42:32,072 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6592 +[2025-02-22 14:42:32,327 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4197 +[2025-02-22 14:42:32,445 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4151 +[2025-02-22 14:42:32,553 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3694 +[2025-02-22 14:42:32,618 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6494 +[2025-02-22 14:42:32,821 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3506 +[2025-02-22 14:42:32,941 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1327 +[2025-02-22 14:42:33,030 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1169 +[2025-02-22 14:42:33,213 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1918 +[2025-02-22 14:42:33,411 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7993 +[2025-02-22 14:42:33,523 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.1316 +[2025-02-22 14:42:33,581 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7232 +[2025-02-22 14:42:33,641 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5783 +[2025-02-22 14:42:33,918 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4623 +[2025-02-22 14:42:33,960 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4614 +[2025-02-22 14:42:34,026 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8870 +[2025-02-22 14:42:34,171 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7243 +[2025-02-22 14:42:34,432 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6985 +[2025-02-22 14:42:34,533 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.2189 +[2025-02-22 14:42:34,793 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7504 +[2025-02-22 14:42:34,936 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6676 +[2025-02-22 14:42:50,210 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:42:50,210 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:42:50,210 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] cabinet : 0.2939 0.5324 0.7135 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] bed : 0.3105 0.7547 0.8863 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] chair : 0.7558 0.9122 0.9477 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] sofa : 0.3504 0.5675 0.7832 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] table : 0.4711 0.7180 0.8301 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] door : 0.2882 0.5069 0.6238 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] window : 0.2910 0.4926 0.6963 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] bookshelf : 0.2692 0.5750 0.7436 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] picture : 0.3634 0.5051 0.5863 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] counter : 0.0719 0.2856 0.6299 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] desk : 0.1343 0.4483 0.8648 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] curtain : 0.3674 0.5430 0.6267 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] refridgerator : 0.4554 0.6195 0.6729 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] shower curtain : 0.4339 0.6103 0.7437 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] toilet : 0.8916 1.0000 1.0000 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] sink : 0.4513 0.7386 0.8794 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] bathtub : 0.6728 0.7742 0.8710 +[2025-02-22 14:42:50,210 INFO evaluator.py line 547 2775932] otherfurniture : 0.4076 0.5794 0.6654 +[2025-02-22 14:42:50,210 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:42:50,210 INFO evaluator.py line 554 2775932] average : 0.4044 0.6202 0.7647 +[2025-02-22 14:42:50,210 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:42:50,210 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:42:50,237 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:42:50,246 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:42:59,524 INFO hook.py line 109 2775932] Train: [98/100][50/800] Data 0.003 (0.007) Batch 0.124 (0.150) Remain 00:05:53 loss: -0.7914 Lr: 1.51174e-05 +[2025-02-22 14:43:06,936 INFO hook.py line 109 2775932] Train: [98/100][100/800] Data 0.003 (0.005) Batch 0.168 (0.149) Remain 00:05:43 loss: -0.8067 Lr: 1.45145e-05 +[2025-02-22 14:43:14,011 INFO hook.py line 109 2775932] Train: [98/100][150/800] Data 0.003 (0.004) Batch 0.139 (0.147) Remain 00:05:29 loss: -0.7602 Lr: 1.39244e-05 +[2025-02-22 14:43:20,871 INFO hook.py line 109 2775932] Train: [98/100][200/800] Data 0.003 (0.004) Batch 0.119 (0.144) Remain 00:05:17 loss: -0.7621 Lr: 1.33471e-05 +[2025-02-22 14:43:28,206 INFO hook.py line 109 2775932] Train: [98/100][250/800] Data 0.003 (0.004) Batch 0.132 (0.145) Remain 00:05:11 loss: -0.8071 Lr: 1.27825e-05 +[2025-02-22 14:43:34,957 INFO hook.py line 109 2775932] Train: [98/100][300/800] Data 0.003 (0.004) Batch 0.142 (0.143) Remain 00:05:00 loss: -0.7747 Lr: 1.22307e-05 +[2025-02-22 14:43:41,873 INFO hook.py line 109 2775932] Train: [98/100][350/800] Data 0.003 (0.004) Batch 0.137 (0.142) Remain 00:04:51 loss: -0.8401 Lr: 1.17023e-05 +[2025-02-22 14:43:48,915 INFO hook.py line 109 2775932] Train: [98/100][400/800] Data 0.003 (0.004) Batch 0.130 (0.142) Remain 00:04:44 loss: -0.7837 Lr: 1.11758e-05 +[2025-02-22 14:43:56,023 INFO hook.py line 109 2775932] Train: [98/100][450/800] Data 0.002 (0.004) Batch 0.134 (0.142) Remain 00:04:37 loss: -0.7710 Lr: 1.06620e-05 +[2025-02-22 14:44:03,262 INFO hook.py line 109 2775932] Train: [98/100][500/800] Data 0.003 (0.004) Batch 0.171 (0.142) Remain 00:04:30 loss: -0.7145 Lr: 1.01610e-05 +[2025-02-22 14:44:10,363 INFO hook.py line 109 2775932] Train: [98/100][550/800] Data 0.004 (0.004) Batch 0.132 (0.142) Remain 00:04:23 loss: -0.7815 Lr: 9.67278e-06 +[2025-02-22 14:44:17,643 INFO hook.py line 109 2775932] Train: [98/100][600/800] Data 0.003 (0.004) Batch 0.134 (0.143) Remain 00:04:16 loss: -0.8425 Lr: 9.19733e-06 +[2025-02-22 14:44:24,912 INFO hook.py line 109 2775932] Train: [98/100][650/800] Data 0.002 (0.004) Batch 0.135 (0.143) Remain 00:04:10 loss: -0.7549 Lr: 8.73466e-06 +[2025-02-22 14:44:31,899 INFO hook.py line 109 2775932] Train: [98/100][700/800] Data 0.003 (0.003) Batch 0.152 (0.143) Remain 00:04:02 loss: -0.7789 Lr: 8.28477e-06 +[2025-02-22 14:44:38,973 INFO hook.py line 109 2775932] Train: [98/100][750/800] Data 0.003 (0.003) Batch 0.149 (0.143) Remain 00:03:55 loss: -0.7630 Lr: 7.84765e-06 +[2025-02-22 14:44:45,929 INFO hook.py line 109 2775932] Train: [98/100][800/800] Data 0.002 (0.003) Batch 0.112 (0.142) Remain 00:03:47 loss: -0.8006 Lr: 7.42332e-06 +[2025-02-22 14:44:45,929 INFO misc.py line 135 2775932] Train result: loss: -0.7889 seg_loss: 0.0703 bias_l1_loss: 0.1164 bias_cosine_loss: -0.9756 +[2025-02-22 14:44:45,930 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:44:52,819 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9001 +[2025-02-22 14:44:53,266 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7136 +[2025-02-22 14:44:53,343 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6864 +[2025-02-22 14:44:54,067 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6424 +[2025-02-22 14:44:54,146 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8053 +[2025-02-22 14:44:54,210 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5260 +[2025-02-22 14:44:54,507 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5589 +[2025-02-22 14:44:54,546 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6272 +[2025-02-22 14:44:54,708 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5623 +[2025-02-22 14:44:54,781 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0699 +[2025-02-22 14:44:55,082 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2427 +[2025-02-22 14:44:55,209 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1495 +[2025-02-22 14:44:55,309 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4029 +[2025-02-22 14:44:55,424 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6637 +[2025-02-22 14:44:55,527 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1012 +[2025-02-22 14:44:55,615 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7184 +[2025-02-22 14:44:55,771 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6612 +[2025-02-22 14:44:55,879 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3352 +[2025-02-22 14:44:56,057 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2565 +[2025-02-22 14:44:56,129 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0252 +[2025-02-22 14:44:56,299 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7762 +[2025-02-22 14:44:56,477 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3301 +[2025-02-22 14:44:56,572 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0509 +[2025-02-22 14:44:56,638 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.0986 +[2025-02-22 14:44:56,711 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.5692 +[2025-02-22 14:44:56,777 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.6972 +[2025-02-22 14:44:56,924 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0845 +[2025-02-22 14:44:57,068 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6279 +[2025-02-22 14:44:57,172 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8121 +[2025-02-22 14:44:57,260 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7714 +[2025-02-22 14:44:58,099 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6471 +[2025-02-22 14:44:58,359 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2061 +[2025-02-22 14:44:58,405 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7146 +[2025-02-22 14:44:58,523 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4042 +[2025-02-22 14:44:58,568 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5267 +[2025-02-22 14:44:58,733 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5605 +[2025-02-22 14:44:58,819 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7600 +[2025-02-22 14:44:59,006 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7853 +[2025-02-22 14:44:59,205 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7018 +[2025-02-22 14:44:59,447 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.0869 +[2025-02-22 14:44:59,660 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6751 +[2025-02-22 14:44:59,728 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5522 +[2025-02-22 14:44:59,791 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8694 +[2025-02-22 14:45:00,094 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8229 +[2025-02-22 14:45:00,147 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7084 +[2025-02-22 14:45:00,199 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4616 +[2025-02-22 14:45:00,309 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3865 +[2025-02-22 14:45:00,466 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5796 +[2025-02-22 14:45:00,618 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.3367 +[2025-02-22 14:45:00,744 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2424 +[2025-02-22 14:45:00,844 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2367 +[2025-02-22 14:45:01,030 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4958 +[2025-02-22 14:45:01,077 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5938 +[2025-02-22 14:45:01,206 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9638 +[2025-02-22 14:45:01,312 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9215 +[2025-02-22 14:45:01,361 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6407 +[2025-02-22 14:45:01,527 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2022 +[2025-02-22 14:45:01,577 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6530 +[2025-02-22 14:45:01,840 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4229 +[2025-02-22 14:45:01,970 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.4224 +[2025-02-22 14:45:02,094 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3788 +[2025-02-22 14:45:02,173 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6166 +[2025-02-22 14:45:02,429 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.2997 +[2025-02-22 14:45:02,561 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1126 +[2025-02-22 14:45:02,669 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1410 +[2025-02-22 14:45:02,868 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1861 +[2025-02-22 14:45:03,110 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7981 +[2025-02-22 14:45:03,243 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0627 +[2025-02-22 14:45:03,310 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7074 +[2025-02-22 14:45:03,382 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5718 +[2025-02-22 14:45:03,635 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5022 +[2025-02-22 14:45:03,675 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4319 +[2025-02-22 14:45:03,734 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8851 +[2025-02-22 14:45:03,869 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7565 +[2025-02-22 14:45:04,143 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.6903 +[2025-02-22 14:45:04,248 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1629 +[2025-02-22 14:45:04,472 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7577 +[2025-02-22 14:45:04,606 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6481 +[2025-02-22 14:45:19,577 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:45:19,578 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:45:19,578 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] cabinet : 0.3033 0.5458 0.7269 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] bed : 0.3115 0.7250 0.8867 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] chair : 0.7567 0.9072 0.9458 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] sofa : 0.3618 0.5892 0.8014 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] table : 0.4670 0.7124 0.8316 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] door : 0.2878 0.5130 0.6274 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] window : 0.2840 0.4786 0.6904 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] bookshelf : 0.2706 0.5773 0.7389 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] picture : 0.3724 0.5163 0.5716 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] counter : 0.0567 0.2290 0.6359 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] desk : 0.1357 0.4686 0.8606 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] curtain : 0.3655 0.5603 0.6489 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] refridgerator : 0.4535 0.6085 0.6870 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] shower curtain : 0.4284 0.5927 0.7283 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] toilet : 0.8848 1.0000 1.0000 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] sink : 0.4312 0.7143 0.8675 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] bathtub : 0.6712 0.7742 0.8710 +[2025-02-22 14:45:19,578 INFO evaluator.py line 547 2775932] otherfurniture : 0.4111 0.5809 0.6697 +[2025-02-22 14:45:19,578 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:45:19,578 INFO evaluator.py line 554 2775932] average : 0.4030 0.6163 0.7661 +[2025-02-22 14:45:19,578 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:45:19,578 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:45:19,605 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:45:19,613 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:45:28,605 INFO hook.py line 109 2775932] Train: [99/100][50/800] Data 0.003 (0.003) Batch 0.152 (0.154) Remain 00:03:58 loss: -0.7184 Lr: 7.01178e-06 +[2025-02-22 14:45:35,606 INFO hook.py line 109 2775932] Train: [99/100][100/800] Data 0.003 (0.003) Batch 0.168 (0.147) Remain 00:03:39 loss: -0.7972 Lr: 6.61302e-06 +[2025-02-22 14:45:42,907 INFO hook.py line 109 2775932] Train: [99/100][150/800] Data 0.002 (0.004) Batch 0.121 (0.146) Remain 00:03:32 loss: -0.8671 Lr: 6.22705e-06 +[2025-02-22 14:45:49,979 INFO hook.py line 109 2775932] Train: [99/100][200/800] Data 0.003 (0.003) Batch 0.161 (0.145) Remain 00:03:23 loss: -0.8760 Lr: 5.85387e-06 +[2025-02-22 14:45:57,218 INFO hook.py line 109 2775932] Train: [99/100][250/800] Data 0.005 (0.003) Batch 0.150 (0.145) Remain 00:03:15 loss: -0.8634 Lr: 5.49349e-06 +[2025-02-22 14:46:04,375 INFO hook.py line 109 2775932] Train: [99/100][300/800] Data 0.003 (0.003) Batch 0.180 (0.145) Remain 00:03:08 loss: -0.8564 Lr: 5.14589e-06 +[2025-02-22 14:46:11,334 INFO hook.py line 109 2775932] Train: [99/100][350/800] Data 0.003 (0.003) Batch 0.115 (0.144) Remain 00:02:59 loss: -0.7017 Lr: 4.81109e-06 +[2025-02-22 14:46:18,391 INFO hook.py line 109 2775932] Train: [99/100][400/800] Data 0.003 (0.003) Batch 0.135 (0.144) Remain 00:02:52 loss: -0.8326 Lr: 4.48909e-06 +[2025-02-22 14:46:25,506 INFO hook.py line 109 2775932] Train: [99/100][450/800] Data 0.003 (0.003) Batch 0.140 (0.143) Remain 00:02:44 loss: -0.7771 Lr: 4.17988e-06 +[2025-02-22 14:46:32,609 INFO hook.py line 109 2775932] Train: [99/100][500/800] Data 0.003 (0.003) Batch 0.131 (0.143) Remain 00:02:37 loss: -0.8068 Lr: 3.88348e-06 +[2025-02-22 14:46:39,761 INFO hook.py line 109 2775932] Train: [99/100][550/800] Data 0.002 (0.003) Batch 0.126 (0.143) Remain 00:02:30 loss: -0.6646 Lr: 3.59987e-06 +[2025-02-22 14:46:46,941 INFO hook.py line 109 2775932] Train: [99/100][600/800] Data 0.003 (0.003) Batch 0.155 (0.143) Remain 00:02:23 loss: -0.7788 Lr: 3.32907e-06 +[2025-02-22 14:46:54,081 INFO hook.py line 109 2775932] Train: [99/100][650/800] Data 0.003 (0.003) Batch 0.170 (0.143) Remain 00:02:16 loss: -0.6842 Lr: 3.07106e-06 +[2025-02-22 14:47:01,113 INFO hook.py line 109 2775932] Train: [99/100][700/800] Data 0.003 (0.003) Batch 0.136 (0.143) Remain 00:02:08 loss: -0.8046 Lr: 2.82586e-06 +[2025-02-22 14:47:07,950 INFO hook.py line 109 2775932] Train: [99/100][750/800] Data 0.003 (0.003) Batch 0.143 (0.143) Remain 00:02:01 loss: -0.8180 Lr: 2.59347e-06 +[2025-02-22 14:47:14,950 INFO hook.py line 109 2775932] Train: [99/100][800/800] Data 0.001 (0.003) Batch 0.130 (0.142) Remain 00:01:53 loss: -0.7894 Lr: 2.37388e-06 +[2025-02-22 14:47:14,951 INFO misc.py line 135 2775932] Train result: loss: -0.7901 seg_loss: 0.0711 bias_l1_loss: 0.1147 bias_cosine_loss: -0.9759 +[2025-02-22 14:47:14,951 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:47:22,194 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.8982 +[2025-02-22 14:47:22,636 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7025 +[2025-02-22 14:47:22,713 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6873 +[2025-02-22 14:47:22,790 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6350 +[2025-02-22 14:47:22,868 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.7987 +[2025-02-22 14:47:22,936 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5257 +[2025-02-22 14:47:23,247 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5789 +[2025-02-22 14:47:23,281 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6180 +[2025-02-22 14:47:23,427 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5424 +[2025-02-22 14:47:23,499 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0709 +[2025-02-22 14:47:23,799 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2478 +[2025-02-22 14:47:23,934 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1501 +[2025-02-22 14:47:24,040 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.3937 +[2025-02-22 14:47:24,160 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6803 +[2025-02-22 14:47:24,259 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.1022 +[2025-02-22 14:47:24,352 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7163 +[2025-02-22 14:47:24,502 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6549 +[2025-02-22 14:47:24,618 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3271 +[2025-02-22 14:47:24,784 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2177 +[2025-02-22 14:47:24,855 INFO evaluator.py line 595 2775932] Test: [20/78] Loss 0.0046 +[2025-02-22 14:47:25,024 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7710 +[2025-02-22 14:47:25,209 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3208 +[2025-02-22 14:47:25,298 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0662 +[2025-02-22 14:47:25,364 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1121 +[2025-02-22 14:47:25,457 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.5820 +[2025-02-22 14:47:25,517 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7220 +[2025-02-22 14:47:25,664 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.1302 +[2025-02-22 14:47:25,795 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6390 +[2025-02-22 14:47:25,875 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8112 +[2025-02-22 14:47:25,952 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7769 +[2025-02-22 14:47:26,832 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6448 +[2025-02-22 14:47:27,092 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.1974 +[2025-02-22 14:47:27,142 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7125 +[2025-02-22 14:47:27,252 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4087 +[2025-02-22 14:47:27,291 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5493 +[2025-02-22 14:47:27,408 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5509 +[2025-02-22 14:47:27,490 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7678 +[2025-02-22 14:47:27,628 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7798 +[2025-02-22 14:47:27,789 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7259 +[2025-02-22 14:47:28,111 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1261 +[2025-02-22 14:47:28,291 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6762 +[2025-02-22 14:47:28,348 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5525 +[2025-02-22 14:47:28,391 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8699 +[2025-02-22 14:47:28,661 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8213 +[2025-02-22 14:47:28,705 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7108 +[2025-02-22 14:47:28,752 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4639 +[2025-02-22 14:47:28,843 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3387 +[2025-02-22 14:47:28,979 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5895 +[2025-02-22 14:47:29,111 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2905 +[2025-02-22 14:47:29,199 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2304 +[2025-02-22 14:47:29,289 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2531 +[2025-02-22 14:47:29,446 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4675 +[2025-02-22 14:47:29,482 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5856 +[2025-02-22 14:47:29,593 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9053 +[2025-02-22 14:47:29,683 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9205 +[2025-02-22 14:47:29,723 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6696 +[2025-02-22 14:47:29,874 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.2089 +[2025-02-22 14:47:29,913 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6568 +[2025-02-22 14:47:30,152 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4335 +[2025-02-22 14:47:30,258 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3956 +[2025-02-22 14:47:30,350 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3934 +[2025-02-22 14:47:30,406 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6426 +[2025-02-22 14:47:30,592 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3212 +[2025-02-22 14:47:30,700 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.1226 +[2025-02-22 14:47:30,776 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1303 +[2025-02-22 14:47:30,922 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1799 +[2025-02-22 14:47:31,092 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7944 +[2025-02-22 14:47:31,189 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0758 +[2025-02-22 14:47:31,240 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7125 +[2025-02-22 14:47:31,291 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5602 +[2025-02-22 14:47:31,476 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.4890 +[2025-02-22 14:47:31,507 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4347 +[2025-02-22 14:47:31,557 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8839 +[2025-02-22 14:47:31,665 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7699 +[2025-02-22 14:47:31,854 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7074 +[2025-02-22 14:47:31,933 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1636 +[2025-02-22 14:47:32,099 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7534 +[2025-02-22 14:47:32,196 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6781 +[2025-02-22 14:47:48,089 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:47:48,089 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:47:48,089 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] cabinet : 0.2979 0.5388 0.7242 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] bed : 0.3202 0.7495 0.8879 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] chair : 0.7595 0.9138 0.9493 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] sofa : 0.3598 0.5905 0.8029 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] table : 0.4649 0.7156 0.8316 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] door : 0.2880 0.5150 0.6320 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] window : 0.2946 0.4893 0.7067 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] bookshelf : 0.2779 0.5816 0.7423 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] picture : 0.3679 0.5140 0.5912 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] counter : 0.0661 0.2527 0.6072 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] desk : 0.1291 0.4453 0.8574 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] curtain : 0.3642 0.5456 0.6457 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] refridgerator : 0.4610 0.6404 0.7086 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] shower curtain : 0.4331 0.5971 0.7322 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] toilet : 0.8914 1.0000 1.0000 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] sink : 0.4286 0.7168 0.8704 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] bathtub : 0.6704 0.7742 0.8710 +[2025-02-22 14:47:48,089 INFO evaluator.py line 547 2775932] otherfurniture : 0.4143 0.5908 0.6750 +[2025-02-22 14:47:48,089 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:47:48,089 INFO evaluator.py line 554 2775932] average : 0.4049 0.6206 0.7686 +[2025-02-22 14:47:48,089 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:47:48,089 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:47:48,124 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:47:48,131 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth +[2025-02-22 14:47:56,921 INFO hook.py line 109 2775932] Train: [100/100][50/800] Data 0.002 (0.003) Batch 0.149 (0.152) Remain 00:01:54 loss: -0.7221 Lr: 2.16710e-06 +[2025-02-22 14:48:03,986 INFO hook.py line 109 2775932] Train: [100/100][100/800] Data 0.003 (0.003) Batch 0.126 (0.147) Remain 00:01:42 loss: -0.8443 Lr: 1.97312e-06 +[2025-02-22 14:48:10,971 INFO hook.py line 109 2775932] Train: [100/100][150/800] Data 0.003 (0.003) Batch 0.129 (0.144) Remain 00:01:33 loss: -0.8158 Lr: 1.79196e-06 +[2025-02-22 14:48:18,079 INFO hook.py line 109 2775932] Train: [100/100][200/800] Data 0.003 (0.003) Batch 0.152 (0.144) Remain 00:01:26 loss: -0.7754 Lr: 1.62360e-06 +[2025-02-22 14:48:25,040 INFO hook.py line 109 2775932] Train: [100/100][250/800] Data 0.002 (0.003) Batch 0.120 (0.143) Remain 00:01:18 loss: -0.7992 Lr: 1.46805e-06 +[2025-02-22 14:48:32,087 INFO hook.py line 109 2775932] Train: [100/100][300/800] Data 0.002 (0.003) Batch 0.140 (0.143) Remain 00:01:11 loss: -0.8637 Lr: 1.32531e-06 +[2025-02-22 14:48:39,466 INFO hook.py line 109 2775932] Train: [100/100][350/800] Data 0.002 (0.003) Batch 0.146 (0.143) Remain 00:01:04 loss: -0.7376 Lr: 1.19539e-06 +[2025-02-22 14:48:46,613 INFO hook.py line 109 2775932] Train: [100/100][400/800] Data 0.003 (0.003) Batch 0.159 (0.143) Remain 00:00:57 loss: -0.7701 Lr: 1.07827e-06 +[2025-02-22 14:48:53,612 INFO hook.py line 109 2775932] Train: [100/100][450/800] Data 0.003 (0.003) Batch 0.148 (0.143) Remain 00:00:49 loss: -0.7851 Lr: 9.73971e-07 +[2025-02-22 14:49:00,787 INFO hook.py line 109 2775932] Train: [100/100][500/800] Data 0.003 (0.003) Batch 0.123 (0.143) Remain 00:00:42 loss: -0.8201 Lr: 8.82481e-07 +[2025-02-22 14:49:07,739 INFO hook.py line 109 2775932] Train: [100/100][550/800] Data 0.004 (0.003) Batch 0.146 (0.143) Remain 00:00:35 loss: -0.7646 Lr: 8.03804e-07 +[2025-02-22 14:49:15,140 INFO hook.py line 109 2775932] Train: [100/100][600/800] Data 0.005 (0.003) Batch 0.157 (0.143) Remain 00:00:28 loss: -0.7319 Lr: 7.37941e-07 +[2025-02-22 14:49:22,114 INFO hook.py line 109 2775932] Train: [100/100][650/800] Data 0.003 (0.003) Batch 0.133 (0.143) Remain 00:00:21 loss: -0.8054 Lr: 6.84891e-07 +[2025-02-22 14:49:28,980 INFO hook.py line 109 2775932] Train: [100/100][700/800] Data 0.004 (0.003) Batch 0.130 (0.142) Remain 00:00:14 loss: -0.7508 Lr: 6.44655e-07 +[2025-02-22 14:49:35,996 INFO hook.py line 109 2775932] Train: [100/100][750/800] Data 0.003 (0.003) Batch 0.148 (0.142) Remain 00:00:07 loss: -0.8376 Lr: 6.17655e-07 +[2025-02-22 14:49:42,794 INFO hook.py line 109 2775932] Train: [100/100][800/800] Data 0.001 (0.003) Batch 0.130 (0.142) Remain 00:00:00 loss: -0.7546 Lr: 6.02791e-07 +[2025-02-22 14:49:42,794 INFO misc.py line 135 2775932] Train result: loss: -0.7885 seg_loss: 0.0717 bias_l1_loss: 0.1151 bias_cosine_loss: -0.9753 +[2025-02-22 14:49:42,794 INFO evaluator.py line 558 2775932] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>> +[2025-02-22 14:49:50,080 INFO evaluator.py line 595 2775932] Test: [1/78] Loss -0.9014 +[2025-02-22 14:49:50,374 INFO evaluator.py line 595 2775932] Test: [2/78] Loss -0.7083 +[2025-02-22 14:49:50,448 INFO evaluator.py line 595 2775932] Test: [3/78] Loss -0.6829 +[2025-02-22 14:49:50,525 INFO evaluator.py line 595 2775932] Test: [4/78] Loss -0.6226 +[2025-02-22 14:49:50,595 INFO evaluator.py line 595 2775932] Test: [5/78] Loss -0.8027 +[2025-02-22 14:49:50,660 INFO evaluator.py line 595 2775932] Test: [6/78] Loss 1.5328 +[2025-02-22 14:49:50,962 INFO evaluator.py line 595 2775932] Test: [7/78] Loss -0.5467 +[2025-02-22 14:49:50,999 INFO evaluator.py line 595 2775932] Test: [8/78] Loss -0.6250 +[2025-02-22 14:49:51,147 INFO evaluator.py line 595 2775932] Test: [9/78] Loss -0.5510 +[2025-02-22 14:49:51,212 INFO evaluator.py line 595 2775932] Test: [10/78] Loss -0.0787 +[2025-02-22 14:49:51,520 INFO evaluator.py line 595 2775932] Test: [11/78] Loss 0.2596 +[2025-02-22 14:49:51,653 INFO evaluator.py line 595 2775932] Test: [12/78] Loss 0.1256 +[2025-02-22 14:49:51,757 INFO evaluator.py line 595 2775932] Test: [13/78] Loss -0.4016 +[2025-02-22 14:49:51,880 INFO evaluator.py line 595 2775932] Test: [14/78] Loss 1.6739 +[2025-02-22 14:49:51,974 INFO evaluator.py line 595 2775932] Test: [15/78] Loss 0.0771 +[2025-02-22 14:49:52,084 INFO evaluator.py line 595 2775932] Test: [16/78] Loss -0.7117 +[2025-02-22 14:49:52,234 INFO evaluator.py line 595 2775932] Test: [17/78] Loss -0.6564 +[2025-02-22 14:49:52,353 INFO evaluator.py line 595 2775932] Test: [18/78] Loss -0.3505 +[2025-02-22 14:49:52,513 INFO evaluator.py line 595 2775932] Test: [19/78] Loss -0.2037 +[2025-02-22 14:49:52,584 INFO evaluator.py line 595 2775932] Test: [20/78] Loss -0.0229 +[2025-02-22 14:49:52,762 INFO evaluator.py line 595 2775932] Test: [21/78] Loss -0.7618 +[2025-02-22 14:49:52,952 INFO evaluator.py line 595 2775932] Test: [22/78] Loss 0.3086 +[2025-02-22 14:49:53,040 INFO evaluator.py line 595 2775932] Test: [23/78] Loss 0.0749 +[2025-02-22 14:49:53,104 INFO evaluator.py line 595 2775932] Test: [24/78] Loss 0.1109 +[2025-02-22 14:49:53,189 INFO evaluator.py line 595 2775932] Test: [25/78] Loss -0.6122 +[2025-02-22 14:49:53,257 INFO evaluator.py line 595 2775932] Test: [26/78] Loss -0.7135 +[2025-02-22 14:49:53,421 INFO evaluator.py line 595 2775932] Test: [27/78] Loss 0.0934 +[2025-02-22 14:49:53,574 INFO evaluator.py line 595 2775932] Test: [28/78] Loss 0.6204 +[2025-02-22 14:49:53,665 INFO evaluator.py line 595 2775932] Test: [29/78] Loss -0.8094 +[2025-02-22 14:49:53,745 INFO evaluator.py line 595 2775932] Test: [30/78] Loss -0.7697 +[2025-02-22 14:49:54,687 INFO evaluator.py line 595 2775932] Test: [31/78] Loss -0.6442 +[2025-02-22 14:49:54,952 INFO evaluator.py line 595 2775932] Test: [32/78] Loss 0.2501 +[2025-02-22 14:49:54,994 INFO evaluator.py line 595 2775932] Test: [33/78] Loss -0.7258 +[2025-02-22 14:49:55,098 INFO evaluator.py line 595 2775932] Test: [34/78] Loss -0.4197 +[2025-02-22 14:49:55,135 INFO evaluator.py line 595 2775932] Test: [35/78] Loss -0.5257 +[2025-02-22 14:49:55,250 INFO evaluator.py line 595 2775932] Test: [36/78] Loss 0.5831 +[2025-02-22 14:49:55,314 INFO evaluator.py line 595 2775932] Test: [37/78] Loss -0.7657 +[2025-02-22 14:49:55,450 INFO evaluator.py line 595 2775932] Test: [38/78] Loss -0.7907 +[2025-02-22 14:49:55,605 INFO evaluator.py line 595 2775932] Test: [39/78] Loss 0.7021 +[2025-02-22 14:49:55,804 INFO evaluator.py line 595 2775932] Test: [40/78] Loss 1.1163 +[2025-02-22 14:49:55,987 INFO evaluator.py line 595 2775932] Test: [41/78] Loss 0.6663 +[2025-02-22 14:49:56,045 INFO evaluator.py line 595 2775932] Test: [42/78] Loss -0.5335 +[2025-02-22 14:49:56,086 INFO evaluator.py line 595 2775932] Test: [43/78] Loss -0.8638 +[2025-02-22 14:49:56,347 INFO evaluator.py line 595 2775932] Test: [44/78] Loss -0.8264 +[2025-02-22 14:49:56,392 INFO evaluator.py line 595 2775932] Test: [45/78] Loss -0.7045 +[2025-02-22 14:49:56,437 INFO evaluator.py line 595 2775932] Test: [46/78] Loss -0.4612 +[2025-02-22 14:49:56,527 INFO evaluator.py line 595 2775932] Test: [47/78] Loss 0.3392 +[2025-02-22 14:49:56,659 INFO evaluator.py line 595 2775932] Test: [48/78] Loss -0.5692 +[2025-02-22 14:49:56,788 INFO evaluator.py line 595 2775932] Test: [49/78] Loss -0.2850 +[2025-02-22 14:49:56,881 INFO evaluator.py line 595 2775932] Test: [50/78] Loss 0.2222 +[2025-02-22 14:49:56,988 INFO evaluator.py line 595 2775932] Test: [51/78] Loss -0.2609 +[2025-02-22 14:49:57,139 INFO evaluator.py line 595 2775932] Test: [52/78] Loss -0.4682 +[2025-02-22 14:49:57,175 INFO evaluator.py line 595 2775932] Test: [53/78] Loss -0.5865 +[2025-02-22 14:49:57,282 INFO evaluator.py line 595 2775932] Test: [54/78] Loss 1.9222 +[2025-02-22 14:49:57,371 INFO evaluator.py line 595 2775932] Test: [55/78] Loss -0.9214 +[2025-02-22 14:49:57,412 INFO evaluator.py line 595 2775932] Test: [56/78] Loss -0.6697 +[2025-02-22 14:49:57,555 INFO evaluator.py line 595 2775932] Test: [57/78] Loss -0.1952 +[2025-02-22 14:49:57,593 INFO evaluator.py line 595 2775932] Test: [58/78] Loss -0.6523 +[2025-02-22 14:49:57,811 INFO evaluator.py line 595 2775932] Test: [59/78] Loss -0.4382 +[2025-02-22 14:49:57,916 INFO evaluator.py line 595 2775932] Test: [60/78] Loss -0.3875 +[2025-02-22 14:49:58,007 INFO evaluator.py line 595 2775932] Test: [61/78] Loss 0.3835 +[2025-02-22 14:49:58,063 INFO evaluator.py line 595 2775932] Test: [62/78] Loss -0.6369 +[2025-02-22 14:49:58,242 INFO evaluator.py line 595 2775932] Test: [63/78] Loss -0.3163 +[2025-02-22 14:49:58,348 INFO evaluator.py line 595 2775932] Test: [64/78] Loss -0.0891 +[2025-02-22 14:49:58,428 INFO evaluator.py line 595 2775932] Test: [65/78] Loss -0.1371 +[2025-02-22 14:49:58,576 INFO evaluator.py line 595 2775932] Test: [66/78] Loss -0.1884 +[2025-02-22 14:49:58,741 INFO evaluator.py line 595 2775932] Test: [67/78] Loss -0.7992 +[2025-02-22 14:49:58,833 INFO evaluator.py line 595 2775932] Test: [68/78] Loss -0.0310 +[2025-02-22 14:49:58,882 INFO evaluator.py line 595 2775932] Test: [69/78] Loss -0.7135 +[2025-02-22 14:49:58,931 INFO evaluator.py line 595 2775932] Test: [70/78] Loss -0.5497 +[2025-02-22 14:49:59,102 INFO evaluator.py line 595 2775932] Test: [71/78] Loss -0.5152 +[2025-02-22 14:49:59,130 INFO evaluator.py line 595 2775932] Test: [72/78] Loss -0.4493 +[2025-02-22 14:49:59,178 INFO evaluator.py line 595 2775932] Test: [73/78] Loss -0.8896 +[2025-02-22 14:49:59,285 INFO evaluator.py line 595 2775932] Test: [74/78] Loss 1.7750 +[2025-02-22 14:49:59,472 INFO evaluator.py line 595 2775932] Test: [75/78] Loss -0.7001 +[2025-02-22 14:49:59,549 INFO evaluator.py line 595 2775932] Test: [76/78] Loss 0.1442 +[2025-02-22 14:49:59,710 INFO evaluator.py line 595 2775932] Test: [77/78] Loss -0.7541 +[2025-02-22 14:49:59,810 INFO evaluator.py line 595 2775932] Test: [78/78] Loss -0.6595 +[2025-02-22 14:50:14,462 INFO evaluator.py line 530 2775932] ################################################ +[2025-02-22 14:50:14,463 INFO evaluator.py line 536 2775932] what : AP AP_50% AP_25% +[2025-02-22 14:50:14,463 INFO evaluator.py line 537 2775932] ################################################ +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] cabinet : 0.2887 0.5362 0.7194 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] bed : 0.3088 0.7210 0.8864 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] chair : 0.7537 0.9064 0.9438 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] sofa : 0.3551 0.5857 0.7983 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] table : 0.4693 0.7179 0.8355 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] door : 0.2904 0.5131 0.6279 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] window : 0.2902 0.4981 0.6956 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] bookshelf : 0.2700 0.5791 0.7417 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] picture : 0.3666 0.5000 0.5811 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] counter : 0.0586 0.2555 0.6150 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] desk : 0.1311 0.4322 0.8444 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] curtain : 0.3752 0.5628 0.6489 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] refridgerator : 0.4589 0.5919 0.6748 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] shower curtain : 0.4413 0.6188 0.7529 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] toilet : 0.8874 1.0000 1.0000 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] sink : 0.4427 0.7353 0.8658 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] bathtub : 0.6688 0.7742 0.8710 +[2025-02-22 14:50:14,463 INFO evaluator.py line 547 2775932] otherfurniture : 0.4076 0.5739 0.6697 +[2025-02-22 14:50:14,463 INFO evaluator.py line 549 2775932] ------------------------------------------------ +[2025-02-22 14:50:14,463 INFO evaluator.py line 554 2775932] average : 0.4036 0.6168 0.7651 +[2025-02-22 14:50:14,463 INFO evaluator.py line 555 2775932] ################################################ +[2025-02-22 14:50:14,463 INFO evaluator.py line 614 2775932] <<<<<<<<<<<<<<<<< End Evaluation <<<<<<<<<<<<<<<<< +[2025-02-22 14:50:14,490 INFO misc.py line 164 2775932] Currently Best AP50: 0.6271 +[2025-02-22 14:50:14,498 INFO misc.py line 173 2775932] Saving checkpoint to: exp/scannet/insseg-pg-spunet-base-m5-lr6e-3-s1/model/model_last.pth