Training in progress, epoch 1

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "jozhang97/deta-swin-large",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetaForObjectDetection"
+  ],
+  "assign_first_stage": true,
+  "assign_second_stage": true,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "attention_probs_dropout_prob": 0.0,
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
+    "drop_path_rate": 0.1,
+    "embed_dim": 192,
+    "encoder_stride": 32,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1536,
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "num_heads": [
+      6,
+      12,
+      24,
+      48
+    ],
+    "num_layers": 4,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ],
+    "patch_size": 4,
+    "path_norm": true,
+    "qkv_bias": true,
+    "use_absolute_embeddings": false,
+    "window_size": 12
+  },
+  "backbone_kwargs": null,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "dice_loss_coefficient": 1,
+  "disable_custom_kernels": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "Bus",
+    "1": "Bike",
+    "2": "Car",
+    "3": "Pedestrian",
+    "4": "Truck"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Bike": 1,
+    "Bus": 0,
+    "Car": 2,
+    "Pedestrian": 3,
+    "Truck": 4
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 2048,
+  "model_type": "deta",
+  "num_feature_levels": 5,
+  "num_queries": 900,
+  "position_embedding_type": "sine",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "two_stage": true,
+  "two_stage_num_proposals": 900,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false,
+  "with_box_refine": true
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetaImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": {
+    "height": 960,
+    "width": 960
+  },
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_height": 960,
+    "max_width": 960
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124b5ea89688ced0886df6e69d18185abffd2b7088ede1d0ba43fdd2ac3549bf
+size 878752042

runs/Feb15_07-46-46_mcity-rtx-4090/events.out.tfevents.1739623607.mcity-rtx-4090.1139582.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82b3d967bf079c422108302ab48c040bf7e0dcc8358386e45bfde6d65e017b5
+size 9259

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a021612c202d5ea3fa63c2297e517a364d7acf76d24629130f841b566a64b793
+size 5560