Upload MaskRCNNForObjectDetection

config.json

@@ -0,0 +1,223 @@
+{
+  "_commit_hash": null,
+  "anchor_generator_ratios": [
+    0.5,
+    1.0,
+    2.0
+  ],
+  "anchor_generator_scales": [
+    8
+  ],
+  "anchor_generator_strides": [
+    4,
+    8,
+    16,
+    32,
+    64
+  ],
+  "architectures": [
+    "MaskRCNNForObjectDetection"
+  ],
+  "backbone_config": {
+    "_out_features": [
+      "stage4",
+      "stage6",
+      "stage8",
+      "stage12"
+    ],
+    "_out_indices": [
+      4,
+      6,
+      8,
+      12
+    ],
+    "add_fpn": true,
+    "attention_probs_dropout_prob": 0.0,
+    "auxiliary_channels": 256,
+    "auxiliary_concat_input": false,
+    "auxiliary_loss_weight": 0.4,
+    "auxiliary_num_convs": 1,
+    "drop_path_rate": 0.1,
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_scale_init_value": 0.1,
+    "model_type": "beit",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "pool_scales": [
+      1,
+      2,
+      3,
+      6
+    ],
+    "reshape_hidden_states": true,
+    "semantic_loss_ignore_index": 255,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4",
+      "stage5",
+      "stage6",
+      "stage7",
+      "stage8",
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12"
+    ],
+    "use_absolute_position_embeddings": true,
+    "use_auxiliary_head": true,
+    "use_mask_token": false,
+    "use_mean_pooling": true,
+    "use_relative_position_bias": false,
+    "use_shared_relative_position_bias": false,
+    "vocab_size": 8192
+  },
+  "bbox_head_bbox_coder_target_means": [
+    0.0,
+    0.0,
+    0.0,
+    0.0
+  ],
+  "bbox_head_bbox_coder_target_stds": [
+    0.1,
+    0.1,
+    0.2,
+    0.2
+  ],
+  "bbox_head_fc_out_channels": 1024,
+  "bbox_head_in_channels": 256,
+  "bbox_head_num_shared_fcs": 2,
+  "bbox_head_reg_class_agnostic": false,
+  "bbox_head_reg_decoded_bbox": false,
+  "bbox_head_roi_feat_size": 7,
+  "bbox_roi_extractor_featmap_strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "bbox_roi_extractor_out_channels": 256,
+  "bbox_roi_extractor_roi_layer": {
+    "output_size": 7,
+    "sampling_ratio": 0,
+    "type": "RoIAlign"
+  },
+  "fpn_num_outputs": 5,
+  "fpn_out_channels": 256,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "mask_head_conv_out_channels": 256,
+  "mask_head_in_channels": 256,
+  "mask_head_num_convs": 4,
+  "mask_roi_extractor_featmap_strides": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "mask_roi_extractor_out_channels": 256,
+  "mask_roi_extractor_roi_layer": {
+    "output_size": 14,
+    "sampling_ratio": 0,
+    "type": "RoIAlign"
+  },
+  "model_type": "maskrcnn",
+  "rcnn_assigner_ignore_iof_thr": -1,
+  "rcnn_assigner_match_low_quality": true,
+  "rcnn_assigner_min_pos_iou": 0.5,
+  "rcnn_assigner_neg_iou_thr": 0.5,
+  "rcnn_assigner_pos_iou_thr": 0.5,
+  "rcnn_sampler_add_gt_as_proposals": true,
+  "rcnn_sampler_num": 512,
+  "rcnn_sampler_num_samples_upper_bound": -1,
+  "rcnn_sampler_pos_fraction": 0.25,
+  "rcnn_test_cfg": {
+    "mask_thr_binary": 0.5,
+    "max_per_img": 100,
+    "nms": {
+      "iou_threshold": 0.5,
+      "type": "nms"
+    },
+    "score_thr": 0.05
+  },
+  "rcnn_train_cfg": {
+    "debug": false,
+    "mask_size": 28,
+    "pos_weight": -1
+  },
+  "rpn_assigner_ignore_iof_thr": -1,
+  "rpn_assigner_match_low_quality": true,
+  "rpn_assigner_min_pos_iou": 0.3,
+  "rpn_assigner_neg_iou_thr": 0.3,
+  "rpn_assigner_pos_iou_thr": 0.7,
+  "rpn_bbox_coder_target_means": [
+    0.0,
+    0.0,
+    0.0,
+    0.0
+  ],
+  "rpn_bbox_coder_target_stds": [
+    1.0,
+    1.0,
+    1.0,
+    1.0
+  ],
+  "rpn_feat_channels": 256,
+  "rpn_in_channels": 256,
+  "rpn_loss_bbox": {
+    "loss_weight": 1.0,
+    "type": "L1Loss"
+  },
+  "rpn_loss_cls": {
+    "loss_weight": 1.0,
+    "type": "CrossEntropyLoss",
+    "use_sigmoid": true
+  },
+  "rpn_proposal": {
+    "max_per_img": 1000,
+    "min_bbox_size": 0,
+    "nms": {
+      "iou_threshold": 0.7,
+      "type": "nms"
+    },
+    "nms_pre": 2000
+  },
+  "rpn_sampler_add_gt_as_proposals": false,
+  "rpn_sampler_num": 256,
+  "rpn_sampler_num_samples_upper_bound": -1,
+  "rpn_sampler_pos_fraction": 0.5,
+  "rpn_test_cfg": {
+    "max_per_img": 1000,
+    "min_bbox_size": 0,
+    "nms": {
+      "iou_threshold": 0.7,
+      "type": "nms"
+    },
+    "nms_pre": 1000
+  },
+  "rpn_train_cfg": {
+    "allowed_border": -1,
+    "debug": false,
+    "pos_weight": -1
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a3b5ede3345fbadff18aa41991d5ecba874ab3b5195a14188a1bbdc574f030
+size 452795617