Upload MaskFormerForInstanceSegmentation

config.json

@@ -0,0 +1,401 @@
+{
+  "_commit_hash": "b569351e060953d37fd7dfb8b16ab83c360a13d6",
+  "_name_or_path": "facebook/maskformer-swin-base-ade",
+  "architectures": [
+    "MaskFormerForInstanceSegmentation"
+  ],
+  "backbone_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.3,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "out_features": [
+      "stage4"
+    ],
+    "out_indices": [
+      4
+    ],
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "pretrain_img_size": 384,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.31.0.dev0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 12
+  },
+  "ce_weight": 1.0,
+  "cross_entropy_weight": 1.0,
+  "decoder_config": {
+    "_commit_hash": null,
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "auxiliary_loss": false,
+    "backbone": "resnet50",
+    "backbone_config": null,
+    "bad_words_ids": null,
+    "bbox_cost": 5,
+    "bbox_loss_coefficient": 5,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "class_cost": 1,
+    "cross_attention_hidden_size": null,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 2048,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": null,
+    "dice_loss_coefficient": 1,
+    "dilation": false,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 8,
+    "encoder_ffn_dim": 2048,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_coefficient": 0.1,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "giou_cost": 2,
+    "giou_loss_coefficient": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "init_xavier_std": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "mask_loss_coefficient": 1,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "detr",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 6,
+    "num_queries": 100,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "position_embedding_type": "sine",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.17.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_pretrained_backbone": true,
+    "use_timm_backbone": true
+  },
+  "dice_weight": 1.0,
+  "fpn_feature_size": 256,
+  "id2label": {
+    "0": "background",
+    "1": "column",
+    "2": "slab",
+    "3": "beam",
+    "4": "pile",
+    "5": "stairs",
+    "6": "cwall",
+    "7": "column_end",
+    "8": "stripfooting",
+    "9": "edgefooting",
+    "10": "cornerfooting",
+    "11": "concentricfooting",
+    "12": "circ_column",
+    "13": "cantileverfooting"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "label2id": {
+    "animal": 126,
+    "arcade machine": 78,
+    "armchair": 30,
+    "awning, sunshade, sunblind": 86,
+    "bag": 115,
+    "ball": 119,
+    "bannister, banister, balustrade, balusters, handrail": 95,
+    "bar": 77,
+    "barrel, cask": 111,
+    "base, pedestal, stand": 40,
+    "basket, handbasket": 112,
+    "bed": 7,
+    "bench": 69,
+    "bicycle": 127,
+    "blanket, cover": 131,
+    "blind, screen": 63,
+    "boat": 76,
+    "book": 67,
+    "bookcase": 62,
+    "booth": 88,
+    "bottle": 98,
+    "box": 41,
+    "bridge, span": 61,
+    "buffet, counter, sideboard": 99,
+    "building": 1,
+    "bulletin board": 144,
+    "bus": 80,
+    "cabinet": 10,
+    "canopy": 106,
+    "car": 20,
+    "case, display case, showcase, vitrine": 55,
+    "ceiling": 5,
+    "chair": 19,
+    "chandelier": 85,
+    "chest of drawers, chest, bureau, dresser": 44,
+    "clock": 148,
+    "clothes": 92,
+    "coffee table": 64,
+    "column, pillar": 42,
+    "computer": 74,
+    "conveyer belt, conveyor belt, conveyer, conveyor, transporter": 105,
+    "counter": 45,
+    "countertop": 70,
+    "cradle": 117,
+    "crt screen": 141,
+    "curtain": 18,
+    "cushion": 39,
+    "desk": 33,
+    "dirt track": 91,
+    "dishwasher": 129,
+    "door": 14,
+    "earth, ground": 13,
+    "escalator, moving staircase, moving stairway": 96,
+    "falls": 113,
+    "fan": 139,
+    "fence": 32,
+    "field": 29,
+    "fireplace": 49,
+    "flag": 149,
+    "floor": 3,
+    "flower": 66,
+    "food, solid food": 120,
+    "fountain": 104,
+    "glass, drinking glass": 147,
+    "grandstand, covered stand": 51,
+    "grass": 9,
+    "hill": 68,
+    "hood, exhaust hood": 133,
+    "house": 25,
+    "hovel, hut, hutch, shack, shanty": 79,
+    "kitchen island": 73,
+    "lake": 128,
+    "lamp": 36,
+    "land, ground, soil": 94,
+    "light": 82,
+    "microwave": 124,
+    "minibike, motorbike": 116,
+    "mirror": 27,
+    "monitor": 143,
+    "mountain, mount": 16,
+    "ottoman, pouf, pouffe, puff, hassock": 97,
+    "oven": 118,
+    "painting, picture": 22,
+    "palm, palm tree": 72,
+    "path": 52,
+    "person": 12,
+    "pier": 140,
+    "pillow": 57,
+    "plane": 90,
+    "plant": 17,
+    "plate": 142,
+    "plaything, toy": 108,
+    "pole": 93,
+    "pool": 109,
+    "pool table, billiard table, snooker table": 56,
+    "poster, posting, placard, notice, bill, card": 100,
+    "pot": 125,
+    "radiator": 146,
+    "rail": 38,
+    "refrigerator, icebox": 50,
+    "river": 60,
+    "road, route": 6,
+    "rock, stone": 34,
+    "rug": 28,
+    "runway": 54,
+    "sand": 46,
+    "sconce": 134,
+    "screen": 130,
+    "screen door, screen": 58,
+    "sculpture": 132,
+    "sea": 26,
+    "seat": 31,
+    "shelf": 24,
+    "ship": 103,
+    "shower": 145,
+    "sidewalk, pavement": 11,
+    "signboard, sign": 43,
+    "sink": 47,
+    "sky": 2,
+    "skyscraper": 48,
+    "sofa": 23,
+    "stage": 101,
+    "stairs": 53,
+    "stairway, staircase": 59,
+    "step, stair": 121,
+    "stool": 110,
+    "stove": 71,
+    "street lamp": 87,
+    "swivel chair": 75,
+    "table": 15,
+    "tank, storage tank": 122,
+    "tent": 114,
+    "toilet, can, commode, crapper, pot, potty, stool, throne": 65,
+    "towel": 81,
+    "tower": 84,
+    "trade name": 123,
+    "traffic light": 136,
+    "trash can": 138,
+    "tray": 137,
+    "tree": 4,
+    "truck": 83,
+    "tub": 37,
+    "tv": 89,
+    "van": 102,
+    "vase": 135,
+    "wall": 0,
+    "wardrobe, closet, press": 35,
+    "washer, automatic washer, washing machine": 107,
+    "water": 21,
+    "window ": 8
+  },
+  "mask_feature_size": 256,
+  "mask_weight": 20.0,
+  "model_type": "maskformer",
+  "no_object_weight": 0.1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "output_auxiliary_logits": null,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_auxiliary_loss": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781b4f9a55c6d457b37a3442e915fe11e9667ac3f100f451bbca0b5be2a9c79a
+size 411411821