{ "_commit_hash": "b569351e060953d37fd7dfb8b16ab83c360a13d6", "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": "4.30.2", "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": "bed", "1": "windowpane", "2": "cabinet", "3": "person", "4": "door", "5": "table", "6": "curtain", "7": "chair", "8": "car", "9": "painting", "10": "sofa", "11": "shelf", "12": "mirror", "13": "armchair", "14": "seat", "15": "fence", "16": "desk", "17": "wardrobe", "18": "lamp", "19": "bathtub", "20": "railing", "21": "cushion", "22": "box", "23": "column", "24": "signboard", "25": "chest of drawers", "26": "counter", "27": "sink", "28": "fireplace", "29": "refrigerator", "30": "stairs", "31": "case", "32": "pool table", "33": "pillow", "34": "screen door", "35": "bookcase", "36": "coffee table", "37": "toilet", "38": "flower", "39": "book", "40": "bench", "41": "countertop", "42": "stove", "43": "palm", "44": "kitchen island", "45": "computer", "46": "swivel chair", "47": "boat", "48": "arcade machine", "49": "bus", "50": "towel", "51": "light", "52": "truck", "53": "chandelier", "54": "awning", "55": "streetlight", "56": "booth", "57": "television receiver", "58": "airplane", "59": "apparel", "60": "pole", "61": "bannister", "62": "ottoman", "63": "bottle", "64": "van", "65": "ship", "66": "fountain", "67": "washer", "68": "plaything", "69": "stool", "70": "barrel", "71": "basket", "72": "bag", "73": "minibike", "74": "oven", "75": "ball", "76": "food", "77": "step", "78": "trade name", "79": "microwave", "80": "pot", "81": "animal", "82": "bicycle", "83": "dishwasher", "84": "screen", "85": "sculpture", "86": "hood", "87": "sconce", "88": "vase", "89": "traffic light", "90": "tray", "91": "ashcan", "92": "fan", "93": "plate", "94": "monitor", "95": "bulletin board", "96": "radiator", "97": "glass", "98": "clock", "99": "flag" }, "init_std": 0.02, "init_xavier_std": 1.0, "label2id": { "airplane": 58, "animal": 81, "apparel": 59, "arcade machine": 48, "armchair": 13, "ashcan": 91, "awning": 54, "bag": 72, "ball": 75, "bannister": 61, "barrel": 70, "basket": 71, "bathtub": 19, "bed": 0, "bench": 40, "bicycle": 82, "boat": 47, "book": 39, "bookcase": 35, "booth": 56, "bottle": 63, "box": 22, "bulletin board": 95, "bus": 49, "cabinet": 2, "car": 8, "case": 31, "chair": 7, "chandelier": 53, "chest of drawers": 25, "clock": 98, "coffee table": 36, "column": 23, "computer": 45, "counter": 26, "countertop": 41, "curtain": 6, "cushion": 21, "desk": 16, "dishwasher": 83, "door": 4, "fan": 92, "fence": 15, "fireplace": 28, "flag": 99, "flower": 38, "food": 76, "fountain": 66, "glass": 97, "hood": 86, "kitchen island": 44, "lamp": 18, "light": 51, "microwave": 79, "minibike": 73, "mirror": 12, "monitor": 94, "ottoman": 62, "oven": 74, "painting": 9, "palm": 43, "person": 3, "pillow": 33, "plate": 93, "plaything": 68, "pole": 60, "pool table": 32, "pot": 80, "radiator": 96, "railing": 20, "refrigerator": 29, "sconce": 87, "screen": 84, "screen door": 34, "sculpture": 85, "seat": 14, "shelf": 11, "ship": 65, "signboard": 24, "sink": 27, "sofa": 10, "stairs": 30, "step": 77, "stool": 69, "stove": 42, "streetlight": 55, "swivel chair": 46, "table": 5, "television receiver": 57, "toilet": 37, "towel": 50, "trade name": 78, "traffic light": 89, "tray": 90, "truck": 52, "van": 64, "vase": 88, "wardrobe": 17, "washer": 67, "windowpane": 1 }, "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 }