|
{ |
|
"architectures": [ |
|
"MaskFormerForInstanceSegmentation" |
|
], |
|
"backbone_config": { |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"architectures": null, |
|
"attention_probs_dropout_prob": 0.0, |
|
"bad_words_ids": 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, |
|
"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, |
|
"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, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"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": "4.18.0.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": { |
|
"_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", |
|
"bad_words_ids": null, |
|
"bbox_cost": 5, |
|
"bbox_loss_coefficient": 5, |
|
"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, |
|
"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_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, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"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": "4.18.0.dev0", |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"dice_weight": 1.0, |
|
"fpn_feature_size": 256, |
|
"id2label": { |
|
"0": "person", |
|
"1": "bicycle", |
|
"2": "car", |
|
"3": "motorcycle", |
|
"4": "airplane", |
|
"5": "bus", |
|
"6": "train", |
|
"7": "truck", |
|
"8": "boat", |
|
"9": "traffic light", |
|
"10": "fire hydrant", |
|
"11": "stop sign", |
|
"12": "parking meter", |
|
"13": "bench", |
|
"14": "bird", |
|
"15": "cat", |
|
"16": "dog", |
|
"17": "horse", |
|
"18": "sheep", |
|
"19": "cow", |
|
"20": "elephant", |
|
"21": "bear", |
|
"22": "zebra", |
|
"23": "giraffe", |
|
"24": "backpack", |
|
"25": "umbrella", |
|
"26": "handbag", |
|
"27": "tie", |
|
"28": "suitcase", |
|
"29": "frisbee", |
|
"30": "skis", |
|
"31": "snowboard", |
|
"32": "sports ball", |
|
"33": "kite", |
|
"34": "baseball bat", |
|
"35": "baseball glove", |
|
"36": "skateboard", |
|
"37": "surfboard", |
|
"38": "tennis racket", |
|
"39": "bottle", |
|
"40": "wine glass", |
|
"41": "cup", |
|
"42": "fork", |
|
"43": "knife", |
|
"44": "spoon", |
|
"45": "bowl", |
|
"46": "banana", |
|
"47": "apple", |
|
"48": "sandwich", |
|
"49": "orange", |
|
"50": "broccoli", |
|
"51": "carrot", |
|
"52": "hot dog", |
|
"53": "pizza", |
|
"54": "donut", |
|
"55": "cake", |
|
"56": "chair", |
|
"57": "couch", |
|
"58": "potted plant", |
|
"59": "bed", |
|
"60": "dining table", |
|
"61": "toilet", |
|
"62": "tv", |
|
"63": "laptop", |
|
"64": "mouse", |
|
"65": "remote", |
|
"66": "keyboard", |
|
"67": "cell phone", |
|
"68": "microwave", |
|
"69": "oven", |
|
"70": "toaster", |
|
"71": "sink", |
|
"72": "refrigerator", |
|
"73": "book", |
|
"74": "clock", |
|
"75": "vase", |
|
"76": "scissors", |
|
"77": "teddy bear", |
|
"78": "hair drier", |
|
"79": "toothbrush", |
|
"80": "banner", |
|
"81": "blanket", |
|
"82": "bridge", |
|
"83": "cardboard", |
|
"84": "counter", |
|
"85": "curtain", |
|
"86": "door-stuff", |
|
"87": "floor-wood", |
|
"88": "flower", |
|
"89": "fruit", |
|
"90": "gravel", |
|
"91": "house", |
|
"92": "light", |
|
"93": "mirror-stuff", |
|
"94": "net", |
|
"95": "pillow", |
|
"96": "platform", |
|
"97": "playingfield", |
|
"98": "railroad", |
|
"99": "river", |
|
"100": "road", |
|
"101": "roof", |
|
"102": "sand", |
|
"103": "sea", |
|
"104": "shelf", |
|
"105": "snow", |
|
"106": "stairs", |
|
"107": "tent", |
|
"108": "towel", |
|
"109": "wall-brick", |
|
"110": "wall-stone", |
|
"111": "wall-tile", |
|
"112": "wall-wood", |
|
"113": "water-other", |
|
"114": "window-blind", |
|
"115": "window-other", |
|
"116": "tree-merged", |
|
"117": "fence-merged", |
|
"118": "ceiling-merged", |
|
"119": "sky-other-merged", |
|
"120": "cabinet-merged", |
|
"121": "table-merged", |
|
"122": "floor-other-merged", |
|
"123": "pavement-merged", |
|
"124": "mountain-merged", |
|
"125": "grass-merged", |
|
"126": "dirt-merged", |
|
"127": "paper-merged", |
|
"128": "food-other-merged", |
|
"129": "building-other-merged", |
|
"130": "rock-merged", |
|
"131": "wall-other-merged", |
|
"132": "rug-merged" |
|
}, |
|
"init_std": 0.02, |
|
"init_xavier_std": 1.0, |
|
"label2id": { |
|
"airplane": 4, |
|
"apple": 47, |
|
"backpack": 24, |
|
"banana": 46, |
|
"banner": 80, |
|
"baseball bat": 34, |
|
"baseball glove": 35, |
|
"bear": 21, |
|
"bed": 59, |
|
"bench": 13, |
|
"bicycle": 1, |
|
"bird": 14, |
|
"blanket": 81, |
|
"boat": 8, |
|
"book": 73, |
|
"bottle": 39, |
|
"bowl": 45, |
|
"bridge": 82, |
|
"broccoli": 50, |
|
"building-other-merged": 129, |
|
"bus": 5, |
|
"cabinet-merged": 120, |
|
"cake": 55, |
|
"car": 2, |
|
"cardboard": 83, |
|
"carrot": 51, |
|
"cat": 15, |
|
"ceiling-merged": 118, |
|
"cell phone": 67, |
|
"chair": 56, |
|
"clock": 74, |
|
"couch": 57, |
|
"counter": 84, |
|
"cow": 19, |
|
"cup": 41, |
|
"curtain": 85, |
|
"dining table": 60, |
|
"dirt-merged": 126, |
|
"dog": 16, |
|
"donut": 54, |
|
"door-stuff": 86, |
|
"elephant": 20, |
|
"fence-merged": 117, |
|
"fire hydrant": 10, |
|
"floor-other-merged": 122, |
|
"floor-wood": 87, |
|
"flower": 88, |
|
"food-other-merged": 128, |
|
"fork": 42, |
|
"frisbee": 29, |
|
"fruit": 89, |
|
"giraffe": 23, |
|
"grass-merged": 125, |
|
"gravel": 90, |
|
"hair drier": 78, |
|
"handbag": 26, |
|
"horse": 17, |
|
"hot dog": 52, |
|
"house": 91, |
|
"keyboard": 66, |
|
"kite": 33, |
|
"knife": 43, |
|
"laptop": 63, |
|
"light": 92, |
|
"microwave": 68, |
|
"mirror-stuff": 93, |
|
"motorcycle": 3, |
|
"mountain-merged": 124, |
|
"mouse": 64, |
|
"net": 94, |
|
"orange": 49, |
|
"oven": 69, |
|
"paper-merged": 127, |
|
"parking meter": 12, |
|
"pavement-merged": 123, |
|
"person": 0, |
|
"pillow": 95, |
|
"pizza": 53, |
|
"platform": 96, |
|
"playingfield": 97, |
|
"potted plant": 58, |
|
"railroad": 98, |
|
"refrigerator": 72, |
|
"remote": 65, |
|
"river": 99, |
|
"road": 100, |
|
"rock-merged": 130, |
|
"roof": 101, |
|
"rug-merged": 132, |
|
"sand": 102, |
|
"sandwich": 48, |
|
"scissors": 76, |
|
"sea": 103, |
|
"sheep": 18, |
|
"shelf": 104, |
|
"sink": 71, |
|
"skateboard": 36, |
|
"skis": 30, |
|
"sky-other-merged": 119, |
|
"snow": 105, |
|
"snowboard": 31, |
|
"spoon": 44, |
|
"sports ball": 32, |
|
"stairs": 106, |
|
"stop sign": 11, |
|
"suitcase": 28, |
|
"surfboard": 37, |
|
"table-merged": 121, |
|
"teddy bear": 77, |
|
"tennis racket": 38, |
|
"tent": 107, |
|
"tie": 27, |
|
"toaster": 70, |
|
"toilet": 61, |
|
"toothbrush": 79, |
|
"towel": 108, |
|
"traffic light": 9, |
|
"train": 6, |
|
"tree-merged": 116, |
|
"truck": 7, |
|
"tv": 62, |
|
"umbrella": 25, |
|
"vase": 75, |
|
"wall-brick": 109, |
|
"wall-other-merged": 131, |
|
"wall-stone": 110, |
|
"wall-tile": 111, |
|
"wall-wood": 112, |
|
"water-other": 113, |
|
"window-blind": 114, |
|
"window-other": 115, |
|
"wine glass": 40, |
|
"zebra": 22 |
|
}, |
|
"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, |
|
"torch_dtype": "float32", |
|
"transformers_version": null, |
|
"use_auxiliary_loss": false |
|
} |
|
|