{ "architectures": [ "OneFormerForUniversalSegmentation" ], "backbone_config": { "attention_probs_dropout_prob": 0.0, "depths": [ 3, 4, 18, 5 ], "dilations": [ [ 1, 20, 1 ], [ 1, 5, 1, 10 ], [ 1, 2, 1, 3, 1, 4, 1, 5, 1, 2, 1, 3, 1, 4, 1, 5, 1, 5 ], [ 1, 2, 1, 2, 1 ] ], "drop_path_rate": 0.3, "embed_dim": 192, "encoder_stride": 32, "feature_channels": [ 192, 384, 768, 1536 ], "hidden_act": "gelu", "hidden_dropout_prob": 0, "kernel_size": 11, "layer_scale_init_value": 0.0, "mlp_ratio": 2.0, "num_channels": 3, "num_heads": [ 6, 12, 24, 48 ], "patch_size": 4, "qkv_bias": true, "strides": [ 4, 8, 16, 32 ] }, "decoder_config": { "common_stride": 4, "conv_dim": 256, "decoder_layers": 10, "dim_feedforward": 2048, "dropout": 0.1, "encoder_feedforward_dim": 1024, "encoder_layers": 6, "enforce_input_proj": false, "hidden_dim": 256, "mask_dim": 256, "norm": "GN", "num_heads": 8, "pre_norm": false, "query_dec_layers": 2, "use_task_norm": true }, "general_config": { "backbone_type": "dinat", "class_weight": 2.0, "contrastive_temperature": 0.07, "contrastive_weight": 0.5, "deep_supervision": true, "dice_weight": 5.0, "ignore_value": 255, "importance_sample_ratio": 0.75, "init_std": 0.02, "init_xavier_std": 1.0, "is_train": false, "layer_norm_eps": 1e-05, "mask_weight": 5.0, "no_object_weight": 0.1, "num_classes": 133, "num_queries": 150, "output_auxiliary_logits": true, "oversample_ratio": 3.0, "train_num_points": 12544, "use_auxiliary_loss": true }, "hidden_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 }, "model_type": "oneformer", "num_attention_heads": 8, "num_hidden_layers": 10, "output_attentions": true, "output_hidden_states": true, "text_encoder_config": { "max_seq_len": 77, "task_seq_len": 77, "text_encoder_context_length": 77, "text_encoder_n_ctx": 16, "text_encoder_num_layers": 6, "text_encoder_proj_layers": 2, "text_encoder_vocab_size": 49408, "text_encoder_width": 256 }, "torch_dtype": "float32", "transformers_version": "4.25.0.dev0" }