{ "_name_or_path": "facebook/detr-resnet-50", "activation_dropout": 0.0, "activation_function": "relu", "architectures": [ "DetrForObjectDetection" ], "attention_dropout": 0.0, "auxiliary_loss": false, "backbone": "resnet50", "backbone_config": null, "backbone_kwargs": { "in_chans": 3, "out_indices": [ 1, 2, 3, 4 ] }, "bbox_cost": 5, "bbox_loss_coefficient": 5, "class_cost": 1, "classifier_dropout": 0.0, "d_model": 256, "decoder_attention_heads": 8, "decoder_ffn_dim": 2048, "decoder_layerdrop": 0.0, "decoder_layers": 6, "dice_loss_coefficient": 1, "dilation": false, "dropout": 0.1, "encoder_attention_heads": 8, "encoder_ffn_dim": 2048, "encoder_layerdrop": 0.0, "encoder_layers": 6, "eos_coefficient": 0.1, "giou_cost": 2, "giou_loss_coefficient": 2, "id2label": { "0": "[PAD]", "1": "[UNK]", "2": "[CLS]", "3": "[SEP]", "4": "[MASK]", "5": " ", "6": "A", "7": "B", "8": "C", "9": "D", "10": "E", "11": "F", "12": "G", "13": "H", "14": "I", "15": "J", "16": "K", "17": "L", "18": "M", "19": "N", "20": "O", "21": "P", "22": "Q", "23": "R", "24": "S", "25": "T", "26": "U", "27": "V", "28": "W", "29": "X", "30": "Y", "31": "Z", "32": "a", "33": "b", "34": "c", "35": "d", "36": "e", "37": "f", "38": "g", "39": "h", "40": "i", "41": "j", "42": "k", "43": "l", "44": "m", "45": "n", "46": "o", "47": "p", "48": "q", "49": "r", "50": "s", "51": "t", "52": "u", "53": "v", "54": "w", "55": "x", "56": "y", "57": "z", "58": "\u0401", "59": "\u0410", "60": "\u0411", "61": "\u0412", "62": "\u0413", "63": "\u0414", "64": "\u0415", "65": "\u0416", "66": "\u0417", "67": "\u0418", "68": "\u0419", "69": "\u041a", "70": "\u041b", "71": "\u041c", "72": "\u041d", "73": "\u041e", "74": "\u041f", "75": "\u0420", "76": "\u0421", "77": "\u0422", "78": "\u0423", "79": "\u0424", "80": "\u0425", "81": "\u0426", "82": "\u0427", "83": "\u0428", "84": "\u0429", "85": "\u042a", "86": "\u042b", "87": "\u042c", "88": "\u042d", "89": "\u042e", "90": "\u042f", "91": "\u0430", "92": "\u0431", "93": "\u0432", "94": "\u0433", "95": "\u0434", "96": "\u0435", "97": "\u0436", "98": "\u0437", "99": "\u0438", "100": "\u0439", "101": "\u043a", "102": "\u043b", "103": "\u043c", "104": "\u043d", "105": "\u043e", "106": "\u043f", "107": "\u0440", "108": "\u0441", "109": "\u0442", "110": "\u0443", "111": "\u0444", "112": "\u0445", "113": "\u0446", "114": "\u0447", "115": "\u0448", "116": "\u0449", "117": "\u044a", "118": "\u044b", "119": "\u044c", "120": "\u044d", "121": "\u044e", "122": "\u044f", "123": "\u0451" }, "init_std": 0.02, "init_xavier_std": 1.0, "is_encoder_decoder": true, "label2id": { " ": 5, "A": 6, "B": 7, "C": 8, "D": 9, "E": 10, "F": 11, "G": 12, "H": 13, "I": 14, "J": 15, "K": 16, "L": 17, "M": 18, "N": 19, "O": 20, "P": 21, "Q": 22, "R": 23, "S": 24, "T": 25, "U": 26, "V": 27, "W": 28, "X": 29, "Y": 30, "Z": 31, "[CLS]": 2, "[MASK]": 4, "[PAD]": 0, "[SEP]": 3, "[UNK]": 1, "a": 32, "b": 33, "c": 34, "d": 35, "e": 36, "f": 37, "g": 38, "h": 39, "i": 40, "j": 41, "k": 42, "l": 43, "m": 44, "n": 45, "o": 46, "p": 47, "q": 48, "r": 49, "s": 50, "t": 51, "u": 52, "v": 53, "w": 54, "x": 55, "y": 56, "z": 57, "\u0401": 58, "\u0410": 59, "\u0411": 60, "\u0412": 61, "\u0413": 62, "\u0414": 63, "\u0415": 64, "\u0416": 65, "\u0417": 66, "\u0418": 67, "\u0419": 68, "\u041a": 69, "\u041b": 70, "\u041c": 71, "\u041d": 72, "\u041e": 73, "\u041f": 74, "\u0420": 75, "\u0421": 76, "\u0422": 77, "\u0423": 78, "\u0424": 79, "\u0425": 80, "\u0426": 81, "\u0427": 82, "\u0428": 83, "\u0429": 84, "\u042a": 85, "\u042b": 86, "\u042c": 87, "\u042d": 88, "\u042e": 89, "\u042f": 90, "\u0430": 91, "\u0431": 92, "\u0432": 93, "\u0433": 94, "\u0434": 95, "\u0435": 96, "\u0436": 97, "\u0437": 98, "\u0438": 99, "\u0439": 100, "\u043a": 101, "\u043b": 102, "\u043c": 103, "\u043d": 104, "\u043e": 105, "\u043f": 106, "\u0440": 107, "\u0441": 108, "\u0442": 109, "\u0443": 110, "\u0444": 111, "\u0445": 112, "\u0446": 113, "\u0447": 114, "\u0448": 115, "\u0449": 116, "\u044a": 117, "\u044b": 118, "\u044c": 119, "\u044d": 120, "\u044e": 121, "\u044f": 122, "\u0451": 123 }, "mask_loss_coefficient": 1, "max_position_embeddings": 1024, "model_type": "detr", "num_channels": 3, "num_hidden_layers": 6, "num_queries": 100, "position_embedding_type": "sine", "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.47.0", "use_pretrained_backbone": true, "use_timm_backbone": true }