relation-detr-resnet50 / config.json
xiuqhou's picture
Upload RelationDetrForObjectDetection
a062e87 verified
raw
history blame
4.97 kB
{
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"RelationDetrForObjectDetection"
],
"attention_dropout": 0.0,
"backbone": "resnet50",
"backbone_config": null,
"backbone_kwargs": {
"in_chans": 3,
"out_indices": [
2,
3,
4
]
},
"bbox_cost": 5,
"bbox_loss_coefficient": 5,
"box_noise_scale": 1.0,
"class_cost": 2,
"class_loss_coefficient": 1,
"d_model": 256,
"d_relation": 16,
"decoder_attention_heads": 8,
"decoder_ffn_dim": 2048,
"decoder_layers": 6,
"decoder_n_points": 4,
"dilation": false,
"disable_custom_kernels": false,
"dropout": 0.0,
"encoder_attention_heads": 8,
"encoder_ffn_dim": 2048,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"encoder_n_points": 4,
"focal_alpha": 0.25,
"focal_gamma": 2.0,
"giou_cost": 2,
"giou_loss_coefficient": 2,
"hybrid_assign": 6,
"hybrid_queries": 1500,
"id2label": {
"0": "none",
"1": "person",
"2": "bicycle",
"3": "car",
"4": "motorcycle",
"5": "airplane",
"6": "bus",
"7": "train",
"8": "truck",
"9": "boat",
"10": "traffic light",
"11": "fire hydrant",
"12": "none",
"13": "stop sign",
"14": "parking meter",
"15": "bench",
"16": "bird",
"17": "cat",
"18": "dog",
"19": "horse",
"20": "sheep",
"21": "cow",
"22": "elephant",
"23": "bear",
"24": "zebra",
"25": "giraffe",
"26": "none",
"27": "backpack",
"28": "umbrella",
"29": "none",
"30": "none",
"31": "handbag",
"32": "tie",
"33": "suitcase",
"34": "frisbee",
"35": "skis",
"36": "snowboard",
"37": "sports ball",
"38": "kite",
"39": "baseball bat",
"40": "baseball glove",
"41": "skateboard",
"42": "surfboard",
"43": "tennis racket",
"44": "bottle",
"45": "none",
"46": "wine glass",
"47": "cup",
"48": "fork",
"49": "knife",
"50": "spoon",
"51": "bowl",
"52": "banana",
"53": "apple",
"54": "sandwich",
"55": "orange",
"56": "broccoli",
"57": "carrot",
"58": "hot dog",
"59": "pizza",
"60": "donut",
"61": "cake",
"62": "chair",
"63": "couch",
"64": "potted plant",
"65": "bed",
"66": "none",
"67": "dining table",
"68": "none",
"69": "none",
"70": "toilet",
"71": "none",
"72": "tv",
"73": "laptop",
"74": "mouse",
"75": "remote",
"76": "keyboard",
"77": "cell phone",
"78": "microwave",
"79": "oven",
"80": "toaster",
"81": "sink",
"82": "refrigerator",
"83": "none",
"84": "book",
"85": "clock",
"86": "vase",
"87": "scissors",
"88": "teddy bear",
"89": "hair drier",
"90": "toothbrush"
},
"init_std": 0.02,
"init_xavier_std": 1.0,
"is_encoder_decoder": true,
"label2id": {
"airplane": 5,
"apple": 53,
"backpack": 27,
"banana": 52,
"baseball bat": 39,
"baseball glove": 40,
"bear": 23,
"bed": 65,
"bench": 15,
"bicycle": 2,
"bird": 16,
"boat": 9,
"book": 84,
"bottle": 44,
"bowl": 51,
"broccoli": 56,
"bus": 6,
"cake": 61,
"car": 3,
"carrot": 57,
"cat": 17,
"cell phone": 77,
"chair": 62,
"clock": 85,
"couch": 63,
"cow": 21,
"cup": 47,
"dining table": 67,
"dog": 18,
"donut": 60,
"elephant": 22,
"fire hydrant": 11,
"fork": 48,
"frisbee": 34,
"giraffe": 25,
"hair drier": 89,
"handbag": 31,
"horse": 19,
"hot dog": 58,
"keyboard": 76,
"kite": 38,
"knife": 49,
"laptop": 73,
"microwave": 78,
"motorcycle": 4,
"mouse": 74,
"none": 83,
"orange": 55,
"oven": 79,
"parking meter": 14,
"person": 1,
"pizza": 59,
"potted plant": 64,
"refrigerator": 82,
"remote": 75,
"sandwich": 54,
"scissors": 87,
"sheep": 20,
"sink": 81,
"skateboard": 41,
"skis": 35,
"snowboard": 36,
"spoon": 50,
"sports ball": 37,
"stop sign": 13,
"suitcase": 33,
"surfboard": 42,
"teddy bear": 88,
"tennis racket": 43,
"tie": 32,
"toaster": 80,
"toilet": 70,
"toothbrush": 90,
"traffic light": 10,
"train": 7,
"truck": 8,
"tv": 72,
"umbrella": 28,
"vase": 86,
"wine glass": 46,
"zebra": 24
},
"label_noise_ratio": 0.5,
"max_position_embeddings": 2048,
"model_type": "relation_detr",
"num_channels": 3,
"num_denoising": 100,
"num_feature_levels": 4,
"num_queries": 900,
"position_embedding_type": "sine",
"rel_scale": 100,
"rel_temperature": 10000,
"sin_cos_normalize": true,
"sin_cos_offset": -0.5,
"sin_cos_scale": 6.283185307179586,
"sin_cos_temperature": 10000,
"torch_dtype": "float32",
"transformers_version": "4.47.0.dev0",
"two_stage_binary_cls": false,
"use_pretrained_backbone": false,
"use_timm_backbone": true
}