prompt-detr / config.json
hzli's picture
Upload DetrForObjectDetection
38c1ee5 verified
{
"_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": "balloon"
},
"init_std": 0.02,
"init_xavier_std": 1.0,
"is_encoder_decoder": true,
"label2id": {
"N/A": 0,
"airplane": 5,
"apple": 53,
"backpack": 27,
"banana": 52,
"baseball bat": 39,
"baseball glove": 40,
"bear": 23,
"bed": 65,
"bench": 15,
"bicycle": 2,
"bird": 16,
"blender": 83,
"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,
"desk": 69,
"dining table": 67,
"dog": 18,
"donut": 60,
"door": 71,
"elephant": 22,
"eye glasses": 30,
"fire hydrant": 11,
"fork": 48,
"frisbee": 34,
"giraffe": 25,
"hair drier": 89,
"handbag": 31,
"hat": 26,
"horse": 19,
"hot dog": 58,
"keyboard": 76,
"kite": 38,
"knife": 49,
"laptop": 73,
"microwave": 78,
"mirror": 66,
"motorcycle": 4,
"mouse": 74,
"orange": 55,
"oven": 79,
"parking meter": 14,
"person": 1,
"pizza": 59,
"plate": 45,
"potted plant": 64,
"refrigerator": 82,
"remote": 75,
"sandwich": 54,
"scissors": 87,
"sheep": 20,
"shoe": 29,
"sink": 81,
"skateboard": 41,
"skis": 35,
"snowboard": 36,
"spoon": 50,
"sports ball": 37,
"stop sign": 13,
"street sign": 12,
"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,
"window": 68,
"wine glass": 46,
"zebra": 24
},
"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": "4.47.1",
"use_pretrained_backbone": true,
"use_timm_backbone": true
}