Hugging Face's logo

IDEA-Research
/
grounding-dino-tiny

Zero-Shot Object Detection
Transformers
PyTorch
Safetensors
grounding-dino
vision
Model card Files Community
5
grounding-dino-tiny
File size: 1,735 Bytes 
882b03b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
deef33a
882b03b
 
 
c8ab596
882b03b
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
{
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "architectures": [
    "GroundingDINOForObjectDetection"
  ],
  "attention_dropout": 0.0,
  "auxiliary_loss": false,
  "backbone": "swin",
  "backbone_config": {
    "depths": [
      2,
      2,
      6,
      2
    ],
    "model_type": "swin",
    "num_heads": [
      3,
      6,
      12,
      24
    ],
    "out_features": [
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      2,
      3,
      4
    ]
  },
  "bbox_cost": 5,
  "bbox_loss_coefficient": 5,
  "class_cost": 1,
  "d_model": 256,
  "decoder_attention_heads": 8,
  "decoder_bbox_embed_share": true,
  "decoder_ffn_dim": 2048,
  "decoder_layers": 6,
  "decoder_n_points": 4,
  "dilation": false,
  "disable_custom_kernels": false,
  "dropout": 0.1,
  "embedding_init_target": true,
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 2048,
  "encoder_layers": 6,
  "encoder_n_points": 4,
  "focal_alpha": 0.25,
  "fusion_dropout": 0.0,
  "fusion_droppath": 0.1,
  "giou_cost": 2,
  "giou_loss_coefficient": 2,
  "is_encoder_decoder": true,
  "max_text_len": 256,
  "model_type": "grounding-dino",
  "num_channels": 3,
  "num_feature_levels": 4,
  "num_queries": 900,
  "position_embedding_type": "sine",
  "positional_embedding_temperature": 20,
  "query_dim": 4,
  "text_backbone_config": {
    "model_type": "grounding-dino-text-prenet"
  },
  "text_enhancer_dropout": 0.0,
  "torch_dtype": "float32",
  "transformers_version": "4.35.0.dev0",
  "two_stage": true,
  "two_stage_bbox_embed_share": false,
  "two_stage_class_embed_share": false,
  "two_stage_num_proposals": 900,
  "use_pretrained_backbone": true,
  "use_timm_backbone": false,
  "with_box_refine": true
}