Hugging Face's logo

FoundationVision
/
groma-det-pretrain

Transformers
PyTorch
ddetr
Inference Endpoints
Model card Files Community
groma-det-pretrain
File size: 2,195 Bytes 
992f71f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
81
82
83
84
85
86
87
 
{
  "architectures": [
    "CustomDDETRModel"
  ],
  "ddetr_cfg": {
    "activation_dropout": 0.0,
    "activation_function": "relu",
    "attention_dropout": 0.0,
    "auxiliary_loss": true,
    "backbone": "resnet50",
    "backbone_config": null,
    "bbox_cost": 5,
    "bbox_loss_coefficient": 5,
    "class_cost": 2,
    "cls_loss_coefficient": 2,
    "d_model": 256,
    "decoder_attention_heads": 8,
    "decoder_ffn_dim": 1024,
    "decoder_layers": 6,
    "decoder_n_points": 4,
    "dice_loss_coefficient": 1,
    "dilation": false,
    "disable_custom_kernels": false,
    "dropout": 0.1,
    "encoder_attention_heads": 8,
    "encoder_ffn_dim": 1024,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 6,
    "encoder_n_points": 4,
    "eos_coefficient": 0.1,
    "focal_alpha": 0.25,
    "giou_cost": 2,
    "giou_loss_coefficient": 2,
    "id2label": {
      "0": "LABEL_0"
    },
    "init_std": 0.02,
    "init_xavier_std": 1.0,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0
    },
    "mask_loss_coefficient": 1,
    "max_position_embeddings": 1024,
    "model_type": "deformable_detr",
    "num_channels": 3,
    "num_feature_levels": 1,
    "num_queries": 300,
    "position_embedding_type": "sine",
    "transformers_version": "4.32.0",
    "two_stage": true,
    "two_stage_num_proposals": 300,
    "use_pretrained_backbone": true,
    "use_timm_backbone": true,
    "with_box_refine": true
  },
  "model_type": "ddetr",
  "torch_dtype": "float32",
  "transformers_version": "4.32.0",
  "vis_encoder_cfg": {
    "architectures": [
      "Dinov2Model"
    ],
    "attention_probs_dropout_prob": 0.0,
    "drop_path_rate": 0.0,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1024,
    "image_size": 518,
    "initializer_range": 0.02,
    "layer_norm_eps": 1e-06,
    "layerscale_value": 1.0,
    "mlp_ratio": 4,
    "model_type": "dinov2",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "qkv_bias": true,
    "torch_dtype": "float32",
    "transformers_version": "4.32.0",
    "use_swiglu_ffn": false
  },
  "vis_output_layer": -2,
  "zs_weight_path": null
}