File size: 2,246 Bytes
237e0b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f209fd
237e0b6
 
 
 
 
 
 
 
 
 
 
 
6f209fd
237e0b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f209fd
237e0b6
 
 
 
 
 
 
 
6f209fd
237e0b6
6f209fd
237e0b6
 
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
{
  "activation_dropout": 0.0,
  "activation_function": "relu",
  "angle_loss_coefficient": 1,
  "architectures": [
    "Mono3DVGv2ForSingleObjectDetection"
  ],
  "attention_dropout": 0.0,
  "auxiliary_loss": false,
  "backbone": "swin_large_patch4_window7_224",
  "backbone_config": null,
  "bbox_cost": 5,
  "bbox_loss_coefficient": 5,
  "center3d_cost": 10,
  "center3d_loss_coefficient": 10,
  "class_cost": 2,
  "cls_loss_coefficient": 2,
  "d_model": 256,
  "decoder_attention_heads": 8,
  "decoder_depth_residual": false,
  "decoder_ffn_dim": 256,
  "decoder_layers": 3,
  "decoder_n_points": 4,
  "decoder_self_attn": false,
  "decoder_text_residual": false,
  "depth_loss_coefficient": 1,
  "depth_map_loss_coefficient": 1,
  "depth_max": 60.0,
  "depth_min": 0.001,
  "dim_loss_coefficient": 1,
  "disable_custom_kernels": false,
  "dropout": 0.1,
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 256,
  "encoder_layers": 6,
  "encoder_n_points": 4,
  "focal_alpha": 0.25,
  "freeze_backbone": true,
  "giou_cost": 2,
  "giou_loss_coefficient": 2,
  "id2label": {
    "0": "pedestrian",
    "1": "car",
    "2": "cyclist",
    "3": "van",
    "4": "truck",
    "5": "tram",
    "6": "bus",
    "7": "person_sitting",
    "8": "motorcyclist"
  },
  "init_box": false,
  "init_std": 0.02,
  "init_xavier_std": 1.0,
  "is_encoder_decoder": true,
  "label2id": {
    "bus": 6,
    "car": 1,
    "cyclist": 2,
    "motorcyclist": 8,
    "pedestrian": 0,
    "person_sitting": 7,
    "tram": 5,
    "truck": 4,
    "van": 3
  },
  "model_type": "mono3dvgv2",
  "num_channels": 3,
  "num_depth_bins": 80,
  "num_feature_levels": 4,
  "num_queries": 1,
  "num_text_output_layers": 6,
  "position_embedding_type": "sine",
  "pretrained_backbone_path": "pretrained-models/swin_large_patch4_window7_224/model.safetensors",
  "text_encoder_type": "pretrained-models/roberta-base",
  "torch_dtype": "float32",
  "transformers_version": "4.44.0",
  "two_stage": false,
  "use_dab": true,
  "use_pretrained_backbone": true,
  "use_text_guided_adapter": false,
  "use_timm_backbone": true,
  "vl_encoder_type": "simple-bridge-tower",
  "with_box_refine": true
}