Hugging Face's logo

jnmrr
/
rtdetr-v2-voucher-classifier

Object Detection
TensorBoard
Safetensors
rt_detr_v2
computer-vision
voucher-classification
rt-detr
rtdetrv2
Model card Files
xet
Metrics Community
rtdetr-v2-voucher-classifier
File size: 2,698 Bytes 
890e7ea
 
 
 
 
 
 
 
 
 
 
 
 
 
e026564
890e7ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e026564
 
 
890e7ea
 
 
 
 
 
 
 
 
 
 
 
 
e026564
 
890e7ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5468fd0
 
 
890e7ea
 
 
 
 
5468fd0
 
 
890e7ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d5038e0
890e7ea
 
 
 
 
 
 
 
 
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
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
 
{
  "activation_dropout": 0.0,
  "activation_function": "silu",
  "anchor_image_size": null,
  "architectures": [
    "RTDetrV2ForObjectDetection"
  ],
  "attention_dropout": 0.0,
  "auxiliary_loss": true,
  "backbone": null,
  "backbone_config": {
    "depths": [
      3,
      4,
      23,
      3
    ],
    "downsample_in_bottleneck": false,
    "downsample_in_first_stage": false,
    "embedding_size": 64,
    "hidden_act": "relu",
    "hidden_sizes": [
      256,
      512,
      1024,
      2048
    ],
    "layer_type": "bottleneck",
    "model_type": "rt_detr_resnet",
    "num_channels": 3,
    "out_features": [
      "stage2",
      "stage3",
      "stage4"
    ],
    "out_indices": [
      2,
      3,
      4
    ],
    "stage_names": [
      "stem",
      "stage1",
      "stage2",
      "stage3",
      "stage4"
    ],
    "torch_dtype": "float32"
  },
  "backbone_kwargs": null,
  "batch_norm_eps": 1e-05,
  "box_noise_scale": 1.0,
  "d_model": 256,
  "decoder_activation_function": "relu",
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 1024,
  "decoder_in_channels": [
    384,
    384,
    384
  ],
  "decoder_layers": 6,
  "decoder_method": "default",
  "decoder_n_levels": 3,
  "decoder_n_points": 4,
  "decoder_offset_scale": 0.5,
  "disable_custom_kernels": true,
  "dropout": 0.0,
  "encode_proj_layers": [
    2
  ],
  "encoder_activation_function": "gelu",
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 2048,
  "encoder_hidden_dim": 384,
  "encoder_in_channels": [
    512,
    1024,
    2048
  ],
  "encoder_layers": 1,
  "eos_coefficient": 0.0001,
  "eval_size": null,
  "feat_strides": [
    8,
    16,
    32
  ],
  "focal_loss_alpha": 0.75,
  "focal_loss_gamma": 2.0,
  "freeze_backbone_batch_norms": true,
  "hidden_expansion": 1.0,
  "id2label": {
    "0": "digital",
    "1": "fisico",
    "2": "tesoreria"
  },
  "initializer_bias_prior_prob": null,
  "initializer_range": 0.01,
  "is_encoder_decoder": true,
  "label2id": {
    "digital": 0,
    "fisico": 1,
    "tesoreria": 2
  },
  "label_noise_ratio": 0.5,
  "layer_norm_eps": 1e-05,
  "learn_initial_query": false,
  "matcher_alpha": 0.25,
  "matcher_bbox_cost": 5.0,
  "matcher_class_cost": 2.0,
  "matcher_gamma": 2.0,
  "matcher_giou_cost": 2.0,
  "model_type": "rt_detr_v2",
  "normalize_before": false,
  "num_denoising": 100,
  "num_feature_levels": 3,
  "num_queries": 300,
  "positional_encoding_temperature": 10000,
  "torch_dtype": "float32",
  "transformers_version": "4.55.2",
  "use_focal_loss": true,
  "use_pretrained_backbone": false,
  "use_timm_backbone": false,
  "weight_loss_bbox": 5.0,
  "weight_loss_giou": 2.0,
  "weight_loss_vfl": 1.0,
  "with_box_refine": true
}