Hugging Face's logo

nicolasdupuisroy
/
vit-letter-identification-v3

Image Classification
Transformers
TensorBoard
Safetensors
vit
vision
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
vit-letter-identification-v3
File size: 2,297 Bytes 
36675e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
 
{
  "_name_or_path": "google/vit-base-patch16-224-in21k",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "finetuning_task": "image-classification",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "A_",
    "1": "B_",
    "10": "K_",
    "11": "L_",
    "12": "M_",
    "13": "N_",
    "14": "O_",
    "15": "P_",
    "16": "Q_",
    "17": "R_",
    "18": "S_",
    "19": "T_",
    "2": "C_",
    "20": "U_",
    "21": "V_",
    "22": "W_",
    "23": "X_",
    "24": "Y_",
    "25": "Z_",
    "26": "a",
    "27": "b",
    "28": "c",
    "29": "d",
    "3": "D_",
    "30": "e",
    "31": "f",
    "32": "g",
    "33": "h",
    "34": "i",
    "35": "j",
    "36": "k",
    "37": "l",
    "38": "m",
    "39": "n",
    "4": "E_",
    "40": "o",
    "41": "p",
    "42": "q",
    "43": "r",
    "44": "s",
    "45": "t",
    "46": "u",
    "47": "v",
    "48": "w",
    "49": "x",
    "5": "F_",
    "50": "y",
    "51": "z",
    "6": "G_",
    "7": "H_",
    "8": "I_",
    "9": "J_"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "A_": "0",
    "B_": "1",
    "C_": "2",
    "D_": "3",
    "E_": "4",
    "F_": "5",
    "G_": "6",
    "H_": "7",
    "I_": "8",
    "J_": "9",
    "K_": "10",
    "L_": "11",
    "M_": "12",
    "N_": "13",
    "O_": "14",
    "P_": "15",
    "Q_": "16",
    "R_": "17",
    "S_": "18",
    "T_": "19",
    "U_": "20",
    "V_": "21",
    "W_": "22",
    "X_": "23",
    "Y_": "24",
    "Z_": "25",
    "a": "26",
    "b": "27",
    "c": "28",
    "d": "29",
    "e": "30",
    "f": "31",
    "g": "32",
    "h": "33",
    "i": "34",
    "j": "35",
    "k": "36",
    "l": "37",
    "m": "38",
    "n": "39",
    "o": "40",
    "p": "41",
    "q": "42",
    "r": "43",
    "s": "44",
    "t": "45",
    "u": "46",
    "v": "47",
    "w": "48",
    "x": "49",
    "y": "50",
    "z": "51"
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.37.0.dev0"
}