Hugging Face's logo

luciagil
/
Human_action_classifier

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Human_action_classifier
File size: 1,275 Bytes 
1e43038
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "_name_or_path": "google/vit-base-patch16-224-in21K",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "texting",
    "1": "sleeping",
    "2": "hugging",
    "3": "laughing",
    "4": "using_laptop",
    "5": "cycling",
    "6": "clapping",
    "7": "calling",
    "8": "listening_to_music",
    "9": "drinking",
    "10": "dancing",
    "11": "eating",
    "12": "sitting",
    "13": "running",
    "14": "fighting"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "calling": 7,
    "clapping": 6,
    "cycling": 5,
    "dancing": 10,
    "drinking": 9,
    "eating": 11,
    "fighting": 14,
    "hugging": 2,
    "laughing": 3,
    "listening_to_music": 8,
    "running": 13,
    "sitting": 12,
    "sleeping": 1,
    "texting": 0,
    "using_laptop": 4
  },
  "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": "4.39.3"
}