|
{ |
|
"_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": "person leaning back in chair", |
|
"1": "person sitting leaning left", |
|
"2": "person sitting leaning right ", |
|
"3": "person sitting slouched", |
|
"4": "person sitting upright facing forward" |
|
}, |
|
"image_size": 224, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"person leaning back in chair": "0", |
|
"person sitting leaning left": "1", |
|
"person sitting leaning right ": "2", |
|
"person sitting slouched": "3", |
|
"person sitting upright facing forward": "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": "4.33.2" |
|
} |
|
|