vit-cifar10 / config.json
jamescalam's picture
first model
b363d25
{
"_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": "airplane",
"1": "automobile",
"2": "bird",
"3": "cat",
"4": "deer",
"5": "dog",
"6": "frog",
"7": "horse",
"8": "ship",
"9": "truck"
},
"image_size": 224,
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"airplane": "0",
"automobile": "1",
"bird": "2",
"cat": "3",
"deer": "4",
"dog": "5",
"frog": "6",
"horse": "7",
"ship": "8",
"truck": "9"
},
"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": "4.21.3"
}