{
  "architectures": [
    "ViTForImageClassification"
  ],
  "model_type": "vit",
  "num_labels": 4,
  "id2label": {
    "0": "Control-Axial",
    "1": "Control-Sagittal",
    "2": "MS-Axial",
    "3": "MS-Sagittal"
  },
  "label2id": {
    "Control-Axial": "0",
    "Control-Sagittal": "1",
    "MS-Axial": "2",
    "MS-Sagittal": "3"
  },
  "image_size": 224,
  "num_channels": 3,
  "patch_size": 16,
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "attention_probs_dropout_prob": 0.0,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "qkv_bias": true
}