{
  "_name_or_path": "google/vit-base-patch16-224",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "airport",
    "1": "bathroom",
    "10": "skatepark",
    "11": "warehouse",
    "12": "zoo",
    "2": "beach",
    "3": "building_site",
    "4": "factory",
    "5": "food",
    "6": "harbour",
    "7": "office",
    "8": "railway",
    "9": "road"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "airport": "0",
    "bathroom": "1",
    "beach": "2",
    "building_site": "3",
    "factory": "4",
    "food": "5",
    "harbour": "6",
    "office": "7",
    "railway": "8",
    "road": "9",
    "skatepark": "10",
    "warehouse": "11",
    "zoo": "12"
  },
  "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": "4.31.0"
}