{
  "_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": "Ambulance",
    "1": "Barge",
    "10": "Segway",
    "11": "Snowmobile",
    "12": "Tank",
    "13": "Taxi",
    "14": "Truck",
    "15": "Van",
    "2": "Bicycle",
    "3": "Boat",
    "4": "Bus",
    "5": "Car",
    "6": "Cart",
    "7": "Helicopter",
    "8": "Limousine",
    "9": "Motorcycle"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Ambulance": "0",
    "Barge": "1",
    "Bicycle": "2",
    "Boat": "3",
    "Bus": "4",
    "Car": "5",
    "Cart": "6",
    "Helicopter": "7",
    "Limousine": "8",
    "Motorcycle": "9",
    "Segway": "10",
    "Snowmobile": "11",
    "Tank": "12",
    "Taxi": "13",
    "Truck": "14",
    "Van": "15"
  },
  "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": "4.35.2"
}