config.json

{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "bicycle",
    "1": "bus",
    "2": "car",
    "3": "crosswalk",
    "4": "hydrant"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "bicycle": 0,
    "bus": 1,
    "car": 2,
    "crosswalk": 3,
    "hydrant": 4
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "pooler_act": "tanh",
  "pooler_output_size": 768,
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3"
}