{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Blazers",
    "1": "Cargos",
    "10": "Sneakers",
    "11": "Sweatshirts",
    "12": "T-Shirt",
    "13": "Trousers",
    "14": "polo-Shirt",
    "2": "Casual Shirt",
    "3": "Formal Shirts",
    "4": "Hoodies",
    "5": "Jeans",
    "6": "Joggers",
    "7": "Sandals",
    "8": "Shoes",
    "9": "Shorts"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Blazers": "0",
    "Cargos": "1",
    "Casual Shirt": "2",
    "Formal Shirts": "3",
    "Hoodies": "4",
    "Jeans": "5",
    "Joggers": "6",
    "Sandals": "7",
    "Shoes": "8",
    "Shorts": "9",
    "Sneakers": "10",
    "Sweatshirts": "11",
    "T-Shirt": "12",
    "Trousers": "13",
    "polo-Shirt": "14"
  },
  "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,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.55.4"
}