{
  "_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": "Cross hands behind back",
    "1": "Hands on hips",
    "2": "Squat",
    "3": "Stand with hands clasped",
    "4": "Stand with hands on hips and feet crossed",
    "5": "Stand with one hand on hips",
    "6": "Standard standing posture",
    "7": "Standing with arms crossed"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Cross hands behind back": "0",
    "Hands on hips": "1",
    "Squat": "2",
    "Stand with hands clasped": "3",
    "Stand with hands on hips and feet crossed": "4",
    "Stand with one hand on hips": "5",
    "Standard standing posture": "6",
    "Standing with arms crossed": "7"
  },
  "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": "4.30.2"
}