{
  "_name_or_path": "microsoft/swin-tiny-patch4-window7-224",
  "architectures": [
    "SwinForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "depths": [
    2,
    2,
    6,
    2
  ],
  "drop_path_rate": 0.1,
  "embed_dim": 96,
  "encoder_stride": 32,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "calling",
    "1": "clapping",
    "2": "dancing",
    "3": "laughing",
    "4": "sleeping",
    "5": "fighting",
    "6": "texting",
    "7": "listening_to_music",
    "8": "drinking",
    "9": "running",
    "10": "using_laptop",
    "11": "cycling",
    "12": "sitting",
    "13": "eating",
    "14": "hugging"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "calling": 0,
    "clapping": 1,
    "cycling": 11,
    "dancing": 2,
    "drinking": 8,
    "eating": 13,
    "fighting": 5,
    "hugging": 14,
    "laughing": 3,
    "listening_to_music": 7,
    "running": 9,
    "sitting": 12,
    "sleeping": 4,
    "texting": 6,
    "using_laptop": 10
  },
  "layer_norm_eps": 1e-05,
  "mlp_ratio": 4.0,
  "model_type": "swin",
  "num_channels": 3,
  "num_heads": [
    3,
    6,
    12,
    24
  ],
  "num_layers": 4,
  "out_features": [
    "stage4"
  ],
  "out_indices": [
    4
  ],
  "patch_size": 4,
  "path_norm": true,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "stage_names": [
    "stem",
    "stage1",
    "stage2",
    "stage3",
    "stage4"
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.39.3",
  "use_absolute_embeddings": false,
  "window_size": 7
}