config.json

{
  "_name_or_path": "landmark-classification-vit",
  "architectures": [
    "Swinv2ForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "depths": [
    2,
    2,
    6,
    2
  ],
  "drop_path_rate": 0.1,
  "embed_dim": 96,
  "encoder_stride": 64,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Observation , document"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "mlp_ratio": 4.0,
  "model_type": "swinv2",
  "num_channels": 3,
  "num_heads": [
    3,
    6,
    12,
    24
  ],
  "num_layers": 4,
  "patch_size": 4,
  "path_norm": true,
  "pretrained_window_sizes": [
    0,
    0,
    0,
    0
  ],
  "qkv_bias": true,
  "torch_dtype": "float64",
  "transformers_version": "4.47.1",
  "use_absolute_embeddings": false,
  "window_size": 10
}