config.json

{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "depths": [
    3,
    3,
    9,
    3
  ],
  "drop_path_rate": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "hidden_sizes": [
    96,
    192,
    384,
    768
  ],
  "id2label": {
    "0": "AnnualCrop",
    "1": "Forest",
    "2": "HerbaceousVegetation",
    "3": "Highway",
    "4": "Industrial",
    "5": "Pasture",
    "6": "PermanentCrop",
    "7": "Residential",
    "8": "River",
    "9": "SeaLake"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "AnnualCrop": 0,
    "Forest": 1,
    "HerbaceousVegetation": 2,
    "Highway": 3,
    "Industrial": 4,
    "Pasture": 5,
    "PermanentCrop": 6,
    "Residential": 7,
    "River": 8,
    "SeaLake": 9
  },
  "layer_norm_eps": 1e-12,
  "layer_scale_init_value": 1e-06,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "num_stages": 4,
  "output_attentions": true,
  "patch_size": 4,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.25.1"
}