config.json

{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "parking lot",
    "1": "avenue",
    "2": "highway",
    "3": "bridge",
    "4": "marina",
    "5": "crossroads",
    "6": "airport runway",
    "7": "pipeline",
    "8": "town",
    "9": "airplane",
    "10": "forest",
    "11": "mangrove",
    "12": "artificial grassland",
    "13": "river protection forest",
    "14": "shrubwood",
    "15": "sapling",
    "16": "sparse forest",
    "17": "lakeshore",
    "18": "river",
    "19": "stream",
    "20": "coastline",
    "21": "hirst",
    "22": "dam",
    "23": "sea",
    "24": "snow mountain",
    "25": "sandbeach",
    "26": "mountain",
    "27": "desert",
    "28": "dry farm",
    "29": "green farmland",
    "30": "bare land",
    "31": "city building",
    "32": "residents",
    "33": "container",
    "34": "storage room"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "airplane": 9,
    "airport runway": 6,
    "artificial grassland": 12,
    "avenue": 1,
    "bare land": 30,
    "bridge": 3,
    "city building": 31,
    "coastline": 20,
    "container": 33,
    "crossroads": 5,
    "dam": 22,
    "desert": 27,
    "dry farm": 28,
    "forest": 10,
    "green farmland": 29,
    "highway": 2,
    "hirst": 21,
    "lakeshore": 17,
    "mangrove": 11,
    "marina": 4,
    "mountain": 26,
    "parking lot": 0,
    "pipeline": 7,
    "residents": 32,
    "river": 18,
    "river protection forest": 13,
    "sandbeach": 25,
    "sapling": 15,
    "sea": 23,
    "shrubwood": 14,
    "snow mountain": 24,
    "sparse forest": 16,
    "storage room": 34,
    "stream": 19,
    "town": 8
  },
  "model_type": "siglip",
  "problem_type": "single_label_classification",
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "projection_size": 768,
    "torch_dtype": "float32",
    "vocab_size": 256000
  },
  "torch_dtype": "float32",
  "transformers_version": "4.50.0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 224,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "torch_dtype": "float32"
  }
}