config.json

{
  "_name_or_path": "apple/mobilevit-xx-small",
  "architectures": [
    "MobileViTForImageClassification"
  ],
  "aspp_dropout_prob": 0.1,
  "aspp_out_channels": 256,
  "atrous_rates": [
    6,
    12,
    18
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "conv_kernel_size": 3,
  "expand_ratio": 2.0,
  "hidden_act": "silu",
  "hidden_dropout_prob": 0.05,
  "hidden_sizes": [
    64,
    80,
    96
  ],
  "id2label": {
    "0": "snowing",
    "1": "raining",
    "2": "sunny",
    "3": "cloudy",
    "4": "night",
    "5": "snow_on_road",
    "6": "partial_snow_on_road",
    "7": "clear_pavement",
    "8": "wet_pavement",
    "9": "iced_lens"
  },
  "image_size": 256,
  "initializer_range": 0.02,
  "label2id": {
    "clear_pavement": 7,
    "cloudy": 3,
    "iced_lens": 9,
    "night": 4,
    "partial_snow_on_road": 6,
    "raining": 1,
    "snow_on_road": 5,
    "snowing": 0,
    "sunny": 2,
    "wet_pavement": 8
  },
  "layer_norm_eps": 1e-05,
  "mlp_ratio": 2.0,
  "model_type": "mobilevit",
  "neck_hidden_sizes": [
    16,
    16,
    24,
    48,
    64,
    80,
    320
  ],
  "num_attention_heads": 4,
  "num_channels": 3,
  "output_stride": 32,
  "patch_size": 2,
  "problem_type": "multi_label_classification",
  "qkv_bias": true,
  "semantic_loss_ignore_index": 255,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2"
}