config.json

{
  "_name_or_path": "apple/mobilevitv2-1.0-imagenet1k-256",
  "architectures": [
    "MobileViTV2ForImageClassification"
  ],
  "aspp_dropout_prob": 0.1,
  "aspp_out_channels": 512,
  "atrous_rates": [
    6,
    12,
    18
  ],
  "attn_dropout": 0.0,
  "base_attn_unit_dims": [
    128,
    192,
    256
  ],
  "classifier_dropout_prob": 0.1,
  "conv_kernel_size": 3,
  "expand_ratio": 2.0,
  "ffn_dropout": 0.0,
  "ffn_multiplier": 2,
  "hidden_act": "swish",
  "id2label": {
    "0": "beignets",
    "1": "bruschetta",
    "2": "chicken_wings",
    "3": "hamburger",
    "4": "pork_chop",
    "5": "prime_rib",
    "6": "ramen"
  },
  "image_size": 256,
  "initializer_range": 0.02,
  "label2id": {
    "beignets": 0,
    "bruschetta": 1,
    "chicken_wings": 2,
    "hamburger": 3,
    "pork_chop": 4,
    "prime_rib": 5,
    "ramen": 6
  },
  "layer_norm_eps": 1e-05,
  "mlp_ratio": 2.0,
  "model_type": "mobilevitv2",
  "n_attn_blocks": [
    2,
    4,
    3
  ],
  "num_channels": 3,
  "output_stride": 32,
  "patch_size": 2,
  "problem_type": "single_label_classification",
  "semantic_loss_ignore_index": 255,
  "torch_dtype": "float32",
  "transformers_version": "4.35.2",
  "width_multiplier": 1.0
}