config.json

{
  "_name_or_path": "nvidia/mit-b4",
  "architectures": [
    "SegformerForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "decoder_hidden_size": 768,
  "depths": [
    3,
    8,
    27,
    3
  ],
  "downsampling_rates": [
    1,
    4,
    8,
    16
  ],
  "drop_path_rate": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_sizes": [
    64,
    128,
    320,
    512
  ],
  "id2label": {
    "0": "background",
    "1": "face",
    "2": "hair",
    "3": "top",
    "4": "dress",
    "5": "skirt",
    "6": "pants",
    "7": "belt",
    "8": "bag",
    "9": "hat",
    "10": "scarf",
    "11": "glasses",
    "12": "arms",
    "13": "hands",
    "14": "legs",
    "15": "feet",
    "16": "torso",
    "17": "jewelry"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "arms": 12,
    "background": 0,
    "bag": 8,
    "belt": 7,
    "dress": 4,
    "face": 1,
    "feet": 15,
    "glasses": 11,
    "hair": 2,
    "hands": 13,
    "hat": 9,
    "jewelry": 17,
    "legs": 14,
    "pants": 6,
    "scarf": 10,
    "skirt": 5,
    "top": 3,
    "torso": 16
  },
  "layer_norm_eps": 1e-06,
  "mlp_ratios": [
    4,
    4,
    4,
    4
  ],
  "model_type": "segformer",
  "num_attention_heads": [
    1,
    2,
    5,
    8
  ],
  "num_channels": 3,
  "num_encoder_blocks": 4,
  "patch_sizes": [
    7,
    3,
    3,
    3
  ],
  "reshape_last_stage": true,
  "semantic_loss_ignore_index": 255,
  "sr_ratios": [
    8,
    4,
    2,
    1
  ],
  "strides": [
    4,
    2,
    2,
    2
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.42.4"
}