config.json

{
  "architectures": [
    "SegformerForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "auto_map": {
    "AutoModelForImageSegmentation": "model.SegformerForSemanticSegmentation"
  },
  "classifier_dropout_prob": 0.1,
  "decoder_hidden_size": 256,
  "depths": [
    2,
    2,
    2,
    2
  ],
  "drop_path_rate": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_sizes": [
    32,
    64,
    160,
    256
  ],
  "id2label": {
    "0": "skin",
    "1": "l_brow",
    "2": "r_brow",
    "3": "l_eye",
    "4": "r_eye",
    "5": "eye_g",
    "6": "l_ear",
    "7": "r_ear",
    "8": "ear_r",
    "9": "nose",
    "10": "mouth",
    "11": "u_lip",
    "12": "l_lip",
    "13": "neck",
    "14": "neck_l",
    "15": "cloth",
    "16": "hair",
    "17": "hat"
  },
  "initializer_range": 0.02,
  "label2id": {
    "cloth": 15,
    "ear_r": 8,
    "eye_g": 5,
    "hair": 16,
    "hat": 17,
    "l_brow": 1,
    "l_ear": 6,
    "l_eye": 3,
    "l_lip": 12,
    "mouth": 10,
    "neck": 13,
    "neck_l": 14,
    "nose": 9,
    "r_brow": 2,
    "r_ear": 7,
    "r_eye": 4,
    "skin": 0,
    "u_lip": 11
  },
  "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_classes": 18,
  "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": "4.36.2"
}