config.json

{
  "_name_or_path": "nvidia/segformer-b2-finetuned-cityscapes-1024-1024",
  "architectures": [
    "SegformerForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "decoder_hidden_size": 768,
  "depths": [
    3,
    4,
    6,
    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": "unlabeled",
    "1": "ego vehicle",
    "2": "rectification border",
    "3": "out of roi",
    "4": "static",
    "5": "dynamic",
    "6": "ground",
    "7": "road",
    "8": "sidewalk",
    "9": "parking",
    "10": "rail track",
    "11": "building",
    "12": "wall",
    "13": "fence",
    "14": "guard rail",
    "15": "bridge",
    "16": "tunnel",
    "17": "pole",
    "18": "polegroup",
    "19": "traffic light",
    "20": "traffic sign",
    "21": "vegetation",
    "22": "terrain",
    "23": "sky",
    "24": "person",
    "25": "rider",
    "26": "car",
    "27": "truck",
    "28": "bus",
    "29": "caravan",
    "30": "trailer",
    "31": "train",
    "32": "motorcycle",
    "33": "bicycle",
    "34": "license plate"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "bicycle": 33,
    "bridge": 15,
    "building": 11,
    "bus": 28,
    "car": 26,
    "caravan": 29,
    "dynamic": 5,
    "ego vehicle": 1,
    "fence": 13,
    "ground": 6,
    "guard rail": 14,
    "license plate": 34,
    "motorcycle": 32,
    "out of roi": 3,
    "parking": 9,
    "person": 24,
    "pole": 17,
    "polegroup": 18,
    "rail track": 10,
    "rectification border": 2,
    "rider": 25,
    "road": 7,
    "sidewalk": 8,
    "sky": 23,
    "static": 4,
    "terrain": 22,
    "traffic light": 19,
    "traffic sign": 20,
    "trailer": 30,
    "train": 31,
    "truck": 27,
    "tunnel": 16,
    "unlabeled": 0,
    "vegetation": 21,
    "wall": 12
  },
  "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": "4.47.1"
}