config.json

{
  "_name_or_path": "nvidia/segformer-b5-finetuned-cityscapes-1024-1024",
  "architectures": [
    "SegformerForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "decoder_hidden_size": 768,
  "depths": [
    3,
    6,
    40,
    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": "road",
    "1": "sidewalk",
    "2": "building",
    "3": "wall",
    "4": "fence",
    "5": "pole",
    "6": "traffic light",
    "7": "traffic sign",
    "8": "vegetation",
    "9": "terrain",
    "10": "sky",
    "11": "person",
    "12": "rider",
    "13": "car",
    "14": "truck",
    "15": "bus",
    "16": "train",
    "17": "motorcycle",
    "18": "bicycle"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "bicycle": 18,
    "building": 2,
    "bus": 15,
    "car": 13,
    "fence": 4,
    "motorcycle": 17,
    "person": 11,
    "pole": 5,
    "rider": 12,
    "road": 0,
    "sidewalk": 1,
    "sky": 10,
    "terrain": 9,
    "traffic light": 6,
    "traffic sign": 7,
    "train": 16,
    "truck": 14,
    "vegetation": 8,
    "wall": 3
  },
  "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
  ],
  "transformers_version": "4.37.0.dev0"
}