config.json

{
  "_name_or_path": "nvidia/segformer-b5-finetuned-ade-640-640",
  "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": "void",
    "1": "dirt",
    "2": "sand",
    "3": "grass",
    "4": "tree",
    "5": "pole",
    "6": "water",
    "7": "sky",
    "8": "vehicle",
    "9": "container/generic-object",
    "10": "asphalt",
    "11": "gravel",
    "12": "building",
    "13": "mulch",
    "14": "rock-bed",
    "15": "log",
    "16": "bicycle",
    "17": "person",
    "18": "fence",
    "19": "bush",
    "20": "sign",
    "21": "rock",
    "22": "bridge",
    "23": "concrete",
    "24": "picnic-table"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "asphalt": 10,
    "bicycle": 16,
    "bridge": 22,
    "building": 12,
    "bush": 19,
    "concrete": 23,
    "container/generic-object": 9,
    "dirt": 1,
    "fence": 18,
    "grass": 3,
    "gravel": 11,
    "log": 15,
    "mulch": 13,
    "person": 17,
    "picnic-table": 24,
    "pole": 5,
    "rock": 21,
    "rock-bed": 14,
    "sand": 2,
    "sign": 20,
    "sky": 7,
    "tree": 4,
    "vehicle": 8,
    "void": 0,
    "water": 6
  },
  "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": "4.44.2"
}