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": "construction--barrier--fence",
    "1": "construction--barrier--guard-rail",
    "2": "construction--barrier--other-barrier",
    "3": "construction--barrier--wall",
    "4": "construction--flat--road",
    "5": "construction--flat--service-lane",
    "6": "construction--flat--sidewalk",
    "7": "construction--structure--building",
    "8": "human--person",
    "9": "human--rider--bicyclist",
    "10": "marking--crosswalk-zebra",
    "11": "marking--general",
    "12": "nature--sky",
    "13": "nature--terrain",
    "14": "nature--vegetation",
    "15": "object--support--pole",
    "16": "object--support--traffic-sign-frame",
    "17": "object--traffic-light",
    "18": "object--traffic-sign--front",
    "19": "object--vehicle--bicycle",
    "20": "object--vehicle--bus",
    "21": "object--vehicle--car",
    "22": "object--vehicle--truck"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "label2id": {
    "construction--barrier--fence": 0,
    "construction--barrier--guard-rail": 1,
    "construction--barrier--other-barrier": 2,
    "construction--barrier--wall": 3,
    "construction--flat--road": 4,
    "construction--flat--service-lane": 5,
    "construction--flat--sidewalk": 6,
    "construction--structure--building": 7,
    "human--person": 8,
    "human--rider--bicyclist": 9,
    "marking--crosswalk-zebra": 10,
    "marking--general": 11,
    "nature--sky": 12,
    "nature--terrain": 13,
    "nature--vegetation": 14,
    "object--support--pole": 15,
    "object--support--traffic-sign-frame": 16,
    "object--traffic-light": 17,
    "object--traffic-sign--front": 18,
    "object--vehicle--bicycle": 19,
    "object--vehicle--bus": 20,
    "object--vehicle--car": 21,
    "object--vehicle--truck": 22
  },
  "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": "4.48.1"
}