espnet_cityscapes_1024_512_120k_x2.yml

train_dataset:
  type: Cityscapes
  dataset_root: cityscapes
  transforms:
    - type: ResizeStepScaling
      min_scale_factor: 0.5
      max_scale_factor: 2.0
      scale_step_size: 0.25
    - type: RandomPaddingCrop
      crop_size: [1024, 512]
    - type: RandomHorizontalFlip
    - type: RandomDistort
      brightness_range: 0.4
      contrast_range: 0.4
      saturation_range: 0.4
    - type: Normalize
  mode: train

val_dataset:
  type: Cityscapes
  dataset_root: cityscapes
  transforms:
    - type: Normalize
  mode: val

model:
  type: EESPNetHead
  backbone:
    type: EESPNet
    drop_prob: 0.0
    scale: 2.0
  num_classes: 19
  drop_prob: 0.0

optimizer:
  type: adam
  weight_decay: 0.0002

lr_scheduler:
  type: PolynomialDecay
  learning_rate: 0.001
  end_lr: 0.0
  power: 0.9

iters: 120000
batch_size: 8

loss:
  types:
    - type: CrossEntropyLoss
      weight: [2.79834108 ,6.92945723 ,3.84068512 ,9.94349362 ,9.77098823 ,9.51484 ,10.30981624 ,9.94307377 ,4.64933892 ,9.55759938 ,7.86692178 ,9.53126629 ,10.3496365 ,6.67234062 ,10.26054204 ,10.28785275 ,10.28988296 ,10.40546021 ,10.13848367]
  coef: [1, 1]