batch_size: 2
iters: 80000

train_dataset:
  type: Cityscapes
  dataset_root: data/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: data/cityscapes
  transforms:
    - type: Normalize
  mode: val


optimizer:
  type: SGD
  momentum: 0.9
  weight_decay: 4.0e-5

lr_scheduler:
  type: PolynomialDecay
  learning_rate: 0.01
  end_lr: 0
  power: 0.9

loss:
  types:
    - type: CrossEntropyLoss
  coef: [1]

model:
  type: DeepLabV3
  backbone:
    type: ResNet101_vd
    output_stride: 8
    multi_grid: [1, 2, 4]
    pretrained: https://bj.bcebos.com/paddleseg/dygraph/resnet101_vd_ssld.tar.gz
  backbone_indices: [3]
  aspp_ratios: [1, 12, 24, 36]
  aspp_out_channels: 256
  align_corners: False
  pretrained: null