batch_size: 8
iters: 1000

train_dataset:
  type: Dataset
  dataset_root: data/mini_supervisely
  train_path: data/mini_supervisely/train.txt
  num_classes: 2
  transforms:
    - type: Resize
      target_size: [192, 192]
    - type: ResizeStepScaling
      scale_step_size: 0
    - type: RandomRotation
    - type: RandomPaddingCrop
      crop_size: [192, 192]
    - type: RandomHorizontalFlip
    - type: RandomDistort
    - type: RandomBlur
      prob: 0.3
    - type: Normalize
  mode: train

val_dataset:
  type: Dataset
  dataset_root: data/mini_supervisely
  val_path: data/mini_supervisely/val.txt
  num_classes: 2
  transforms:
    - type: Resize
      target_size: [192, 192]
    - type: Normalize
  mode: val

export:
  transforms:
    - type: Resize
      target_size: [192, 192]
    - type: Normalize


optimizer:
  type: sgd
  momentum: 0.9
  weight_decay: 0.0005

lr_scheduler:
  type: PolynomialDecay
  learning_rate: 0.001
  end_lr: 0
  power: 0.9

loss:
  types:
    - type: MixedLoss
      losses:
        - type: CrossEntropyLoss
        - type: LovaszSoftmaxLoss
      coef: [0.8, 0.2]
  coef: [1, 1, 1, 1]

model:
  type: PPLiteSeg
  backbone:
    type: STDC1  # [x2 x4 x8 x16 x32]
    pretrained: https://bj.bcebos.com/paddleseg/dygraph/PP_STDCNet1.tar.gz
  cm_out_ch: 128
  backbone_indices: [1, 2, 3, 4]
  arm_out_chs: [4, 16, 32, 64]
  seg_head_inter_chs: [4, 16, 32, 64]
  pretrained: pretrained_models/human_pp_humansegv2_mobile_192x192_pretrained/model.pdparams