PPLCNet_x1_0.yaml

# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: ./output/
  device: gpu
  save_interval: 1
  eval_during_train: True
  start_eval_epoch: 18
  eval_interval: 1
  epochs: 20
  print_batch_step: 10
  use_visualdl: False
  # used for static mode and model export
  image_shape: [3, 80, 160]
  save_inference_dir: ./inference
  # training model under @to_static
  to_static: False
  use_dali: False

# model architecture
Arch:
  name: PPLCNet_x1_0
  class_num: 2
  pretrained: True
  use_ssld: True
  stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
 
# loss function config for traing/eval process
Loss:
  Train:
    - CELoss:
        weight: 1.0
  Eval:
    - CELoss:
        weight: 1.0


Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Cosine
    learning_rate: 0.8
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    coeff: 0.00004


# data loader for train and eval
DataLoader:
  Train:
    dataset:
      name: ImageNetDataset
      image_root: ./dataset/textline_orientation/
      cls_label_path: ./dataset/textline_orientation/train_list.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - TimmAutoAugment:
            prob: 1.0
            config_str: rand-m9-mstd0.5-inc1
            interpolation: bicubic
            img_size: [160, 80]
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - RandomErasing:
            EPSILON: 0.0
            sl: 0.02
            sh: 1.0/3.0
            r1: 0.3
            attempt: 10
            use_log_aspect: True
            mode: pixel

    sampler:
      name: DistributedBatchSampler
      batch_size: 256
      drop_last: False
      shuffle: True
    loader:
      num_workers: 16
      use_shared_memory: True

  Eval:
    dataset: 
      name: ImageNetDataset
      image_root: ./dataset/textline_orientation/
      cls_label_path: ./dataset/textline_orientation/val_list.txt
      transform_ops:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            size: [160, 80]
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
    sampler:
      name: DistributedBatchSampler
      batch_size: 128
      drop_last: False
      shuffle: False
    loader:
      num_workers: 8
      use_shared_memory: True

Infer:
  infer_imgs: deploy/images/PULC/textline_orientation/textline_orientation_test_0_0.png
  batch_size: 10
  transforms:
    - DecodeImage:
        to_rgb: True
        channel_first: False
    - ResizeImage:
        size: [160, 80]
    - NormalizeImage:
        scale: 1.0/255.0
        mean: [0.485, 0.456, 0.406]
        std: [0.229, 0.224, 0.225]
        order: ''
    - ToCHWImage:
  PostProcess:
    name: Topk
    topk: 1
    class_id_map_file: ppcls/utils/PULC_label_list/textline_orientation_label_list.txt

Metric:
  Train:
    - TopkAcc:
        topk: [1, 2]
  Eval:
    - TopkAcc:
        topk: [1, 2]