PaddleX/paddlex/repo_apis/PaddleOCR_api/configs/PP-OCRv4_mobile_det.yaml

Global:
  debug: false
  use_gpu: true
  epoch_num: 100
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: output
  save_epoch_step: 1
  eval_batch_step:
  - 0
  - 100
  cal_metric_during_train: false
  checkpoints:
  pretrained_model: https://paddleocr.bj.bcebos.com/pretrained/ch_PP-OCRv4_det_trained.pdparams
  save_inference_dir: null
  use_visualdl: false
  distributed: true

Architecture:
  model_type: det
  algorithm: DB
  Transform: null
  Backbone:
    name: PPLCNetV3
    scale: 0.75
    det: True
  Neck:
    name: RSEFPN
    out_channels: 96
    shortcut: True
  Head:
    name: DBHead
    k: 50
    fix_nan: True

Loss:
  name: DBLoss
  balance_loss: true
  main_loss_type: DiceLoss
  alpha: 5
  beta: 10
  ohem_ratio: 3

Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
    name: Cosine
    learning_rate: 0.001
    warmup_epoch: 2
  regularizer:
    name: L2
    factor: 1e-6

PostProcess:
  name: DBPostProcess
  thresh: 0.3
  box_thresh: 0.6
  max_candidates: 1000
  unclip_ratio: 1.5

Metric:
  name: DetMetric
  main_indicator: hmean

Train:
  dataset:
    name: TextDetDataset
    data_dir: datasets/ICDAR2015
    label_file_list:
      - datasets/ICDAR2015/train.txt
    transforms:
    - DecodeImage:
        img_mode: BGR
        channel_first: false
    - DetLabelEncode: null
    - CopyPaste: null
    - IaaAugment:
        augmenter_args:
        - type: Fliplr
          args:
            p: 0.5
        - type: Affine
          args:
            rotate:
            - -10
            - 10
        - type: Resize
          args:
            size:
            - 0.5
            - 3
    - EastRandomCropData:
        size:
        - 640
        - 640
        max_tries: 50
        keep_ratio: true
    - MakeBorderMap:
        shrink_ratio: 0.4
        thresh_min: 0.3
        thresh_max: 0.7
        total_epoch: 500
    - MakeShrinkMap:
        shrink_ratio: 0.4
        min_text_size: 8
        total_epoch: 500
    - NormalizeImage:
        scale: 1./255.
        mean:
        - 0.485
        - 0.456
        - 0.406
        std:
        - 0.229
        - 0.224
        - 0.225
        order: hwc
    - ToCHWImage: null
    - KeepKeys:
        keep_keys:
        - image
        - threshold_map
        - threshold_mask
        - shrink_map
        - shrink_mask
  loader:
    shuffle: true
    drop_last: false
    batch_size_per_card: 8
    num_workers: 3

Eval:
  dataset:
    name: TextDetDataset
    data_dir: datasets/ICDAR2015
    label_file_list:
      - datasets/ICDAR2015/val.txt
    transforms:
    - DecodeImage:
        img_mode: BGR
        channel_first: false
    - DetLabelEncode: null
    - DetResizeForTest:
        resize_long: 960
    - NormalizeImage:
        scale: 1./255.
        mean:
        - 0.485
        - 0.456
        - 0.406
        std:
        - 0.229
        - 0.224
        - 0.225
        order: hwc
    - ToCHWImage: null
    - KeepKeys:
        keep_keys:
        - image
        - shape
        - polys
        - ignore_tags
  loader:
    shuffle: false
    drop_last: false
    batch_size_per_card: 1
    num_workers: 0
profiler_options: null