OpenOCR/configs/det/dbnet/repvit_db.yml

Global:
  device: gpu
  epoch_num: &epoch_num 500
  log_smooth_window: 20
  print_batch_step: 100
  output_dir: ./output/det_repsvtr_db
  save_epoch_step: [400, 25]
  eval_batch_step:
  - 0
  - 1000
  cal_metric_during_train: false
  checkpoints:
  pretrained_model: openocr_det_repvit_ch.pth
  save_inference_dir: null
  use_tensorboard: false
  infer_img:
  save_res_path: ./checkpoints/det_db/predicts_db.txt
  distributed: true
  model_type: det

Architecture:
  algorithm: DB_mobile
  Backbone:
    name: RepSVTR_det
  Neck:
    name: RSEFPN
    out_channels: 96
    shortcut: True
  Head:
    name: DBHead
    k: 50

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

Optimizer:
  name: Adam
  lr: 0.001
  weight_decay: 5.0e-05
  filter_bias_and_bn: False

LRScheduler:
  name: CosineAnnealingLR
  warmup_epoch: 2

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

Metric:
  name: DetMetric
  main_indicator: hmean

Train:
  dataset:
    name: SimpleDataSet
    data_dir: ../icdar2015/text_localization/
    label_file_list:
      - ../icdar2015/text_localization/train_icdar2015_label.txt
    ratio_list: [1.0]
    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: *epoch_num
    - MakeShrinkMap:
        shrink_ratio: 0.4
        min_text_size: 8
        total_epoch: *epoch_num
    - 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: 8

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: ../icdar2015/text_localization/
    label_file_list:
      - ../icdar2015/text_localization/test_icdar2015_label.txt
    transforms:
    - DecodeImage:
        img_mode: BGR
        channel_first: false
    - DetLabelEncode: null
    - DetResizeForTest:
        # image_shape: [1280, 1280]
        # keep_ratio: True
        # padding: True
        limit_side_len: 960
        limit_type: max
    - 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: 2
profiler_options: null