DocumentAIKit/configs/det/det_r50_vd_pse.yml

Global:
  use_gpu: true
  epoch_num: 600
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/det_r50_vd_pse/
  save_epoch_step: 600
  # evaluation is run every 125 iterations
  eval_batch_step: [ 0,125 ]
  cal_metric_during_train: False
  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
  checkpoints: #./output/det_r50_vd_pse_batch8_ColorJitter/best_accuracy
  save_inference_dir:
  use_visualdl: False
  infer_img: doc/imgs_en/img_10.jpg
  save_res_path: ./output/det_pse/predicts_pse.txt

Architecture:
  model_type: det
  algorithm: PSE
  Transform:
  Backbone:
    name: ResNet_vd
    layers: 50
  Neck:
    name: FPN
    out_channels: 256
  Head:
    name: PSEHead
    hidden_dim: 256
    out_channels: 7

Loss:
  name: PSELoss
  alpha: 0.7
  ohem_ratio: 3
  kernel_sample_mask: pred
  reduction: none

Optimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
    name: Step
    learning_rate: 0.0001
    step_size: 200
    gamma: 0.1
  regularizer:
    name: 'L2'
    factor: 0.0005

PostProcess:
  name: PSEPostProcess
  thresh: 0
  box_thresh: 0.85
  min_area: 16
  box_type: quad # 'quad' or 'poly'
  scale: 1

Metric:
  name: DetMetric
  main_indicator: hmean

Train:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/icdar2015/text_localization/
    label_file_list:
      - ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
    ratio_list: [ 1.0 ]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - DetLabelEncode: # Class handling label
      - ColorJitter:
          brightness: 0.12549019607843137
          saturation: 0.5
      - IaaAugment:
          augmenter_args:
            - { 'type': Resize, 'args': { 'size': [ 0.5, 3 ] } }
            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
            - { 'type': Affine, 'args': { 'rotate': [ -10, 10 ] } }
      - MakePseGt:
          kernel_num: 7
          min_shrink_ratio: 0.4
          size: 640
      - RandomCropImgMask:
          size: [ 640,640 ]
          main_key: gt_text
          crop_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ]
      - NormalizeImage:
          scale: 1./255.
          mean: [ 0.485, 0.456, 0.406 ]
          std: [ 0.229, 0.224, 0.225 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'image', 'gt_text', 'gt_kernels', 'mask' ] # the order of the dataloader list
  loader:
    shuffle: True
    drop_last: False
    batch_size_per_card: 8
    num_workers: 8

Eval:
  dataset:
    name: SimpleDataSet
    data_dir: ./train_data/icdar2015/text_localization/
    label_file_list:
      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
    ratio_list: [ 1.0 ]
    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - DetLabelEncode: # Class handling label
      - DetResizeForTest:
          limit_side_len: 736
          limit_type: min
      - NormalizeImage:
          scale: 1./255.
          mean: [ 0.485, 0.456, 0.406 ]
          std: [ 0.229, 0.224, 0.225 ]
          order: 'hwc'
      - ToCHWImage:
      - KeepKeys:
          keep_keys: [ 'image', 'shape', 'polys', 'ignore_tags' ]
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 1 # must be 1
    num_workers: 8