first commit

configs/det/det_mv3_pse.yml

+Global:
+  use_gpu: true
+  epoch_num: 600
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_mv3_pse/
+  save_epoch_step: 600
+  # evaluation is run every 63 iterations
+  eval_batch_step: [ 0,63 ]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/MobileNetV3_large_x0_5_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: null
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: FPN
+    out_channels: 96
+  Head:
+    name: PSEHead
+    hidden_dim: 96
+    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: 0.001
+    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: 16
+    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
\ No newline at end of file

configs/det/det_r50_vd_db.yml

+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/det_r50_vd/
+  save_epoch_step: 1200
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0,2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 50
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  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
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: DBPostProcess
+  thresh: 0.3
+  box_thresh: 0.7
+  max_candidates: 1000
+  unclip_ratio: 1.5
+
+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
+      - 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
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 16
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          image_shape: [736, 1280]
+      - 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

configs/det/det_r50_vd_dcn_fce_ctw.yml

+Global:
+  use_gpu: true
+  epoch_num: 1500
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./output/det_r50_dcn_fce_ctw/
+  save_epoch_step: 100
+  # evaluation is run every 835 iterations
+  eval_batch_step: [0, 835]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_fce/predicts_fce.txt
+
+
+Architecture:
+  model_type: det
+  algorithm: FCE
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 50
+    dcn_stage: [False, True, True, True]
+    out_indices: [1,2,3]
+  Neck:
+    name: FCEFPN
+    out_channels: 256
+    has_extra_convs: False
+    extra_stage: 0
+  Head:
+    name: FCEHead
+    fourier_degree: 5
+Loss:
+  name: FCELoss
+  fourier_degree: 5
+  num_sample: 50
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: FCEPostProcess
+  scales: [8, 16, 32]
+  alpha: 1.0
+  beta: 1.0
+  fourier_degree: 5
+  box_type: 'poly'
+
+Metric:
+  name: DetFCEMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list: 
+      - ./train_data/ctw1500/imgs/training.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - ColorJitter: 
+          brightness: 0.142
+          saturation: 0.5
+          contrast: 0.5
+      - RandomScaling: 
+      - RandomCropFlip:
+          crop_ratio: 0.5
+      - RandomCropPolyInstances:
+          crop_ratio: 0.8
+          min_side_ratio: 0.3
+      - RandomRotatePolyInstances:
+          rotate_ratio: 0.5
+          max_angle: 30
+          pad_with_fixed_color: False
+      - SquareResizePad:
+          target_size: 800
+          pad_ratio: 0.6
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+      - FCENetTargets:
+          fourier_degree: 5
+      - 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', 'p3_maps', 'p4_maps', 'p5_maps'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 6
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/ctw1500/imgs/
+    label_file_list:
+      - ./train_data/ctw1500/imgs/test.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+          ignore_orientation: True
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_type: 'min'
+          limit_side_len: 736
+      - NormalizeImage:
+          scale: 1./255.
+          mean: [0.485, 0.456, 0.406]
+          std: [0.229, 0.224, 0.225]
+          order: 'hwc'
+      - Pad: 
+      - 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: 2
\ No newline at end of file

configs/det/det_r50_vd_east.yml

+Global:
+  use_gpu: true
+  epoch_num: 10000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/east_r50_vd/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_pretrained
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  save_res_path: ./output/det_east/predicts_east.txt
+
+Architecture:
+  model_type: det
+  algorithm: EAST
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 50
+  Neck:
+    name: EASTFPN
+    model_name: large
+  Head:
+    name: EASTHead
+    model_name: large
+
+Loss:
+  name: EASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: EASTPostProcess
+  score_thresh: 0.8
+  cover_thresh: 0.1
+  nms_thresh: 0.2
+
+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
+      - EASTProcessTrain:
+          image_shape: [512, 512]
+          background_ratio: 0.125
+          min_crop_side_ratio: 0.1
+          min_text_size: 10
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'geo_map', 'training_mask'] # dataloader will return list in this order
+  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
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          limit_side_len: 2400
+          limit_type: max
+      - 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: 2
\ No newline at end of file

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
+    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
\ No newline at end of file

configs/det/det_r50_vd_sast_icdar15.yml

+Global:
+  use_gpu: true
+  epoch_num: 5000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/sast_r50_vd_ic15/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  save_res_path: ./output/sast_r50_vd_ic15/predicts_sast.txt
+
+
+Architecture:
+  model_type: det
+  algorithm: SAST
+  Transform:
+  Backbone:
+    name: ResNet_SAST
+    layers: 50
+  Neck:
+    name: SASTFPN
+    with_cab: True
+  Head:
+    name: SASTHead
+
+Loss:
+  name: SASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: SASTPostProcess
+  score_thresh: 0.5
+  sample_pts_num: 2
+  nms_thresh: 0.2
+  expand_scale: 1.0
+  shrink_ratio_of_width: 0.3
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: [./train_data/icdar2013/train_label_json.txt, ./train_data/icdar2015/train_label_json.txt, ./train_data/icdar17_mlt_latin/train_label_json.txt, ./train_data/coco_text_icdar_4pts/train_label_json.txt]
+    ratio_list: [0.1, 0.45, 0.3, 0.15]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - SASTProcessTrain:
+          image_shape: [512, 512]
+          min_crop_side_ratio: 0.3
+          min_crop_size: 24
+          min_text_size: 4
+          max_text_size: 512
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'border_map', 'training_mask', 'tvo_map', 'tco_map'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          resize_long: 1536
+      - 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: 2

configs/det/det_r50_vd_sast_totaltext.yml

+Global:
+  use_gpu: true
+  epoch_num: 5000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/sast_r50_vd_tt/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: 
+  save_res_path: ./output/sast_r50_vd_tt/predicts_sast.txt
+
+Architecture:
+  model_type: det
+  algorithm: SAST
+  Transform:
+  Backbone:
+    name: ResNet_SAST
+    layers: 50
+  Neck:
+    name: SASTFPN
+    with_cab: True
+  Head:
+    name: SASTHead
+
+Loss:
+  name: SASTLoss
+  
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+  #  name: Cosine
+    learning_rate: 0.001
+  #  warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+PostProcess:
+  name: SASTPostProcess
+  score_thresh: 0.5
+  sample_pts_num: 6
+  nms_thresh: 0.2
+  expand_scale: 1.2
+  shrink_ratio_of_width: 0.2
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
+    ratio_list: [0.5, 0.5]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - SASTProcessTrain:
+          image_shape: [512, 512]
+          min_crop_side_ratio: 0.3
+          min_crop_size: 24
+          min_text_size: 4
+          max_text_size: 512
+      - KeepKeys:
+          keep_keys: ['image', 'score_map', 'border_map', 'training_mask', 'tvo_map', 'tco_map'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: 
+        - ./train_data/total_text_icdar_14pt/test_label_json.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+          resize_long: 768
+      - 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: 2
\ No newline at end of file

configs/det/det_res18_db_v2.0.yml

+Global:
+  use_gpu: true
+  epoch_num: 1200
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/ch_db_res18/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  cal_metric_during_train: False
+  pretrained_model: ./pretrain_models/ResNet18_vd_pretrained
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
+
+Architecture:
+  model_type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 18
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 256
+  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
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+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: 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
+      - IaaAugment:
+          augmenter_args:
+            - { 'type': Fliplr, 'args': { 'p': 0.5 } }
+            - { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
+            - { 'type': Resize, 'args': { 'size': [0.5, 3] } }
+      - EastRandomCropData:
+          size: [960, 960]
+          max_tries: 50
+          keep_ratio: true
+      - MakeBorderMap:
+          shrink_ratio: 0.4
+          thresh_min: 0.3
+          thresh_max: 0.7
+      - MakeShrinkMap:
+          shrink_ratio: 0.4
+          min_text_size: 8
+      - 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/icdar2015/text_localization/
+    label_file_list:
+      - ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - DetLabelEncode: # Class handling label
+      - DetResizeForTest:
+#           image_shape: [736, 1280]
+      - 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: 2

configs/e2e/e2e_r50_vd_pg.yml

+Global:
+  use_gpu: True
+  epoch_num: 600
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/pgnet_r50_vd_totaltext/
+  save_epoch_step: 10
+  # evaluation is run every 0 iterationss after the 1000th iteration
+  eval_batch_step: [ 0, 1000 ]
+  cal_metric_during_train: False
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  valid_set: totaltext # two mode: totaltext valid curved words, partvgg valid non-curved words
+  save_res_path: ./output/pgnet_r50_vd_totaltext/predicts_pgnet.txt
+  character_dict_path: ppocr/utils/ic15_dict.txt
+  character_type: EN
+  max_text_length: 50 # the max length in seq
+  max_text_nums: 30 # the max seq nums in a pic
+  tcl_len: 64
+
+Architecture:
+  model_type: e2e
+  algorithm: PGNet
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 50
+  Neck:
+    name: PGFPN
+  Head:
+    name: PGHead
+
+Loss:
+  name: PGLoss
+  tcl_bs: 64
+  max_text_length: 50 # the same as Global: max_text_length
+  max_text_nums: 30 # the same as Global：max_text_nums
+  pad_num: 36 # the length of dict for pad
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+
+PostProcess:
+  name: PGPostProcess
+  score_thresh: 0.5
+  mode: fast   # fast or slow two ways
+
+Metric:
+  name: E2EMetric
+  mode: A   # two ways for eval, A: label from txt,  B: label from gt_mat
+  gt_mat_dir:  ./train_data/total_text/gt  # the dir of gt_mat
+  character_dict_path: ppocr/utils/ic15_dict.txt
+  main_indicator: f_score_e2e
+
+Train:
+  dataset:
+    name: PGDataSet
+    data_dir: ./train_data/total_text/train
+    label_file_list: [./train_data/total_text/train/train.txt]
+    ratio_list: [1.0]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - E2ELabelEncodeTrain:
+      - PGProcessTrain:
+          batch_size: 14  # same as loader: batch_size_per_card
+          min_crop_size: 24
+          min_text_size: 4
+          max_text_size: 512
+      - KeepKeys:
+          keep_keys: [ 'images', 'tcl_maps', 'tcl_label_maps', 'border_maps','direction_maps', 'training_masks', 'label_list', 'pos_list', 'pos_mask' ] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: True
+    batch_size_per_card: 14
+    num_workers: 16
+
+Eval:
+  dataset:
+    name: PGDataSet
+    data_dir: ./train_data/total_text/test
+    label_file_list: [./train_data/total_text/test/test.txt]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - E2ELabelEncodeTest:
+      - E2EResizeForTest:
+          max_side_len: 768
+      - 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', 'texts', 'ignore_tags', 'img_id']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 2

configs/kie/kie_unet_sdmgr.yml

+Global:
+  use_gpu: True
+  epoch_num: 60
+  log_smooth_window: 20
+  print_batch_step: 50
+  save_model_dir: ./output/kie_5/
+  save_epoch_step: 50
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [ 0, 80 ]
+  # 1. If pretrained_model is saved in static mode, such as classification pretrained model
+  #    from static branch, load_static_weights must be set as True.
+  # 2. If you want to finetune the pretrained models we provide in the docs,
+  #    you should set load_static_weights as False.
+  load_static_weights: False
+  cal_metric_during_train: False
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  class_path: ./train_data/wildreceipt/class_list.txt
+  infer_img: ./train_data/wildreceipt/1.txt
+  save_res_path: ./output/sdmgr_kie/predicts_kie.txt
+  img_scale: [ 1024, 512 ]
+
+Architecture:
+  model_type: kie
+  algorithm: SDMGR
+  Transform:
+  Backbone:
+    name: Kie_backbone
+  Head:
+    name: SDMGRHead
+
+Loss:
+  name: SDMGRLoss
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    learning_rate: 0.001
+    decay_epochs: [ 60, 80, 100]
+    values: [ 0.001, 0.0001, 0.00001]
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0.00005
+
+PostProcess:
+  name: None
+
+Metric:
+  name: KIEMetric
+  main_indicator: hmean
+  # Classes that will be ignored while computing F1 score.
+  ignore_classes: [0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 25]
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/wildreceipt/
+    label_file_list: [ './train_data/wildreceipt/wildreceipt_train.txt' ]
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - KieLabelEncode: # Class handling label
+          character_dict_path: ./train_data/wildreceipt/dict.txt
+      - KieResize:
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'relations', 'texts', 'points', 'labels', 'tag', 'shape'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 4
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/wildreceipt
+    label_file_list:
+      - ./train_data/wildreceipt/wildreceipt_test.txt
+      # - /paddle/data/PaddleOCR/train_data/wildreceipt/1.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - KieLabelEncode: # Class handling label
+          character_dict_path: ./train_data/wildreceipt/dict.txt
+      - KieResize:
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'image', 'relations', 'texts', 'points', 'labels', 'tag', 'ori_image', 'ori_boxes', 'shape']
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 1 # must be 1
+    num_workers: 4

configs/rec/PP-OCRv3/ch_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v3
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/rec/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/rec/rec_gt_train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/rec/ic15_data/
+    label_file_list:
+    - ./train_data/rec/ic15_data/rec_gt_test.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 800
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_ppocr_v3_distillation
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_distillation.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs : [700, 800]
+    values : [0.0005, 0.00005]
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: &model_type "rec"
+  name: DistillationModel
+  algorithm: Distillation
+  Models:
+    Teacher:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: SVTR
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+        last_conv_stride: [1, 2]
+        last_pool_type: avg
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 64
+                depth: 2
+                hidden_dims: 120
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - SARHead:
+              enc_dim: 512
+              max_text_length: *max_text_length
+    Student:
+      pretrained:
+      freeze_params: false
+      return_all_feats: true
+      model_type: *model_type
+      algorithm: SVTR
+      Transform:
+      Backbone:
+        name: MobileNetV1Enhance
+        scale: 0.5
+        last_conv_stride: [1, 2]
+        last_pool_type: avg
+      Head:
+        name: MultiHead
+        head_list:
+          - CTCHead:
+              Neck:
+                name: svtr
+                dims: 64
+                depth: 2
+                hidden_dims: 120
+                use_guide: True
+              Head:
+                fc_decay: 0.00001
+          - SARHead:
+              enc_dim: 512
+              max_text_length: *max_text_length
+Loss:
+  name: CombinedLoss
+  loss_config_list:
+  - DistillationDMLLoss:
+      weight: 1.0
+      act: "softmax"
+      use_log: true
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: head_out
+      multi_head: True
+      dis_head: ctc
+      name: dml_ctc
+  - DistillationDMLLoss:
+      weight: 0.5
+      act: "softmax"
+      use_log: true
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: head_out
+      multi_head: True
+      dis_head: sar
+      name: dml_sar
+  - DistillationDistanceLoss:
+      weight: 1.0
+      mode: "l2"
+      model_name_pairs:
+      - ["Student", "Teacher"]
+      key: backbone_out
+  - DistillationCTCLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      key: head_out
+      multi_head: True
+  - DistillationSARLoss:
+      weight: 1.0
+      model_name_list: ["Student", "Teacher"]
+      key: head_out
+      multi_head: True
+
+PostProcess:
+  name: DistillationCTCLabelDecode
+  model_name: ["Student", "Teacher"]
+  key: head_out
+  multi_head: True
+
+Metric:
+  name: DistillationMetric
+  base_metric_name: RecMetric
+  main_indicator: acc
+  key: "Student"
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_en_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/en_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_en.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    # data_dir: ./train_data/
+    data_dir: ./train_data/rec/
+    ext_op_transform_idx: 1
+    label_file_list:
+    # - ./train_data/train_list.txt
+    - ./train_data/rec/rec_gt_train.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    # - ./train_data/val_list.txt
+    - ./train_data/rec/ic15_data/rec_gt_test.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_arabic_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/arabic_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_arabic.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/chinese_cht_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_chinese_cht_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/chinese_cht_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_chinese_cht.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/cyrillic_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_cyrillic_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/cyrillic_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_cyrillic.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/devanagari_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_devanagari_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/devanagari_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_devanagari.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/japan_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_japan_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/japan_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_japan.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4

configs/rec/PP-OCRv3/multi_language/ka_PP-OCRv3_rec.yml

+Global:
+  debug: false
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/v3_ka_mobile
+  save_epoch_step: 3
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: true
+  pretrained_model:
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  character_dict_path: ppocr/utils/dict/ka_dict.txt
+  max_text_length: &max_text_length 25
+  infer_mode: false
+  use_space_char: true
+  distributed: true
+  save_res_path: ./output/rec/predicts_ppocrv3_ka.txt
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: L2
+    factor: 3.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SVTR
+  Transform:
+  Backbone:
+    name: MobileNetV1Enhance
+    scale: 0.5
+    last_conv_stride: [1, 2]
+    last_pool_type: avg
+  Head:
+    name: MultiHead
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 64
+            depth: 2
+            hidden_dims: 120
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - SARHead:
+          enc_dim: 512
+          max_text_length: *max_text_length
+
+Loss:
+  name: MultiLoss
+  loss_config_list:
+    - CTCLoss:
+    - SARLoss:
+
+PostProcess:  
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: False
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    ext_op_transform_idx: 1
+    label_file_list:
+    - ./train_data/train_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - RecConAug:
+        prob: 0.5
+        ext_data_num: 2
+        image_shape: [48, 320, 3]
+    - RecAug:
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: true
+    batch_size_per_card: 128
+    drop_last: true
+    num_workers: 4
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data
+    label_file_list:
+    - ./train_data/val_list.txt
+    transforms:
+    - DecodeImage:
+        img_mode: BGR
+        channel_first: false
+    - MultiLabelEncode:
+    - RecResizeImg:
+        image_shape: [3, 48, 320]
+    - KeepKeys:
+        keep_keys:
+        - image
+        - label_ctc
+        - label_sar
+        - length
+        - valid_ratio
+  loader:
+    shuffle: false
+    drop_last: false
+    batch_size_per_card: 128
+    num_workers: 4