dygraph first commit

configs/det/det_db_icdar15_reader.yml

-TrainReader:
-  reader_function: ppocr.data.det.dataset_traversal,TrainReader
-  process_function: ppocr.data.det.db_process,DBProcessTrain
-  num_workers: 8
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
-
-EvalReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.db_process,DBProcessTest
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-  test_image_shape: [736, 1280]
-  
-TestReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.db_process,DBProcessTest
-  infer_img:
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-  test_image_shape: [736, 1280]
-  do_eval: True

configs/det/det_east_icdar15_reader.yml

-TrainReader:
-  reader_function: ppocr.data.det.dataset_traversal,TrainReader
-  process_function: ppocr.data.det.east_process,EASTProcessTrain
-  num_workers: 8
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
-  background_ratio: 0.125
-  min_crop_side_ratio: 0.1
-  min_text_size: 10
-
-EvalReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.east_process,EASTProcessTest
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-  
-TestReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.east_process,EASTProcessTest
-  infer_img:
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-  do_eval: True

configs/det/det_mv3_db.yml

 Global:
-  algorithm: DB
   use_gpu: true
   epoch_num: 1200
   log_smooth_window: 20
   print_batch_step: 2
-  save_model_dir: ./output/det_db/
-  save_epoch_step: 200
+  save_model_dir: ./output/20201010/
+  save_epoch_step: 1200
   # evaluation is run every 5000 iterations after the 4000th iteration
-  eval_batch_step: [4000, 5000]
-  train_batch_size_per_card: 16
-  test_batch_size_per_card: 16
-  image_shape: [3, 640, 640]
-  reader_yml: ./configs/det/det_db_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/MobileNetV3_large_x0_5_pretrained/
-  checkpoints:
-  save_res_path: ./output/det_db/predicts_db.txt
+  eval_batch_step: 8
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  load_static_weights: True
+  cal_metric_during_train: False
+  pretrained_model: /home/zhoujun20/pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: #./output/det_db_0.001_DiceLoss_256_pp_config_2.0b_4gpu/best_accuracy
   save_inference_dir:
+  use_visualdl: True
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
 
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  learning_rate:
+#    name: Cosine
+    lr: 0.001
+#    warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
 
-Backbone:
-  function: ppocr.modeling.backbones.det_mobilenet_v3,MobileNetV3
+Architecture:
+  type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: MobileNetV3
     scale: 0.5
     model_name: large
-
-Head:
-  function: ppocr.modeling.heads.det_db_head,DBHead
-  model_name: large
+  Neck:
+    name: FPN
+    out_channels: 256
+  Head:
+    name: DBHead
     k: 50
-  inner_channels: 96
-  out_channels: 2
 
 Loss:
-  function: ppocr.modeling.losses.det_db_loss,DBLoss
+  name: DBLoss
   balance_loss: true
   main_loss_type: DiceLoss
   alpha: 5
   beta: 10
   ohem_ratio: 3
 
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999
-
 PostProcess:
-  function: ppocr.postprocess.db_postprocess,DBPostProcess
+  name: DBPostProcess
   thresh: 0.3
-  box_thresh: 0.7
+  box_thresh: 0.6
   max_candidates: 1000
-  unclip_ratio: 2.0
+  unclip_ratio: 1.5
+
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+TRAIN:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/detection/
+    file_list:
+      - /home/zhoujun20/detection/train_icdar2015_label.txt # dataset1
+    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'] # dataloader将按照此顺序返回list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size: 16
+    num_workers: 6
+
+EVAL:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/detection/
+    file_list:
+      - /home/zhoujun20/detection/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: 1 # must be 1
+    num_workers: 6
\ No newline at end of file

configs/det/det_mv3_east.yml

-Global:
-  algorithm: EAST
-  use_gpu: true
-  epoch_num: 100000
-  log_smooth_window: 20
-  print_batch_step: 5
-  save_model_dir: ./output/det_east/
-  save_epoch_step: 200
-  eval_batch_step: [5000, 5000]
-  train_batch_size_per_card: 16
-  test_batch_size_per_card: 16
-  image_shape: [3, 512, 512]
-  reader_yml: ./configs/det/det_east_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/MobileNetV3_large_x0_5_pretrained/
-  checkpoints:
-  save_res_path: ./output/det_east/predicts_east.txt
-  save_inference_dir:
-  
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
-
-Backbone:
-  function: ppocr.modeling.backbones.det_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: large
-
-Head:
-  function: ppocr.modeling.heads.det_east_head,EASTHead
-  model_name: small
-  
-Loss:
-  function: ppocr.modeling.losses.det_east_loss,EASTLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999
-
-PostProcess:
-  function: ppocr.postprocess.east_postprocess,EASTPostPocess
-  score_thresh: 0.8
-  cover_thresh: 0.1
-  nms_thresh: 0.2
-  

configs/det/det_r50_vd_db.yml

 Global:
-  algorithm: DB
   use_gpu: true
   epoch_num: 1200
   log_smooth_window: 20
   print_batch_step: 2
-  save_model_dir: ./output/det_db/
-  save_epoch_step: 200
-  eval_batch_step: [5000, 5000]
-  train_batch_size_per_card: 8
-  test_batch_size_per_card: 16
-  image_shape: [3, 640, 640]
-  reader_yml: ./configs/det/det_db_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
-  save_res_path: ./output/det_db/predicts_db.txt
-  checkpoints:
+  save_model_dir: ./output/20201010/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: 8
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  load_static_weights: True
+  cal_metric_during_train: False
+  pretrained_model: /home/zhoujun20/pretrain_models/MobileNetV3_large_x0_5_pretrained
+  checkpoints: #./output/det_db_0.001_DiceLoss_256_pp_config_2.0b_4gpu/best_accuracy
   save_inference_dir:
+  use_visualdl: True
+  infer_img: doc/imgs_en/img_10.jpg
+  save_res_path: ./output/det_db/predicts_db.txt
 
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  learning_rate:
+#    name: Cosine
+    lr: 0.001
+#    warmup_epoch: 0
+  regularizer:
+    name: 'L2'
+    factor: 0
 
-Backbone:
-  function: ppocr.modeling.backbones.det_resnet_vd,ResNet
+Architecture:
+  type: det
+  algorithm: DB
+  Transform:
+  Backbone:
+    name: ResNet
     layers: 50
-
-Head:
-  function: ppocr.modeling.heads.det_db_head,DBHead
-  model_name: large
+  Neck:
+    name: FPN
+    out_channels: 256
+  Head:
+    name: DBHead
     k: 50
-  inner_channels: 256
-  out_channels: 2
 
 Loss:
-  function: ppocr.modeling.losses.det_db_loss,DBLoss
+  name: DBLoss
   balance_loss: true
   main_loss_type: DiceLoss
   alpha: 5
   beta: 10
   ohem_ratio: 3
 
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999
-
 PostProcess:
-  function: ppocr.postprocess.db_postprocess,DBPostProcess
+  name: DBPostProcess
   thresh: 0.3
-  box_thresh: 0.7
+  box_thresh: 0.6
   max_candidates: 1000
   unclip_ratio: 1.5
 
+Metric:
+  name: DetMetric
+  main_indicator: hmean
+
+TRAIN:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/detection/
+    file_list:
+      - /home/zhoujun20/detection/train_icdar2015_label.txt # dataset1
+    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'] # dataloader将按照此顺序返回list
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size: 16
+    num_workers: 6
+
+EVAL:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/detection/
+    file_list:
+      - /home/zhoujun20/detection/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: 1 # must be 1
+    num_workers: 6
\ No newline at end of file

configs/det/det_r50_vd_east.yml

-Global:
-  algorithm: EAST
-  use_gpu: true
-  epoch_num: 100000
-  log_smooth_window: 20
-  print_batch_step: 5
-  save_model_dir: ./output/det_east/
-  save_epoch_step: 200
-  eval_batch_step: [5000, 5000]
-  train_batch_size_per_card: 8
-  test_batch_size_per_card: 16
-  image_shape: [3, 512, 512]
-  reader_yml: ./configs/det/det_east_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
-  save_res_path: ./output/det_east/predicts_east.txt
-  checkpoints:
-  save_inference_dir:
-
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
-
-Backbone:
-  function: ppocr.modeling.backbones.det_resnet_vd,ResNet
-  layers: 50
-
-Head:
-  function: ppocr.modeling.heads.det_east_head,EASTHead
-  model_name: large
-  
-Loss:
-  function: ppocr.modeling.losses.det_east_loss,EASTLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999
-
-PostProcess:
-  function: ppocr.postprocess.east_postprocess,EASTPostPocess
-  score_thresh: 0.8
-  cover_thresh: 0.1
-  nms_thresh: 0.2
-  

configs/det/det_r50_vd_sast_icdar15.yml

-Global:
-  algorithm: SAST
-  use_gpu: true
-  epoch_num: 2000
-  log_smooth_window: 20
-  print_batch_step: 2
-  save_model_dir: ./output/det_sast/
-  save_epoch_step: 20
-  eval_batch_step: 5000
-  train_batch_size_per_card: 8
-  test_batch_size_per_card: 8
-  image_shape: [3, 512, 512]
-  reader_yml: ./configs/det/det_sast_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
-  save_res_path: ./output/det_sast/predicts_sast.txt
-  checkpoints: 
-  save_inference_dir:
-
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
-
-Backbone:
-  function: ppocr.modeling.backbones.det_resnet_vd_sast,ResNet
-  layers: 50
-
-Head:
-  function: ppocr.modeling.heads.det_sast_head,SASTHead
-  model_name: large
-  only_fpn_up: False
-#   with_cab: False
-  with_cab: True
-
-Loss:
-  function: ppocr.modeling.losses.det_sast_loss,SASTLoss
-
-Optimizer:
-  function: ppocr.optimizer,RMSProp
-  base_lr: 0.001
-  decay:
-    function: piecewise_decay
-    boundaries: [30000, 50000, 80000, 100000, 150000]
-    decay_rate: 0.3
-
-PostProcess:
-  function: ppocr.postprocess.sast_postprocess,SASTPostProcess
-  score_thresh: 0.5
-  sample_pts_num: 2
-  nms_thresh: 0.2
-  expand_scale: 1.0
-  shrink_ratio_of_width: 0.3
\ No newline at end of file

configs/det/det_r50_vd_sast_totaltext.yml

-Global:
-  algorithm: SAST
-  use_gpu: true
-  epoch_num: 2000
-  log_smooth_window: 20
-  print_batch_step: 2
-  save_model_dir: ./output/det_sast/
-  save_epoch_step: 20
-  eval_batch_step: 5000
-  train_batch_size_per_card: 8
-  test_batch_size_per_card: 1
-  image_shape: [3, 512, 512]
-  reader_yml: ./configs/det/det_sast_totaltext_reader.yml
-  pretrain_weights: ./pretrain_models/ResNet50_vd_ssld_pretrained/
-  save_res_path: ./output/det_sast/predicts_sast.txt
-  checkpoints:
-  save_inference_dir:
-
-Architecture:
-  function: ppocr.modeling.architectures.det_model,DetModel
-
-Backbone:
-  function: ppocr.modeling.backbones.det_resnet_vd_sast,ResNet
-  layers: 50
-
-Head:
-  function: ppocr.modeling.heads.det_sast_head,SASTHead
-  model_name: large
-  only_fpn_up: False
-  # with_cab: False
-  with_cab: True
-
-Loss:
-  function: ppocr.modeling.losses.det_sast_loss,SASTLoss
-
-Optimizer:
-  function: ppocr.optimizer,RMSProp
-  base_lr: 0.001
-  decay:
-    function: piecewise_decay
-    boundaries: [30000, 50000, 80000, 100000, 150000]
-    decay_rate: 0.3
-
-PostProcess:
-  function: ppocr.postprocess.sast_postprocess,SASTPostProcess
-  score_thresh: 0.5
-  sample_pts_num: 6
-  nms_thresh: 0.2
-  expand_scale: 1.2
-  shrink_ratio_of_width: 0.2
\ No newline at end of file

configs/det/det_sast_icdar15_reader.yml

-TrainReader:
-  reader_function: ppocr.data.det.dataset_traversal,TrainReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTrain
-  num_workers: 8
-  img_set_dir: ./train_data/
-  label_file_path: [./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]
-  data_ratio_list: [0.1, 0.45, 0.3, 0.15]
-  min_crop_side_ratio: 0.3
-  min_crop_size: 24
-  min_text_size: 4
-  max_text_size: 512
-
-EvalReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTest
-  img_set_dir: ./train_data/icdar2015/text_localization/
-  label_file_path: ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
-  max_side_len: 1536
-  
-TestReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTest
-  infer_img: ./train_data/icdar2015/text_localization/ch4_test_images/img_11.jpg
-  max_side_len: 1536

configs/det/det_sast_totaltext_reader.yml

-TrainReader:
-  reader_function: ppocr.data.det.dataset_traversal,TrainReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTrain
-  num_workers: 8
-  img_set_dir: ./train_data/
-  label_file_path: [./train_data/art_latin_icdar_14pt/train_no_tt_test/train_label_json.txt, ./train_data/total_text_icdar_14pt/train_label_json.txt]
-  data_ratio_list: [0.5, 0.5]
-  min_crop_side_ratio: 0.3
-  min_crop_size: 24
-  min_text_size: 4
-  max_text_size: 512
-
-EvalReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTest
-  img_set_dir: ./train_data/
-  label_file_path: ./train_data/total_text_icdar_14pt/test_label_json.txt
-  max_side_len: 768
-  
-TestReader:
-  reader_function: ppocr.data.det.dataset_traversal,EvalTestReader
-  process_function: ppocr.data.det.sast_process,SASTProcessTest
-  infer_img: ./train_data/afs/total_text/Images/Test/img623.jpg
-  max_side_len: 768

configs/rec/rec_benchmark_reader.yml

-TrainReader:
-  reader_function: ppocr.data.rec.dataset_traversal,LMDBReader
-  num_workers: 8
-  lmdb_sets_dir: ./train_data/data_lmdb_release/training/
-  
-EvalReader:
-  reader_function: ppocr.data.rec.dataset_traversal,LMDBReader
-  lmdb_sets_dir: ./train_data/data_lmdb_release/validation/
-
-TestReader:
-  reader_function: ppocr.data.rec.dataset_traversal,LMDBReader
-  lmdb_sets_dir: ./train_data/data_lmdb_release/evaluation/

configs/rec/rec_chinese_common_train.yml

-Global:
-  algorithm: CRNN
-  use_gpu: true
-  epoch_num: 3000
-  log_smooth_window: 20
-  print_batch_step: 10
-  save_model_dir: ./output/rec_CRNN
-  save_epoch_step: 3
-  eval_batch_step: 2000
-  train_batch_size_per_card: 128
-  test_batch_size_per_card: 128
-  image_shape: [3, 32, 320]
-  max_text_length: 25
-  character_type: ch
-  character_dict_path: ./ppocr/utils/ppocr_keys_v1.txt
-  loss_type: ctc
-  distort: false
-  use_space_char: false
-  reader_yml: ./configs/rec/rec_chinese_reader.yml
-  pretrain_weights:
-  checkpoints:
-  save_inference_dir:
-  infer_img:
-
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
-
-Backbone:
-  function: ppocr.modeling.backbones.rec_resnet_vd,ResNet
-  layers: 34
-
-Head:
-  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
-  encoder_type: rnn
-  SeqRNN:
-    hidden_size: 256
-    
-Loss:
-  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.0005
-  beta1: 0.9
-  beta2: 0.999

configs/rec/rec_chinese_lite_train.yml

-Global:
-  algorithm: CRNN
-  use_gpu: true
-  epoch_num: 3000
-  log_smooth_window: 20
-  print_batch_step: 10
-  save_model_dir: ./output/rec_CRNN
-  save_epoch_step: 3
-  eval_batch_step: 2000
-  train_batch_size_per_card: 256
-  test_batch_size_per_card: 256
-  image_shape: [3, 32, 320]
-  max_text_length: 25
-  character_type: ch
-  character_dict_path: ./ppocr/utils/ppocr_keys_v1.txt
-  loss_type: ctc
-  distort: false
-  use_space_char: false
-  reader_yml: ./configs/rec/rec_chinese_reader.yml
-  pretrain_weights:
-  checkpoints:
-  save_inference_dir:
-  infer_img:
-
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
-
-Backbone:
-  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: small
-
-Head:
-  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
-  encoder_type: rnn
-  SeqRNN:
-    hidden_size: 48
-    
-Loss:
-  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.0005
-  beta1: 0.9
-  beta2: 0.999

configs/rec/rec_chinese_reader.yml

-TrainReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  num_workers: 8
-  img_set_dir: ./train_data
-  label_file_path: ./train_data/rec_gt_train.txt
-  
-EvalReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  img_set_dir: ./train_data
-  label_file_path: ./train_data/rec_gt_test.txt
-
-TestReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader

configs/rec/rec_icdar15_reader.yml

-TrainReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  num_workers: 8
-  img_set_dir: ./train_data/ic15_data
-  label_file_path: ./train_data/ic15_data/rec_gt_train.txt
-  
-EvalReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader
-  img_set_dir: ./train_data/ic15_data
-  label_file_path: ./train_data/ic15_data/rec_gt_test.txt
-
-TestReader:
-  reader_function: ppocr.data.rec.dataset_traversal,SimpleReader

configs/rec/rec_icdar15_train.yml

-Global:
-  algorithm: CRNN
-  use_gpu: true
-  epoch_num: 1000
-  log_smooth_window: 20
-  print_batch_step: 10
-  save_model_dir: ./output/rec_CRNN
-  save_epoch_step: 300
-  eval_batch_step: 500
-  train_batch_size_per_card: 256
-  test_batch_size_per_card: 256
-  image_shape: [3, 32, 100]
-  max_text_length: 25
-  character_type: en
-  loss_type: ctc
-  distort: true
-  debug: false
-  reader_yml: ./configs/rec/rec_icdar15_reader.yml
-  pretrain_weights: ./pretrain_models/rec_mv3_none_bilstm_ctc/best_accuracy
-  checkpoints:
-  save_inference_dir:
-  infer_img:
-
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
-
-Backbone:
-  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: large
-
-Head:
-  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
-  encoder_type: rnn
-  SeqRNN:
-    hidden_size: 96
-    
-Loss:
-  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.0005
-  beta1: 0.9
-  beta2: 0.999
-  decay:
-    function: cosine_decay
-    step_each_epoch: 20
-    total_epoch: 1000

configs/rec/rec_mv3_none_bilstm_ctc.yml

 Global:
-  algorithm: CRNN
-  use_gpu: true
-  epoch_num: 72
+  use_gpu: false
+  epoch_num: 500
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: output/rec_CRNN
-  save_epoch_step: 3
-  eval_batch_step: 2000
-  train_batch_size_per_card: 256
-  test_batch_size_per_card: 256
-  image_shape: [3, 32, 100]
-  max_text_length: 25
-  character_type: en
-  loss_type: ctc
-  reader_yml: ./configs/rec/rec_benchmark_reader.yml
-  pretrain_weights:
-  checkpoints:
+  save_model_dir: ./output/rec/test/
+  save_epoch_step: 500
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: 127
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  load_static_weights: True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: #output/rec/rec_crnn/best_accuracy
   save_inference_dir:
-  infer_img:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  max_text_length: 80
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  character_type: 'ch'
+  use_space_char: False
+  infer_mode: False
+  use_tps: False
 
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
 
-Backbone:
-  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: large
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  learning_rate:
+    name: Cosine
+    lr: 0.001
+    warmup_epoch: 4
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
 
-Head:
-  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
-  encoder_type: rnn
-  SeqRNN:
+Architecture:
+  type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [ 1, 2, 2, 2 ]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: fc
     hidden_size: 96
+  Head:
+    name: CTC
+    fc_decay: 0.00001
 
 Loss:
-  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
+  name: CTCLoss
 
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+TRAIN:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/rec
+    file_list:
+      - /home/zhoujun20/rec/real_data.txt # dataset1
+    ratio_list: [ 0.4,0.6 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecAug:
+      - RecResizeImg:
+          image_shape: [ 3,32,320 ]
+      - keepKeys:
+          keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
+  loader:
+    batch_size: 256
+    shuffle: True
+    drop_last: True
+    num_workers: 6
+
+EVAL:
+  dataset:
+    name: SimpleDataSet
+    data_dir: /home/zhoujun20/rec
+    file_list:
+      - /home/zhoujun20/rec/label_val_all.txt
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [ 3,32,320 ]
+      - keepKeys:
+          keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size: 256
+    num_workers: 6

configs/rec/rec_mv3_none_bilstm_ctc_lmdb.yml

+Global:
+  use_gpu: true
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 1
+  save_model_dir: ./output/rec/test/
+  save_epoch_step: 500
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: 1016
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  load_static_weights: True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: #output/rec/rec_crnn/best_accuracy
+  save_inference_dir:
+  use_visualdl: True
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  max_text_length: 80
+  character_dict_path: /home/zhoujun20/rec/lmdb/dict.txt
+  character_type: 'ch'
+  use_space_char: True
+  infer_mode: False
+  use_tps: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  learning_rate:
+    name: Cosine
+    lr: 0.0005
+    warmup_epoch: 1
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: small
+    small_stride: [ 1, 2, 2, 2 ]
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 48
+  Head:
+    name: CTC
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+TRAIN:
+  dataset:
+    name: LMDBDateSet
+    file_list:
+      - /home/zhoujun20/rec/lmdb/train # dataset1
+    ratio_list: [ 0.4,0.6 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecAug:
+      - RecResizeImg:
+          image_shape: [ 3,32,320 ]
+      - keepKeys:
+          keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
+  loader:
+    batch_size: 256
+    shuffle: True
+    drop_last: True
+    num_workers: 6
+
+EVAL:
+  dataset:
+    name: LMDBDateSet
+    file_list:
+      - /home/zhoujun20/rec/lmdb/val
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [ 3,32,320 ]
+      - keepKeys:
+          keep_keys: [ 'image','label','length' ] # dataloader将按照此顺序返回list
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size: 256
+    num_workers: 6

configs/rec/rec_mv3_none_none_ctc.yml

-Global:
-  algorithm: Rosetta
-  use_gpu: true
-  epoch_num: 72
-  log_smooth_window: 20
-  print_batch_step: 10
-  save_model_dir: output/rec_Rosetta
-  save_epoch_step: 3
-  eval_batch_step: 2000
-  train_batch_size_per_card: 256
-  test_batch_size_per_card: 256
-  image_shape: [3, 32, 100]
-  max_text_length: 25
-  character_type: en
-  loss_type: ctc
-  reader_yml: ./configs/rec/rec_benchmark_reader.yml
-  pretrain_weights: 
-  checkpoints:
-  save_inference_dir:
-  infer_img:
-
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
-
-Backbone:
-  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: large
-
-Head:
-  function: ppocr.modeling.heads.rec_ctc_head,CTCPredict
-  encoder_type: reshape
-  
-Loss:
-  function: ppocr.modeling.losses.rec_ctc_loss,CTCLoss
-
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999

configs/rec/rec_mv3_tps_bilstm_attn.yml

-Global:
-  algorithm: RARE
-  use_gpu: true
-  epoch_num: 72
-  log_smooth_window: 20
-  print_batch_step: 10
-  save_model_dir: output/rec_RARE
-  save_epoch_step: 3
-  eval_batch_step: 2000
-  train_batch_size_per_card: 256
-  test_batch_size_per_card: 256
-  image_shape: [3, 32, 100]
-  max_text_length: 25
-  character_type: en
-  loss_type: attention
-  tps: true
-  reader_yml: ./configs/rec/rec_benchmark_reader.yml
-  pretrain_weights:
-  checkpoints:
-  save_inference_dir:
-  infer_img:
-
-
-Architecture:
-  function: ppocr.modeling.architectures.rec_model,RecModel
-
-TPS:
-  function: ppocr.modeling.stns.tps,TPS
-  num_fiducial: 20
-  loc_lr: 0.1
-  model_name: small
-  
-Backbone:
-  function: ppocr.modeling.backbones.rec_mobilenet_v3,MobileNetV3
-  scale: 0.5
-  model_name: large
- 
-Head:
-  function: ppocr.modeling.heads.rec_attention_head,AttentionPredict
-  encoder_type: rnn
-  SeqRNN:
-    hidden_size: 96
-  Attention:
-    decoder_size: 96
-    word_vector_dim: 96
-  
-Loss:
-  function: ppocr.modeling.losses.rec_attention_loss,AttentionLoss
-  
-Optimizer:
-  function: ppocr.optimizer,AdamDecay
-  base_lr: 0.001
-  beta1: 0.9
-  beta2: 0.999