Merge pull request #13 from PaddlePaddle/dygraph

Dygraph

MANIFEST.in

 include LICENSE.txt
 include README.md
 
-recursive-include ppocr/utils *.txt utility.py character.py check.py
-recursive-include ppocr/data/det *.py
+recursive-include ppocr/utils *.txt utility.py logging.py
+recursive-include ppocr/data/ *.py
 recursive-include ppocr/postprocess *.py
-recursive-include ppocr/postprocess/lanms *.*
-recursive-include tools/infer *.py
+recursive-include tools/infer *.py
\ No newline at end of file

configs/det/ch_ppocr_v2.0/ch_det_mv3_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_mv3/
+  save_epoch_step: 1200
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [3000, 2000]
+  # 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: ./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: 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: MobileNetV3
+    scale: 0.5
+    model_name: large
+    disable_se: True
+  Neck:
+    name: DBFPN
+    out_channels: 96
+  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/det/ch_ppocr_v2.0/ch_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]
+  # 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: ./pretrain_models/ResNet18_vd_pretrained
+  checkpoints: #./output/det_db_0.001_DiceLoss_256_pp_config_2.0b_4gpu/best_accuracy
+  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/det/det_mv3_east.yml

+Global:
+  use_gpu: true
+  epoch_num: 10000
+  log_smooth_window: 20
+  print_batch_step: 2
+  save_model_dir: ./output/east_mv3/
+  save_epoch_step: 1000
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [4000, 5000]
+  # 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: ./pretrain_models/MobileNetV3_large_x0_5_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: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: EASTFPN
+    model_name: small
+  Head:
+    name: EASTHead
+    model_name: small
+
+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: 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
+    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_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]
+  # 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: ./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_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]
+  # 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: ./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_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]
+    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
\ No newline at end of file

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]
+  # 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: ./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
+    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/
+    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/rec/ch_ppocr_v1.1/rec_chinese_common_train_v1.1.yaml → configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yaml

@@ -3,7 +3,7 @@ Global:
   epoch_num: 500
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: ./output/rec_chinese_common_v1.1
+  save_model_dir: ./output/rec_chinese_common_v2.0
   save_epoch_step: 3
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [0, 2000]

configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yaml → configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yaml

@@ -3,7 +3,7 @@ Global:
   epoch_num: 500
   log_smooth_window: 20
   print_batch_step: 10
-  save_model_dir: ./output/rec_chinese_lite_v1.1
+  save_model_dir: ./output/rec_chinese_lite_v2.0
   save_epoch_step: 3
   # evaluation is run every 5000 iterations after the 4000th iteration
   eval_batch_step: [0, 2000]
@@ -19,7 +19,7 @@ Global:
   character_type: ch
   max_text_length: 25
   infer_mode: False
-  use_space_char: False
+  use_space_char: True
 
 
 Optimizer:

configs/rec/multi_language/rec_en_number_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_en_number_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/en_dict.txt
+  character_type: ch
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_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: CTCHead
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/train_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.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 will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_french_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_french_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints: 
+  save_inference_dir: 
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/french_dict.txt
+  character_type: french
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_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: CTCHead
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/train_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.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 will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_german_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_german_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/german_dict.txt
+  character_type: german
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_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: CTCHead
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/train_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.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 will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_japan_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_japan_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/japan_dict.txt
+  character_type: japan
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_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: CTCHead
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/train_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.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 will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

configs/rec/multi_language/rec_korean_lite_train.yml

+Global:
+  use_gpu: True
+  epoch_num: 500
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec_korean_lite
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 2000]
+  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img:
+  # for data or label process
+  character_dict_path: ppocr/utils/dict/korean_dict.txt
+  character_type: korean
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_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: CTCHead
+    fc_decay: 0.00001
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/train_list.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/eval_list.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 will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 256
+    num_workers: 8

deploy/cpp_infer/src/ocr_cls.cpp

@@ -81,7 +81,7 @@ cv::Mat Classifier::Run(cv::Mat &img) {
 
 void Classifier::LoadModel(const std::string &model_dir) {
   AnalysisConfig config;
-  config.SetModel(model_dir + "/model", model_dir + "/params");
+  config.SetModel(model_dir + ".pdmodel", model_dir + ".pdiparams");
 
   if (this->use_gpu_) {
     config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);

deploy/cpp_infer/src/ocr_det.cpp

@@ -18,7 +18,7 @@ namespace PaddleOCR {
 
 void DBDetector::LoadModel(const std::string &model_dir) {
   AnalysisConfig config;
-  config.SetModel(model_dir + "/model", model_dir + "/params");
+  config.SetModel(model_dir + ".pdmodel", model_dir + ".pdiparams");
 
   if (this->use_gpu_) {
     config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);

deploy/cpp_infer/src/ocr_rec.cpp

@@ -103,7 +103,7 @@ void CRNNRecognizer::Run(std::vector<std::vector<std::vector<int>>> boxes,
 
 void CRNNRecognizer::LoadModel(const std::string &model_dir) {
   AnalysisConfig config;
-  config.SetModel(model_dir + "/model", model_dir + "/params");
+  config.SetModel(model_dir + ".pdmodel", model_dir + ".pdiparams");
 
   if (this->use_gpu_) {
     config.EnableUseGpu(this->gpu_mem_, this->gpu_id_);
@@ -186,4 +186,4 @@ cv::Mat CRNNRecognizer::GetRotateCropImage(const cv::Mat &srcimage,
   }
 }
 
-} // namespace PaddleOCR
\ No newline at end of file
+} // namespace PaddleOCR

deploy/docker/hubserving/README.md

+English | [简体中文](README_cn.md)
+
+## Introduction
+Many users hope package the PaddleOCR service into a docker image, so that it can be quickly released and used in the docker or k8s environment.
+
+This page provides some standardized code to achieve this goal. You can quickly publish the PaddleOCR project into a callable Restful API service through the following steps. (At present, the deployment based on the HubServing mode is implemented first, and author plans to increase the deployment of the PaddleServing mode in the futrue)
+
+## 1. Prerequisites
+
+You need to install the following basic components first：
+a. Docker
+b. Graphics driver and CUDA 10.0+（GPU）
+c. NVIDIA Container Toolkit（GPU，Docker 19.03+ can skip this）
+d. cuDNN 7.6+（GPU）
+
+## 2. Build Image
+a. Goto Dockerfile directory（ps：Need to distinguish between cpu and gpu version, the following takes cpu as an example, gpu version needs to replace the keyword）
+```
+cd deploy/docker/hubserving/cpu
+```
+c. Build image
+```
+docker build -t paddleocr:cpu .
+```
+
+## 3. Start container
+a. CPU version
+```
+sudo docker run -dp 8868:8868 --name paddle_ocr paddleocr:cpu
+```
+b. GPU version (base on NVIDIA Container Toolkit)
+```
+sudo nvidia-docker run -dp 8868:8868 --name paddle_ocr paddleocr:gpu
+```
+c. GPU version (Docker 19.03++)
+```
+sudo docker run -dp 8868:8868 --gpus all --name paddle_ocr paddleocr:gpu
+```
+d. Check service status（If you can see the following statement then it means completed：Successfully installed ocr_system && Running on http://0.0.0.0:8868/）
+```
+docker logs -f paddle_ocr
+```
+
+## 4. Test
+a. Calculate the Base64 encoding of the picture to be recognized (if you just test, you can use a free online tool, like：https://freeonlinetools24.com/base64-image/）
+b. Post a service request（sample request in sample_request.txt）
+
+```
+curl -H "Content-Type:application/json" -X POST --data "{\"images\": [\"Input image Base64 encode(need to delete the code 'data:image/jpg;base64,'）\"]}" http://localhost:8868/predict/ocr_system
+```
+c. Get resposne（If the call is successful, the following result will be returned）
+```
+{"msg":"","results":[[{"confidence":0.8403433561325073,"text":"约定","text_region":[[345,377],[641,390],[634,540],[339,528]]},{"confidence":0.8131805658340454,"text":"最终相遇","text_region":[[356,532],[624,530],[624,596],[356,598]]}]],"status":"0"}
+```

deploy/docker/hubserving/README_cn.md

+[English](README.md) | 简体中文
+
+## Docker化部署服务
+在日常项目应用中，相信大家一般都会希望能通过Docker技术，把PaddleOCR服务打包成一个镜像，以便在Docker或k8s环境里，快速发布上线使用。
+
+本文将提供一些标准化的代码来实现这样的目标。大家通过如下步骤可以把PaddleOCR项目快速发布成可调用的Restful API服务。（目前暂时先实现了基于HubServing模式的部署，后续作者计划增加PaddleServing模式的部署）
+
+## 1.实施前提准备
+
+需要先完成如下基本组件的安装：
+a. Docker环境
+b. 显卡驱动和CUDA 10.0+（GPU）
+c. NVIDIA Container Toolkit（GPU，Docker 19.03以上版本可以跳过此步）
+d. cuDNN 7.6+（GPU）
+
+## 2.制作镜像
+a.切换至Dockerfile目录（注：需要区分cpu或gpu版本，下文以cpu为例，gpu版本需要替换一下关键字即可）
+```
+cd deploy/docker/hubserving/cpu
+```
+c.生成镜像
+```
+docker build -t paddleocr:cpu .
+```
+
+## 3.启动Docker容器
+a. CPU 版本
+```
+sudo docker run -dp 8868:8868 --name paddle_ocr paddleocr:cpu
+```
+b. GPU 版本 (通过NVIDIA Container Toolkit)
+```
+sudo nvidia-docker run -dp 8868:8868 --name paddle_ocr paddleocr:gpu
+```
+c. GPU 版本 (Docker 19.03以上版本，可以直接用如下命令)
+```
+sudo docker run -dp 8868:8869 --gpus all --name paddle_ocr paddleocr:gpu
+```
+d. 检查服务运行情况（出现：Successfully installed ocr_system和Running on http://0.0.0.0:8868 等信息，表示运行成功）
+```
+docker logs -f paddle_ocr
+```
+
+## 4.测试服务
+a. 计算待识别图片的Base64编码（如果只是测试一下效果，可以通过免费的在线工具实现，如：http://tool.chinaz.com/tools/imgtobase/）
+b. 发送服务请求（可参见sample_request.txt中的值）
+```
+curl -H "Content-Type:application/json" -X POST --data "{\"images\": [\"填入图片Base64编码(需要删除'data:image/jpg;base64,'）\"]}" http://localhost:8868/predict/ocr_system
+```
+c. 返回结果（如果调用成功，会返回如下结果）
+```
+{"msg":"","results":[[{"confidence":0.8403433561325073,"text":"约定","text_region":[[345,377],[641,390],[634,540],[339,528]]},{"confidence":0.8131805658340454,"text":"最终相遇","text_region":[[356,532],[624,530],[624,596],[356,598]]}]],"status":"0"}
+```

deploy/docker/hubserving/cpu/Dockerfile

+# Version: 1.0.0
+FROM hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda10.0-cudnn7-dev
+
+# PaddleOCR base on Python3.7
+RUN pip3.7 install --upgrade pip -i https://mirror.baidu.com/pypi/simple
+
+RUN python3.7 -m pip install paddlepaddle==2.0.0rc0 -i https://mirror.baidu.com/pypi/simple
+
+RUN pip3.7 install paddlehub --upgrade -i https://mirror.baidu.com/pypi/simple
+
+RUN git clone https://github.com/PaddlePaddle/PaddleOCR.git /PaddleOCR
+
+WORKDIR /PaddleOCR
+
+RUN pip3.7 install -r requirements.txt -i https://mirror.baidu.com/pypi/simple
+
+RUN mkdir -p /PaddleOCR/inference/
+# Download orc detect model(light version). if you want to change normal version, you can change ch_ppocr_mobile_v1.1_det_infer to ch_ppocr_server_v1.1_det_infer, also remember change det_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD {link} /PaddleOCR/inference/
+RUN tar xf /PaddleOCR/inference/{file} -C /PaddleOCR/inference/
+
+# Download direction classifier(light version). If you want to change normal version, you can change ch_ppocr_mobile_v1.1_cls_infer to ch_ppocr_mobile_v1.1_cls_infer, also remember change cls_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD {link} /PaddleOCR/inference/
+RUN tar xf /PaddleOCR/inference/{file}.tar -C /PaddleOCR/inference/
+
+# Download orc recognition model(light version). If you want to change normal version, you can change ch_ppocr_mobile_v1.1_rec_infer to ch_ppocr_server_v1.1_rec_infer, also remember change rec_model_dir in deploy/hubserving/ocr_system/params.py）
+ADD {link} /PaddleOCR/inference/
+RUN tar xf /PaddleOCR/inference/{file}.tar -C /PaddleOCR/inference/
+
+EXPOSE 8868
+
+CMD ["/bin/bash","-c","hub install deploy/hubserving/ocr_system/ && hub serving start -m ocr_system"]
\ No newline at end of file