Merge branch 'dygraph' into lite

configs/det/det_r50_vd_db.yml

@@ -7,7 +7,10 @@ Global:
   save_epoch_step: 1200
   # evaluation is run every 2000 iterations
   eval_batch_step: [0,2000]
-  # if pretrained_model is saved in static mode, load_static_weights must set to True
+  # 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: True
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained

configs/det/det_r50_vd_east.yml

@@ -7,7 +7,10 @@ Global:
   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
+  # 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: True
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet50_vd_pretrained/

configs/det/det_r50_vd_sast_icdar15.yml

@@ -7,7 +7,10 @@ Global:
   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
+  # 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: True
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/

configs/det/det_r50_vd_sast_totaltext.yml

@@ -7,7 +7,10 @@ Global:
   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
+  # 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: True
   cal_metric_during_train: False
   pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained/

configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml

@@ -7,7 +7,6 @@ Global:
   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:

configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml

@@ -7,7 +7,6 @@ Global:
   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: 

configs/rec/multi_language/generate_multi_language_configs.py

@@ -131,7 +131,7 @@ if __name__ == '__main__':
     if FLAGS.val:
         global_config['Eval']['dataset']['label_file_list'] = [FLAGS.val]
         eval_label_path = os.path.join(project_path,FLAGS.val)
-        loss_file(Eval_label_path)
+        loss_file(eval_label_path)
     if FLAGS.dict:
         global_config['Global']['character_dict_path'] = FLAGS.dict
         dict_path = os.path.join(project_path,FLAGS.dict)

configs/rec/multi_language/rec_en_number_lite_train.yml

@@ -16,7 +16,7 @@ Global:
   infer_img:
   # for data or label process
   character_dict_path: ppocr/utils/dict/en_dict.txt
-  character_type: ch
+  character_type: EN
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_icdar15_train.yml

@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:

configs/rec/rec_mv3_none_bilstm_ctc.yml

 Global:
-  use_gpu: true
+  use_gpu: True
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -59,7 +58,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -78,7 +77,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_mv3_none_none_ctc.yml

@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -58,7 +57,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -77,7 +76,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_mv3_tps_bilstm_att.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/rec_mv3_tps_bilstm_att/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  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
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0.00001
+
+Architecture:
+  model_type: rec
+  algorithm: RARE
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: small
+  Backbone:
+    name: MobileNetV3
+    scale: 0.5
+    model_name: large
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn 
+    hidden_size: 96
+  Head:
+    name: AttentionHead  
+    hidden_size: 96
+    
+
+Loss:
+  name: AttentionLoss
+
+PostProcess:
+  name: AttnLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - 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: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - 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: 1

configs/rec/rec_mv3_tps_bilstm_ctc.yml

 Global:
-  use_gpu: true
+  use_gpu: True
   epoch_num: 72
   log_smooth_window: 20
   print_batch_step: 10
@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -63,7 +62,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -82,7 +81,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_none_bilstm_ctc.yml

@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -58,7 +57,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -77,7 +76,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_none_none_ctc.yml

@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -56,7 +55,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -75,7 +74,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r34_vd_tps_bilstm_att.yml

+Global:
+  use_gpu: True
+  epoch_num: 400
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/b3_rare_r34_none_gru/
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  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
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    learning_rate: 0.0005
+  regularizer:
+    name: 'L2'
+    factor: 0.00000
+
+Architecture:
+  model_type: rec
+  algorithm: RARE
+  Transform:
+    name: TPS
+    num_fiducial: 20
+    loc_lr: 0.1
+    model_name: large
+  Backbone:
+    name: ResNet  
+    layers: 34
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn 
+    hidden_size: 256 #96
+  Head:
+    name: AttentionHead  # AttentionHead
+    hidden_size: 256 #
+    l2_decay: 0.00001
+
+Loss:
+  name: AttentionLoss
+
+PostProcess:
+  name: AttnLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - 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: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - AttnLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 100]
+      - 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/rec_r34_vd_tps_bilstm_ctc.yml

@@ -7,7 +7,6 @@ Global:
   save_epoch_step: 3
   # evaluation is run every 2000 iterations
   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:
@@ -62,7 +61,7 @@ Metric:
 
 Train:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/training/
     transforms:
       - DecodeImage: # load image
@@ -81,7 +80,7 @@ Train:
 
 Eval:
   dataset:
-    name: LMDBDateSet
+    name: LMDBDataSet
     data_dir: ./train_data/data_lmdb_release/validation/
     transforms:
       - DecodeImage: # load image

configs/rec/rec_r50_fpn_srn.yml

+Global:
+  use_gpu: True
+  epoch_num: 72
+  log_smooth_window: 20
+  print_batch_step: 5
+  save_model_dir: ./output/rec/srn_new
+  save_epoch_step: 3
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 5000]
+  cal_metric_during_train: True
+  pretrained_model: 
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path: 
+  character_type: en
+  max_text_length: 25
+  num_heads: 8
+  infer_mode: False
+  use_space_char: False
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  clip_norm: 10.0
+  lr:
+    learning_rate: 0.0001
+
+Architecture:
+  model_type: rec
+  algorithm: SRN
+  in_channels: 1
+  Transform:
+  Backbone:
+    name: ResNetFPN
+  Head:
+    name: SRNHead
+    max_text_length: 25
+    num_heads: 8
+    num_encoder_TUs: 2
+    num_decoder_TUs: 4
+    hidden_dims: 512
+
+Loss:
+  name: SRNLoss
+
+PostProcess:
+  name: SRNLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SRNLabelEncode: # Class handling label
+      - SRNRecResizeImg:
+          image_shape: [1, 64, 256]
+      - KeepKeys:
+          keep_keys: ['image',
+                      'label',
+                      'length',
+                      'encoder_word_pos',
+                      'gsrm_word_pos',
+                      'gsrm_slf_attn_bias1',
+                      'gsrm_slf_attn_bias2'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    batch_size_per_card: 64
+    drop_last: False
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/validation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SRNLabelEncode: # Class handling label
+      - SRNRecResizeImg:
+          image_shape: [1, 64, 256]
+      - KeepKeys:
+          keep_keys: ['image',
+                      'label',
+                      'length',
+                      'encoder_word_pos',
+                      'gsrm_word_pos',
+                      'gsrm_slf_attn_bias1',
+                      'gsrm_slf_attn_bias2'] 
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 32
+    num_workers: 4

deploy/cpp_infer/CMakeLists.txt

@@ -133,7 +133,11 @@ if(WITH_MKL)
     endif ()
   endif()
 else()
-  set(MATH_LIB ${PADDLE_LIB}/third_party/install/openblas/lib/libopenblas${CMAKE_STATIC_LIBRARY_SUFFIX})
+  if (WIN32)
+    set(MATH_LIB ${PADDLE_LIB}/third_party/install/openblas/lib/openblas${CMAKE_STATIC_LIBRARY_SUFFIX})
+  else ()
+    set(MATH_LIB ${PADDLE_LIB}/third_party/install/openblas/lib/libopenblas${CMAKE_STATIC_LIBRARY_SUFFIX})
+  endif ()
 endif()
 
 # Note: libpaddle_inference_api.so/a must put before libpaddle_fluid.so/a
@@ -157,7 +161,7 @@ endif(WITH_STATIC_LIB)
 
 if (NOT WIN32)
     set(DEPS ${DEPS}
-        ${MATH_LIB} ${MKLDNN_LIB} 
+        ${MATH_LIB} ${MKLDNN_LIB}
         glog gflags protobuf z xxhash
         )
     if(EXISTS "${PADDLE_LIB}/third_party/install/snappystream/lib")

deploy/cpp_infer/docs/windows_vs2019_build.md

@@ -14,7 +14,7 @@ PaddleOCR在Windows 平台下基于`Visual Studio 2019 Community` 进行了测
 
 ### Step1: 下载PaddlePaddle C++ 预测库 fluid_inference
 
-PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载:  [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/advanced_guide/inference_deployment/inference/windows_cpp_inference.html)
+PaddlePaddle C++ 预测库针对不同的`CPU`和`CUDA`版本提供了不同的预编译版本，请根据实际情况下载:  [C++预测库下载列表](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/05_inference_deployment/inference/windows_cpp_inference.html)
 
 解压后`D:\projects\fluid_inference`目录包含内容为：
 ```