Merge branch 'PaddlePaddle:dygraph' into dygraph

configs/rec/multi_language/rec_korean_lite_train.yml

@@ -16,7 +16,6 @@ Global:
   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

configs/rec/multi_language/rec_latin_lite_train.yml

@@ -15,7 +15,6 @@ Global:
   use_visualdl: false
   infer_img: null
   character_dict_path: ppocr/utils/dict/latin_dict.txt
-  character_type: latin
   max_text_length: 25
   infer_mode: false
   use_space_char: true

configs/rec/rec_icdar15_train.yml

@@ -14,8 +14,7 @@ Global:
   use_visualdl: False
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
-  character_dict_path: ppocr/utils/ic15_dict.txt
-  character_type: ch
+  character_dict_path: ppocr/utils/en_dict.txt
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_mtb_nrtr.yml

+Global:
+  use_gpu: True
+  epoch_num: 21
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/nrtr/
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  cal_metric_during_train: True
+  pretrained_model:
+  checkpoints: 
+  save_inference_dir:
+  use_visualdl: False
+  infer_img: doc/imgs_words_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/EN_symbol_dict.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_nrtr.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.99
+  clip_norm: 5.0
+  lr:
+    name: Cosine
+    learning_rate: 0.0005
+    warmup_epoch: 2
+  regularizer:
+    name: 'L2'
+    factor: 0.
+
+Architecture:
+  model_type: rec
+  algorithm: NRTR
+  in_channels: 1
+  Transform:
+  Backbone:
+    name: MTB
+    cnn_num: 2
+  Head:
+    name: Transformer
+    d_model: 512
+    num_encoder_layers: 6
+    beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
+    
+
+Loss:
+  name: NRTRLoss
+  smoothing: True
+
+PostProcess:
+  name: NRTRLabelDecode
+
+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
+      - NRTRLabelEncode: # Class handling label
+      - NRTRRecResizeImg:
+          image_shape: [100, 32]
+          resize_type: PIL # PIL or OpenCV
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 512
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - NRTRLabelEncode: # Class handling label
+      - NRTRRecResizeImg:
+          image_shape: [100, 32]
+          resize_type: PIL # PIL or OpenCV
+      - 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
+    use_shared_memory: False

configs/rec/rec_mv3_none_bilstm_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_mv3_none_none_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_mv3_tps_bilstm_att.yml

@@ -15,7 +15,6 @@ Global:
   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

configs/rec/rec_mv3_tps_bilstm_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_r31_sar.yml

+Global:
+  use_gpu: true
+  epoch_num: 5
+  log_smooth_window: 20
+  print_batch_step: 20
+  save_model_dir: ./sar_rec
+  save_epoch_step: 1
+  # evaluation is run every 2000 iterations
+  eval_batch_step: [0, 2000]
+  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/dict90.txt
+  max_text_length: 30
+  infer_mode: False
+  use_space_char: False
+  rm_symbol: True
+  save_res_path: ./output/rec/predicts_sar.txt
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Piecewise
+    decay_epochs: [3, 4]
+    values: [0.001, 0.0001, 0.00001] 
+  regularizer:
+    name: 'L2'
+    factor: 0
+
+Architecture:
+  model_type: rec
+  algorithm: SAR
+  Transform:
+  Backbone:
+    name: ResNet31
+  Head:
+    name: SARHead
+
+Loss:
+  name: SARLoss
+
+PostProcess:
+  name: SARLabelDecode
+
+Metric:
+  name: RecMetric
+
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    label_file_list: ['./train_data/train_list.txt']
+    data_dir: ./train_data/
+    ratio_list: 1.0
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - SARRecResizeImg:
+          image_shape: [3, 48, 48, 160] # h:48 w:[48,160]
+          width_downsample_ratio: 0.25
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 64
+    drop_last: True
+    num_workers: 8
+    use_shared_memory: False
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SARLabelEncode: # Class handling label
+      - SARRecResizeImg:
+          image_shape: [3, 48, 48, 160]
+          width_downsample_ratio: 0.25
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'valid_ratio'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 64
+    num_workers: 4
+    use_shared_memory: False
+  

configs/rec/rec_r34_vd_none_bilstm_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_r34_vd_none_none_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_r34_vd_tps_bilstm_att.yml

@@ -15,7 +15,6 @@ Global:
   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

configs/rec/rec_r34_vd_tps_bilstm_ctc.yml

@@ -15,7 +15,6 @@ Global:
   infer_img: doc/imgs_words_en/word_10.png
   # for data or label process
   character_dict_path:
-  character_type: en
   max_text_length: 25
   infer_mode: False
   use_space_char: False

configs/rec/rec_r50_fpn_srn.yml

@@ -15,7 +15,6 @@ Global:
   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

configs/rec/rec_resnet_stn_bilstm_att.yml

+Global:
+  use_gpu: True
+  epoch_num: 400
+  log_smooth_window: 20
+  print_batch_step: 10
+  save_model_dir: ./output/rec/seed
+  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_en/word_10.png
+  # for data or label process
+  character_dict_path: ppocr/utils/EN_symbol_dict.txt
+  max_text_length: 100
+  infer_mode: False
+  use_space_char: False
+  save_res_path: ./output/rec/predicts_seed.txt
+
+
+Optimizer:
+  name: Adadelta
+  weight_deacy: 0.0
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    decay_epochs: [4,5,8]
+    values: [1.0, 0.1, 0.01]
+  regularizer:
+    name: 'L2'
+    factor: 2.0e-05
+
+
+Architecture:
+  model_type: rec
+  algorithm: SEED
+  Transform:
+    name: STN_ON
+    tps_inputsize: [32, 64]
+    tps_outputsize: [32, 100]
+    num_control_points: 20
+    tps_margins: [0.05,0.05]
+    stn_activation: none
+  Backbone:
+    name: ResNet_ASTER
+  Head:
+    name: AsterHead  # AttentionHead
+    sDim: 512
+    attDim: 512
+    max_len_labels: 100
+
+Loss:
+  name: AsterLoss
+
+PostProcess:
+  name: SEEDLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  is_filter: True
+
+Train:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/training/
+    transforms:
+      - Fasttext:
+          path: "./cc.en.300.bin"
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SEEDLabelEncode: # Class handling label
+      - RecResizeImg:
+          character_type: en
+          image_shape: [3, 64, 256]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length', 'fast_label'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 6
+
+Eval:
+  dataset:
+    name: LMDBDataSet
+    data_dir: ./train_data/data_lmdb_release/evaluation/
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - SEEDLabelEncode: # Class handling label
+      - RecResizeImg:
+          character_type: en
+          image_shape: [3, 64, 256]
+          padding: False
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: True
+    batch_size_per_card: 256
+    num_workers: 4

deploy/cpp_infer/CMakeLists.txt

 project(ppocr CXX C)
+cmake_minimum_required(VERSION 3.14)
 
 option(WITH_MKL        "Compile demo with MKL/OpenBlas support, default use MKL."       ON)
 option(WITH_GPU        "Compile demo with GPU/CPU, default use CPU."                    OFF)
@@ -206,9 +207,12 @@ endif()
 
 set(DEPS ${DEPS} ${OpenCV_LIBS})
 
+include(FetchContent)
+include(external-cmake/auto-log.cmake)
+include_directories(${FETCHCONTENT_BASE_DIR}/extern_autolog-src)
+
 AUX_SOURCE_DIRECTORY(./src SRCS)
 add_executable(${DEMO_NAME} ${SRCS})
-
 target_link_libraries(${DEMO_NAME} ${DEPS})
 
 if (WIN32 AND WITH_MKL)

deploy/cpp_infer/docs/windows_vs2019_build.md

@@ -5,20 +5,20 @@ PaddleOCR在Windows 平台下基于`Visual Studio 2019 Community` 进行了测
 
 ## 前置条件
 * Visual Studio 2019
-* CUDA 9.0 / CUDA 10.0，cudnn 7+ （仅在使用GPU版本的预测库时需要）
+* CUDA 10.2，cudnn 7+ （仅在使用GPU版本的预测库时需要）
 * CMake 3.0+
 
 请确保系统已经安装好上述基本软件，我们使用的是`VS2019`的社区版。
 
 **下面所有示例以工作目录为 `D:\projects`演示**。
 
-### Step1: 下载PaddlePaddle C++ 预测库 fluid_inference
+### Step1: 下载PaddlePaddle C++ 预测库 paddle_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://paddleinference.paddlepaddle.org.cn/user_guides/download_lib.html#windows)
 
-解压后`D:\projects\fluid_inference`目录包含内容为：
+解压后`D:\projects\paddle_inference`目录包含内容为：
 ```
-fluid_inference
+paddle_inference
 ├── paddle # paddle核心库和头文件
 |
 ├── third_party # 第三方依赖库和头文件
@@ -46,13 +46,13 @@ fluid_inference
 
 ![step2.2](https://paddleseg.bj.bcebos.com/inference/vs2019_step3.png)
 
-3. 点击：`项目`->`cpp_inference_demo的CMake设置`
+3. 点击：`项目`->`CMake设置`
 
 ![step3](https://paddleseg.bj.bcebos.com/inference/vs2019_step4.png)
 
-4. 点击`浏览`，分别设置编译选项指定`CUDA`、`CUDNN_LIB`、`OpenCV`、`Paddle预测库`的路径
+4. 分别设置编译选项指定`CUDA`、`CUDNN_LIB`、`OpenCV`、`Paddle预测库`的路径
 
-三个编译参数的含义说明如下（带`*`表示仅在使用**GPU版本**预测库时指定, 其中CUDA库版本尽量对齐，**使用9.0、10.0版本，不使用9.2、10.1等版本CUDA库**）：
+三个编译参数的含义说明如下（带`*`表示仅在使用**GPU版本**预测库时指定, 其中CUDA库版本尽量对齐）：
 
 |  参数名   | 含义  |
 |  ----  | ----  |
@@ -67,6 +67,11 @@ fluid_inference
 
 ![step4](https://paddleseg.bj.bcebos.com/inference/vs2019_step5.png)
 
+下面给出with GPU的配置示例：
+![step5](./vs2019_build_withgpu_config.png)
+**注意：**
+  CMAKE_BACKWARDS的版本要根据平台安装cmake的版本进行设置。
+
 **设置完成后**, 点击上图中`保存并生成CMake缓存以加载变量`。
 
 5. 点击`生成`->`全部生成`
@@ -74,24 +79,34 @@ fluid_inference
 ![step6](https://paddleseg.bj.bcebos.com/inference/vs2019_step6.png)
 
 
-### Step4: 预测及可视化
+### Step4: 预测
 
-上述`Visual Studio 2019`编译产出的可执行文件在`out\build\x64-Release`目录下，打开`cmd`，并切换到该目录：
+上述`Visual Studio 2019`编译产出的可执行文件在`out\build\x64-Release\Release`目录下，打开`cmd`，并切换到`D:\projects\PaddleOCR\deploy\cpp_infer\`：
 
 ```
-cd D:\projects\PaddleOCR\deploy\cpp_infer\out\build\x64-Release
+cd D:\projects\PaddleOCR\deploy\cpp_infer
 ```
-可执行文件`ocr_system.exe`即为样例的预测程序，其主要使用方法如下
+可执行文件`ppocr.exe`即为样例的预测程序，其主要使用方法如下，更多使用方法可以参考[说明文档](../readme.md)`运行demo`部分。
 
 ```shell
-#预测图片 `D:\projects\PaddleOCR\doc\imgs\10.jpg`  
-.\ocr_system.exe D:\projects\PaddleOCR\deploy\cpp_infer\tools\config.txt D:\projects\PaddleOCR\doc\imgs\10.jpg
+#识别中文图片 `D:\projects\PaddleOCR\doc\imgs_words\ch\`  
+.\out\build\x64-Release\Release\ppocr.exe rec --rec_model_dir=D:\projects\PaddleOCR\ch_ppocr_mobile_v2.0_rec_infer --image_dir=D:\projects\PaddleOCR\doc\imgs_words\ch\
+
+#识别英文图片 'D:\projects\PaddleOCR\doc\imgs_words\en\'
+.\out\build\x64-Release\Release\ppocr.exe rec --rec_model_dir=D:\projects\PaddleOCR\inference\rec_mv3crnn --image_dir=D:\projects\PaddleOCR\doc\imgs_words\en\ --char_list_file=D:\projects\PaddleOCR\ppocr\utils\dict\en_dict.txt
 ```
 
-第一个参数为配置文件路径，第二个参数为需要预测的图片路径。
+
+第一个参数为配置文件路径，第二个参数为需要预测的图片路径，第三个参数为配置文本识别的字典。
 
 
-### 注意
+### FQA
 * 在Windows下的终端中执行文件exe时，可能会发生乱码的现象，此时需要在终端中输入`CHCP 65001`，将终端的编码方式由GBK编码(默认)改为UTF-8编码，更加具体的解释可以参考这篇博客：[https://blog.csdn.net/qq_35038153/article/details/78430359](https://blog.csdn.net/qq_35038153/article/details/78430359)。
 
-* 编译时，如果报错`错误：C1083 无法打开包括文件:"dirent.h":No such file or directory`，可以参考该[文档](https://blog.csdn.net/Dora_blank/article/details/117740837#41_C1083_direnthNo_such_file_or_directory_54)，新建`dirent.h`文件，并添加到`VC++`的包含目录中。
+* 编译时，如果报错`错误：C1083 无法打开包括文件:"dirent.h":No such file or directory`，可以参考该[文档](https://blog.csdn.net/Dora_blank/article/details/117740837#41_C1083_direnthNo_such_file_or_directory_54)，新建`dirent.h`文件，并添加到`utility.cpp`的头文件引用中。同时修改`utility.cpp`70行：`lstat`改成`stat`。
+
+* 编译时，如果报错`Autolog未定义`，新建`autolog.h`文件，内容为：[autolog.h](https://github.com/LDOUBLEV/AutoLog/blob/main/auto_log/autolog.h)，并添加到`main.cpp`的头文件引用中，再次编译。
+
+* 运行时，如果弹窗报错找不到`paddle_inference.dll`或者`openblas.dll`，在`D:\projects\paddle_inference`预测库内找到这两个文件，复制到`D:\projects\PaddleOCR\deploy\cpp_infer\out\build\x64-Release\Release`目录下。不用重新编译，再次运行即可。
+
+* 运行时，弹窗报错提示`应用程序无法正常启动(0xc0000142)`，并且`cmd`窗口内提示`You are using Paddle compiled with TensorRT, but TensorRT dynamic library is not found.`，把tensort目录下的lib里面的所有dll文件复制到release目录下，再次运行即可。

deploy/cpp_infer/external-cmake/auto-log.cmake

+find_package(Git REQUIRED)
+include(FetchContent)
+
+set(FETCHCONTENT_BASE_DIR "${CMAKE_CURRENT_BINARY_DIR}/third-party")
+
+FetchContent_Declare(
+  extern_Autolog
+  PREFIX autolog
+  GIT_REPOSITORY https://github.com/LDOUBLEV/AutoLog.git
+  GIT_TAG        main
+)
+FetchContent_MakeAvailable(extern_Autolog)
+

deploy/cpp_infer/readme.md

@@ -4,15 +4,32 @@
 C++在性能计算上优于python，因此，在大多数CPU、GPU部署场景，多采用C++的部署方式，本节将介绍如何在Linux\Windows (CPU\GPU)环境下配置C++环境并完成
 PaddleOCR模型部署。
 
+* [1. 准备环境](#1)
+  + [1.0 运行准备](#10)
+  + [1.1 编译opencv库](#11)
+  + [1.2 下载或者编译Paddle预测库](#12)
+    - [1.2.1 直接下载安装](#121)
+    - [1.2.2 预测库源码编译](#122)
+* [2 开始运行](#2)
+  + [2.1 将模型导出为inference model](#21)
+  + [2.2 编译PaddleOCR C++预测demo](#22)
+  + [2.3运行demo](#23)
+
+<a name="1"></a>
 
 ## 1. 准备环境
 
-### 运行准备
+<a name="10"></a>
+
+### 1.0 运行准备
+
 - Linux环境，推荐使用docker。
 - Windows环境，目前支持基于`Visual Studio 2019 Community`进行编译。
 
 * 该文档主要介绍基于Linux环境的PaddleOCR C++预测流程，如果需要在Windows下基于预测库进行C++预测，具体编译方法请参考[Windows下编译教程](./docs/windows_vs2019_build.md)
 
+<a name="11"></a>
+
 ### 1.1 编译opencv库
 
 * 首先需要从opencv官网上下载在Linux环境下源码编译的包，以opencv3.4.7为例，下载命令如下。
@@ -71,6 +88,8 @@ opencv3/
 |-- share
 ```
 
+<a name="12"></a>
+
 ### 1.2 下载或者编译Paddle预测库
 
 * 有2种方式获取Paddle预测库，下面进行详细介绍。
@@ -132,9 +151,12 @@ build/paddle_inference_install_dir/
 
 其中`paddle`就是C++预测所需的Paddle库，`version.txt`中包含当前预测库的版本信息。
 
+<a name="2"></a>
 
 ## 2 开始运行
 
+<a name="21"></a>
+
 ### 2.1 将模型导出为inference model
 
 * 可以参考[模型预测章节](../../doc/doc_ch/inference.md)，导出inference model，用于模型预测。模型导出之后，假设放在`inference`目录下，则目录结构如下。
@@ -149,6 +171,7 @@ inference/
 |   |--inference.pdmodel
 ```
 
+<a name="22"></a>
 
 ### 2.2 编译PaddleOCR C++预测demo
 
@@ -172,8 +195,9 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
 
 * 编译完成之后，会在`build`文件夹下生成一个名为`ppocr`的可执行文件。
 
+<a name="23"></a>
 
-### 运行demo
+### 2.3 运行demo
 
 运行方式：  
 ```shell
@@ -258,6 +282,4 @@ CUDNN_LIB_DIR=/your_cudnn_lib_dir
 </div>
 
 
-### 2.3 注意
-
-* 在使用Paddle预测库时，推荐使用2.0.0版本的预测库。
+**注意：在使用Paddle预测库时，推荐使用2.0.0版本的预测库。**