Merge branch 'develop' into develop

doc/doc_ch/android_demo.md

+# Android Demo 快速测试
+
+
+### 1. 安装最新版本的Android Studio
+
+可以从 https://developer.android.com/studio 下载。本Demo使用是4.0版本Android Studio编写。
+
+### 2. 创建新项目
+
+Demo测试的时候使用的是NDK 20b版本，20版本以上均可以支持编译成功。
+
+如果您是初学者，可以用以下方式安装和测试NDK编译环境。
+点击 File -> New ->New Project，  新建  "Native C++" project
+
+
+1. Start a new Android Studio project
+    在项目模版中选择 Native C++ 选择PaddleOCR/depoly/android_demo 路径
+    进入项目后会自动编译，第一次编译会花费较长的时间，建议添加代理加速下载。
+
+**代理添加：**
+
+选择 Android Studio -> Perferences -> Appearance & Behavior -> System Settings -> HTTP Proxy -> Manual proxy configuration
+
+![](../demo/proxy.png)
+
+2. 开始编译
+
+点击编译按钮，连接手机，跟着Android Studio的引导完成操作。
+
+在 Android Studio 里看到下图，表示编译完成：
+
+![](../demo/build.png)
+
+**提示:** 此时如果出现下列找不到OpenCV的报错信息，请重新点击编译，编译完成后退出项目，再次进入。
+
+![](../demo/error.png)
+
+### 3. 发送到手机端
+
+完成编译，点击运行，在手机端查看效果。
+
+### 4. 如何自定义demo图片
+
+1. 图片存放路径:android_demo/app/src/main/assets/images
+
+   将自定义图片放置在该路径下
+
+2. 配置文件: android_demo/app/src/main/res/values/strings.xml
+
+   修改 IMAGE_PATH_DEFAULT 为自定义图片名即可
+
+
+# 获得更多支持
+前往[端计算模型生成平台EasyEdge](https://ai.baidu.com/easyedge/app/open_source_demo?referrerUrl=paddlelite)，获得更多开发支持：
+
+- Demo APP：可使用手机扫码安装，方便手机端快速体验文字识别
+- SDK：模型被封装为适配不同芯片硬件和操作系统SDK，包括完善的接口，方便进行二次开发

doc/doc_ch/config.md

@@ -60,6 +60,8 @@
 |         beta1           |    设置一阶矩估计的指数衰减率  |       0.9         |               \             |
 |         beta2           |    设置二阶矩估计的指数衰减率  |     0.999         |               \             |
 |         decay           |         是否使用decay       |    \              |               \             |
-|      function(decay)    |         设置decay方式       |   cosine_decay    |       目前只支持cosin_decay  |
-|      step_each_epoch    |      每个epoch包含多少次迭代  |         20       | 计算方式：total_image_num / (batch_size_per_card * card_size) |
-|        total_epoch      |    总共迭代多少个epoch        |       1000      | 与Global.epoch_num 一致        |
+|      function(decay)    |         设置decay方式       |   -    |       目前支持cosine_decay与piecewise_decay  |
+|      step_each_epoch    |      每个epoch包含多少次迭代, cosine_decay时有效   |         20       | 计算方式：total_image_num / (batch_size_per_card * card_size) |
+|        total_epoch      |    总共迭代多少个epoch, cosine_decay时有效        |       1000      | 与Global.epoch_num 一致        |
+|        boundaries      |    学习率下降时的迭代次数间隔, piecewise_decay时有效       |       -      | 参数为列表形式        |
+|        decay_rate      |    学习率衰减系数, piecewise_decay时有效       |       -      |  \        |

doc/doc_ch/detection.md

@@ -26,7 +26,7 @@ wget -P ./train_data/  https://paddleocr.bj.bcebos.com/dataset/test_icdar2015_la
 提供的标注文件格式为，其中中间是"\t"分隔：
 ```
 " 图像文件名                    json.dumps编码的图像标注信息"
-ch4_test_images/img_61.jpg    [{"transcription": "MASA", "points": [[310, 104], [416, 141], [418, 216], [312, 179]], ...}]
+ch4_test_images/img_61.jpg    [{"transcription": "MASA", "points": [[310, 104], [416, 141], [418, 216], [312, 179]]}, {...}]
 ```
 json.dumps编码前的图像标注信息是包含多个字典的list，字典中的 `points` 表示文本框的四个点的坐标(x, y)，从左上角的点开始顺时针排列。
 `transcription` 表示当前文本框的文字，在文本检测任务中并不需要这个信息。

doc/doc_ch/installation.md

@@ -3,15 +3,15 @@
 经测试PaddleOCR可在glibc 2.23上运行，您也可以测试其他glibc版本或安装glic 2.23
 PaddleOCR 工作环境
 - PaddlePaddle 1.7+
-- python3
+- python3.7
 - glibc 2.23
 - cuDNN 7.6+ (GPU)
 
-建议使用我们提供的docker运行PaddleOCR，有关docker使用请参考[链接](https://docs.docker.com/get-started/)。
+建议使用我们提供的docker运行PaddleOCR，有关docker、nvidia-docker使用请参考[链接](https://docs.docker.com/get-started/)。
 
 *如您希望使用 mac 或 windows直接运行预测代码，可以从第2步开始执行。*
 
-1. （建议）准备docker环境。第一次使用这个镜像，会自动下载该镜像，请耐心等待。
+**1. （建议）准备docker环境。第一次使用这个镜像，会自动下载该镜像，请耐心等待。**
 ```
 # 切换到工作目录下
 cd /home/Projects
@@ -21,10 +21,10 @@ cd /home/Projects
 如果您希望在CPU环境下使用docker，使用docker而不是nvidia-docker创建docker
 sudo docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev /bin/bash
 
-如果您的机器安装的是CUDA9，请运行以下命令创建容器
+如果使用CUDA9，请运行以下命令创建容器
 sudo nvidia-docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev /bin/bash
 
-如果您的机器安装的是CUDA10，请运行以下命令创建容器
+如果使用CUDA10，请运行以下命令创建容器
 sudo nvidia-docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda10.0-cudnn7-dev /bin/bash
 
 您也可以访问[DockerHub](https://hub.docker.com/r/paddlepaddle/paddle/tags/)获取与您机器适配的镜像。
@@ -47,7 +47,7 @@ docker images
 hub.baidubce.com/paddlepaddle/paddle   latest-gpu-cuda9.0-cudnn7-dev    f56310dcc829
 ```
 
-2. 安装PaddlePaddle Fluid v1.7
+**2. 安装PaddlePaddle Fluid v1.7**
 ```
 pip3 install --upgrade pip
 
@@ -64,7 +64,7 @@ python3 -m pip install paddlepaddle==1.7.2 -i https://pypi.tuna.tsinghua.edu.cn/
 更多的版本需求，请参照[安装文档](https://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
 ```
 
-3. 克隆PaddleOCR repo代码
+**3. 克隆PaddleOCR repo代码**
 ```
 【推荐】git clone https://github.com/PaddlePaddle/PaddleOCR
 
@@ -75,8 +75,11 @@ git clone https://gitee.com/paddlepaddle/PaddleOCR
 注：码云托管代码可能无法实时同步本github项目更新，存在3~5天延时，请优先使用推荐方式。
 ```
 
-4. 安装第三方库
+**4. 安装第三方库**
 ```
 cd PaddleOCR
 pip3 install -r requirments.txt
 ```
+
+注意，windows环境下，建议从[这里](https://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely)下载shapely安装包完成安装，
+直接通过pip安装的shapely库可能出现`[winRrror 126] 找不到指定模块的问题`。

doc/doc_ch/recognition.md

@@ -21,12 +21,11 @@ ln -sf <path/to/dataset> <path/to/paddle_ocr>/train_data/dataset
 * 使用自己数据集：
 
 若您希望使用自己的数据进行训练，请参考下文组织您的数据。
-
 - 训练集
 
 首先请将训练图片放入同一个文件夹（train_images），并用一个txt文件（rec_gt_train.txt）记录图片路径和标签。
 
-* 注意： 默认请将图片路径和图片标签用 \t 分割，如用其他方式分割将造成训练报错
+**注意：** 默认请将图片路径和图片标签用 \t 分割，如用其他方式分割将造成训练报错
 
 ```
 " 图像文件名                 图像标注信息 "
@@ -41,12 +40,9 @@ PaddleOCR 提供了一份用于训练 icdar2015 数据集的标签文件，通
 wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_train.txt
 # 测试集标签
 wget -P ./train_data/ic15_data  https://paddleocr.bj.bcebos.com/dataset/rec_gt_test.txt
-
-
 ```
 
 最终训练集应有如下文件结构：
-
 ```
 |-train_data
     |-ic15_data
@@ -150,7 +146,7 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t
 
 如果验证集很大，测试将会比较耗时，建议减少评估次数，或训练完再进行评估。
 
-* 提示： 可通过 -c 参数选择 `configs/rec/` 路径下的多种模型配置进行训练，PaddleOCR支持的识别算法有：
+**提示：** 可通过 -c 参数选择 `configs/rec/` 路径下的多种模型配置进行训练，PaddleOCR支持的识别算法有：
 
 
 | 配置文件 |  算法名称 |   backbone |   trans   |   seq      |     pred     |

doc/doc_ch/serving.md

@@ -28,21 +28,38 @@ deploy/hubserving/ocr_system/
 # 安装paddlehub  
 pip3 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 
-# 设置环境变量  
+# 在Linux下设置环境变量
 export PYTHONPATH=.
-```   
+# 在Windows下设置环境变量
+SET PYTHONPATH=.
+```
 
 ### 2. 安装服务模块
-PaddleOCR提供3种服务模块，根据需要安装所需模块。如： 
+PaddleOCR提供3种服务模块，根据需要安装所需模块。
 
-安装检测服务模块：  
-```hub install deploy/hubserving/ocr_det/```  
+* 在Linux环境下，安装示例如下：
+```shell
+# 安装检测服务模块：  
+hub install deploy/hubserving/ocr_det/
 
-或，安装识别服务模块：    
-```hub install deploy/hubserving/ocr_rec/```  
+# 或，安装识别服务模块：  
+hub install deploy/hubserving/ocr_rec/
 
-或，安装检测+识别串联服务模块：  
-```hub install deploy/hubserving/ocr_system/```  
+# 或，安装检测+识别串联服务模块：  
+hub install deploy/hubserving/ocr_system/
+```
+
+* 在Windows环境下(文件夹的分隔符为`\`)，安装示例如下：
+```shell
+# 安装检测服务模块：  
+hub install deploy\hubserving\ocr_det\
+
+# 或，安装识别服务模块：  
+hub install deploy\hubserving\ocr_rec\
+
+# 或，安装检测+识别串联服务模块：
+hub install deploy\hubserving\ocr_system\
+```
 
 ### 3. 启动服务
 #### 方式1. 命令行命令启动（仅支持CPU）
@@ -69,9 +86,9 @@ $ hub serving start --modules [Module1==Version1, Module2==Version2, ...] \
 
 #### 方式2. 配置文件启动（支持CPU、GPU）
 **启动命令：**  
-```hub serving start --config/-c config.json```  
+```hub serving start -c config.json```  
 
-其中，`config.json`格式如下： 
+其中，`config.json`格式如下：
 ```python
 {
     "modules_info": {
@@ -124,7 +141,7 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
 ## 返回结果格式说明
 返回结果为列表（list），列表中的每一项为词典（dict），词典一共可能包含3种字段，信息如下：
 
-|字段名称|数据类型|意义| 
+|字段名称|数据类型|意义|
 |-|-|-|
 |text|str|文本内容|
 |confidence|float| 文本识别置信度|
@@ -134,9 +151,9 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
 
 |字段名/模块名|ocr_det|ocr_rec|ocr_system|
 |-|-|-|-|  
-|text||✔|✔| 
-|confidence||✔|✔| 
-|text_region|✔||✔| 
+|text||✔|✔|
+|confidence||✔|✔|
+|text_region|✔||✔|
 
 **说明：** 如果需要增加、删除、修改返回字段，可在相应模块的`module.py`文件中进行修改，完整流程参考下一节自定义修改服务模块。
 
@@ -157,4 +174,3 @@ hub serving start -c deploy/hubserving/ocr_system/config.json
 
 - 5、重新启动服务  
 ```hub serving start -m ocr_system```  
-

doc/doc_ch/update.md

 # 更新
+- 2020.7.23 发布7月21日B站直播课回放和PPT，PaddleOCR开源大礼包全面解读，[获取地址](https://aistudio.baidu.com/aistudio/course/introduce/1519)
 - 2020.7.15 添加基于EasyEdge和Paddle-Lite的移动端DEMO，支持iOS和Android系统
 - 2020.7.15 完善预测部署，添加基于C++预测引擎推理、服务化部署和端侧部署方案，以及超轻量级中文OCR模型预测耗时Benchmark
 - 2020.7.15 整理OCR相关数据集、常用数据标注以及合成工具

doc/doc_en/android_demo_en.md

+# Android Demo quick start
+
+### 1. Install the latest version of Android Studio
+
+It can be downloaded from https://developer.android.com/studio . This Demo is written by Android Studio version 4.0.
+
+### 2. Create a new project
+
+The NDK version 20b is used in the demo test, and the compilation can be successfully supported for version 20 and above.
+
+If you are a beginner, you can install and test the NDK compilation environment in the following ways.
+
+File -> New ->New Project  to create  "Native C++" project
+
+1. Start a new Android Studio project
+
+   Select Native C++ in the project template, select Paddle OCR/deploy/android_demo path
+   After entering the project, it will be automatically compiled. The first compilation
+   will take a long time. It is recommended to add an agent to speed up the download.
+
+**Agent add:**
+
+  Android Studio -> Perferences -> Appearance & Behavior -> System Settings -> HTTP Proxy -> Manual proxy configuration
+
+![](../demo/proxy.png)
+
+2. Start compilation
+
+Click the compile button, connect the phone, and follow the instructions of Android Studio to complete the operation.
+
+When you see the following picture in Android Studio, the compilation is complete:
+
+![](../demo/build.png)
+
+**Tip:** At this time, if the following error message that OpenCV cannot be found appears, please re-click compile,
+exit the project after compiling, and enter again.
+
+![](../demo/error.png)
+
+### 3. Send to mobile
+
+Complete the compilation, click Run, and check the effect on the mobile phone.
+
+### 4. How to customize the demo picture
+
+1. Image storage path: android_demo/app/src/main/assets/images
+
+   Place the custom picture under this path
+
+2. Configuration file: android_demo/app/src/main/res/values/strings.xml
+
+   Modify IMAGE_PATH_DEFAULT to a custom picture name
+
+# Get more support
+
+Go to [EasyEdge](https://ai.baidu.com/easyedge/app/open_source_demo?referrerUrl=paddlelite) to get more development support:
+
+- Demo APP: You can use your mobile phone to scan the code to install, which is convenient for the mobile terminal to quickly experience text recognition
+
+- SDK: The model is packaged to adapt to different chip hardware and operating system SDKs, including a complete interface to facilitate secondary development

doc/doc_en/config_en.md

@@ -60,6 +60,8 @@ Take `rec_icdar15_train.yml` as an example:
 |         beta1           |    Set the exponential decay rate for the 1st moment estimates  |       0.9         |               \             |
 |         beta2           |    Set the exponential decay rate for the 2nd moment estimates  |     0.999         |               \             |
 |         decay           |         Whether to use decay       |    \              |               \             |
-|      function(decay)    |         Set the decay function       |   cosine_decay    |           Only support cosine_decay            |
-|      step_each_epoch    |      The number of steps in an epoch.  |         20       | Calculation ：total_image_num / (batch_size_per_card * card_size) |
-|        total_epoch      |    The number of epochs      |       1000      | Consistent with Global.epoch_num      |
+|      function(decay)    |         Set the decay function       |   cosine_decay    |         Support cosine_decay and piecewise_decay            |
+|      step_each_epoch    |      The number of steps in an epoch. Used in cosine_decay  |         20       | Calculation ：total_image_num / (batch_size_per_card * card_size) |
+|        total_epoch      |    The number of epochs. Used in cosine_decay      |       1000      | Consistent with Global.epoch_num      |
+|        boundaries      |    The step intervals to reduce learning rate. Used in piecewise_decay       |       -      |  The format is list        |
+|        decay_rate      |    Learning rate decay rate. Used in piecewise_decay       |       -      |  \        |

doc/doc_en/detection_en.md

@@ -25,7 +25,7 @@ After decompressing the data set and downloading the annotation file, PaddleOCR/
 The provided annotation file format is as follow, seperated by "\t":
 ```
 " Image file name             Image annotation information encoded by json.dumps"
-ch4_test_images/img_61.jpg    [{"transcription": "MASA", "points": [[310, 104], [416, 141], [418, 216], [312, 179]], ...}]
+ch4_test_images/img_61.jpg    [{"transcription": "MASA", "points": [[310, 104], [416, 141], [418, 216], [312, 179]]}, {...}]
 ```
 The image annotation after json.dumps() encoding is a list containing multiple dictionaries. The `points` in the dictionary represent the coordinates (x, y) of the four points of the text box, arranged clockwise from the point at the upper left corner.
 

doc/doc_en/installation_en.md

@@ -4,28 +4,28 @@ After testing, paddleocr can run on glibc 2.23. You can also test other glibc ve
 
 PaddleOCR working environment:
 - PaddlePaddle1.7
-- python3
+- python3.7
 - glibc 2.23
 
 It is recommended to use the docker provided by us to run PaddleOCR, please refer to the use of docker [link](https://docs.docker.com/get-started/).
 
 *If you want to directly run the prediction code on mac or windows, you can start from step 2.*
 
-1. (Recommended) Prepare a docker environment. The first time you use this image, it will be downloaded automatically. Please be patient.
+**1. (Recommended) Prepare a docker environment. The first time you use this image, it will be downloaded automatically. Please be patient.**
 ```
 # Switch to the working directory
 cd /home/Projects
 # You need to create a docker container for the first run, and do not need to run the current command when you run it again
 # Create a docker container named ppocr and map the current directory to the /paddle directory of the container
 
-#If you want to use docker in a CPU environment, use docker instead of nvidia-docker to create docker
+#If using CPU, use docker instead of nvidia-docker to create docker
 sudo docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev /bin/bash
 ```
-If you have cuda9 installed on your machine, please run the following command to create a container:
+If using CUDA9, please run the following command to create a container:
 ```
 sudo nvidia-docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev /bin/bash
 ```
-If you have cuda10 installed on your machine, please run the following command to create a container:
+If using CUDA10, please run the following command to create a container:
 ```
 sudo nvidia-docker run --name ppocr -v $PWD:/paddle --network=host -it hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda10.0-cudnn7-dev /bin/bash
 ```
@@ -49,7 +49,7 @@ docker images
 hub.baidubce.com/paddlepaddle/paddle   latest-gpu-cuda9.0-cudnn7-dev    f56310dcc829
 ```
 
-2. Install PaddlePaddle Fluid v1.7 (the higher version is not supported yet, the adaptation work is in progress)
+**2. Install PaddlePaddle Fluid v1.7 (the higher version is not supported yet, the adaptation work is in progress)**
 ```
 pip3 install --upgrade pip
 
@@ -65,7 +65,7 @@ python3 -m pip install paddlepaddle==1.7.2 -i https://pypi.tuna.tsinghua.edu.cn/
 For more software version requirements, please refer to the instructions in [Installation Document](https://www.paddlepaddle.org.cn/install/quick) for operation.
 
 
-3. Clone PaddleOCR repo
+**3. Clone PaddleOCR repo**
 ```
 # Recommend
 git clone https://github.com/PaddlePaddle/PaddleOCR
@@ -77,8 +77,14 @@ git clone https://gitee.com/paddlepaddle/PaddleOCR
 # Note: The cloud-hosting code may not be able to synchronize the update with this GitHub project in real time. There might be a delay of 3-5 days. Please give priority to the recommended method.
 ```
 
-4. Install third-party libraries
+**4. Install third-party libraries**
 ```
 cd PaddleOCR
 pip3 install -r requirments.txt
 ```
+
+If you getting this error `OSError: [WinError 126] The specified module could not be found` when you install shapely on windows.
+
+Please try to download Shapely whl file using [http://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely](http://www.lfd.uci.edu/~gohlke/pythonlibs/#shapely).
+
+Reference: [Solve shapely installation on windows](https://stackoverflow.com/questions/44398265/install-shapely-oserror-winerror-126-the-specified-module-could-not-be-found)

doc/doc_en/serving_en.md

@@ -29,25 +29,38 @@ The following steps take the 2-stage series service as an example. If only the d
 # Install paddlehub  
 pip3 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 
-# Set environment variables  
+# Set environment variables on Linux
 export PYTHONPATH=.
-```   
+# Set environment variables on Windows
+SET PYTHONPATH=.
+```
 
 ### 2. Install Service Module
-PaddleOCR provides 3 kinds of service modules, install the required modules according to your needs. Such as:  
+PaddleOCR provides 3 kinds of service modules, install the required modules according to your needs.
 
-Install the detection service module:  
+* On Linux platform, the examples are as follows.
 ```shell
+# Install the detection service module:
 hub install deploy/hubserving/ocr_det/
-```  
-Or, install the recognition service module:  
-```shell
+
+# Or, install the recognition service module:
 hub install deploy/hubserving/ocr_rec/
-```  
-Or, install the 2-stage series service module:  
-```shell
+
+# Or, install the 2-stage series service module:
 hub install deploy/hubserving/ocr_system/
-```  
+```
+
+* On Windows platform, the examples are as follows.
+```shell
+# Install the detection service module:
+hub install deploy\hubserving\ocr_det\
+
+# Or, install the recognition service module:
+hub install deploy\hubserving\ocr_rec\
+
+# Or, install the 2-stage series service module:
+hub install deploy\hubserving\ocr_system\
+```
 
 ### 3. Start service
 #### Way 1. Start with command line parameters (CPU only)
@@ -119,7 +132,7 @@ python tools/test_hubserving.py server_url image_path
 ```  
 
 Two parameters need to be passed to the script:
-- **server_url**：service address，format of which is 
+- **server_url**：service address，format of which is
 `http://[ip_address]:[port]/predict/[module_name]`  
 For example, if the detection, recognition and 2-stage serial services are started with provided configuration files, the respective `server_url` would be:  
 `http://127.0.0.1:8866/predict/ocr_det`  
@@ -135,7 +148,7 @@ python tools/test_hubserving.py http://127.0.0.1:8868/predict/ocr_system ./doc/i
 ## Returned result format
 The returned result is a list. Each item in the list is a dict. The dict may contain three fields. The information is as follows:
 
-|field name|data type|description| 
+|field name|data type|description|
 |-|-|-|
 |text|str|text content|
 |confidence|float|text recognition confidence|
@@ -145,9 +158,9 @@ The fields returned by different modules are different. For example, the results
 
 |field name/module name|ocr_det|ocr_rec|ocr_system|
 |-|-|-|-|  
-|text||✔|✔| 
-|confidence||✔|✔| 
-|text_region|✔||✔| 
+|text||✔|✔|
+|confidence||✔|✔|
+|text_region|✔||✔|
 
 **Note：** If you need to add, delete or modify the returned fields, you can modify the file `module.py` of the corresponding module. For the complete process, refer to the user-defined modification service module in the next section.
 

doc/doc_en/update_en.md

 # RECENT UPDATES
-
+- 2020.7.23, Release the playback and PPT of live class on BiliBili station, PaddleOCR Introduction, [address](https://aistudio.baidu.com/aistudio/course/introduce/1519)
 - 2020.7.15, Add mobile App demo , support both iOS and  Android  ( based on easyedge and Paddle Lite)
 - 2020.7.15, Improve the  deployment ability, add the C + +  inference , serving deployment. In addtion, the benchmarks of the ultra-lightweight Chinese OCR model are provided.
 - 2020.7.15, Add several related datasets, data annotation and synthesis tools.

ppocr/data/det/dataset_traversal.py

@@ -41,7 +41,7 @@ class TrainReader(object):
             "absence process_function in Reader"
         self.process = create_module(params['process_function'])(params)
 
-    def __call__(self, process_id):
+    def __call__(self, process_id):     
         def sample_iter_reader():
             with open(self.label_file_path, "rb") as fin:
                 label_infor_list = fin.readlines()

ppocr/data/det/db_process.py

@@ -17,7 +17,7 @@ import cv2
 import numpy as np
 import json
 import sys
-from ppocr.utils.utility import initial_logger
+from ppocr.utils.utility import initial_logger, check_and_read_gif
 logger = initial_logger()
 
 from .data_augment import AugmentData
@@ -100,7 +100,9 @@ class DBProcessTrain(object):
 
     def __call__(self, label_infor):
         img_path, gt_label = self.convert_label_infor(label_infor)
-        imgvalue = cv2.imread(img_path)
+        imgvalue, flag = check_and_read_gif(img_path)
+        if not flag:
+            imgvalue = cv2.imread(img_path)
         if imgvalue is None:
             logger.info("{} does not exist!".format(img_path))
             return None

ppocr/data/det/east_process.py

@@ -17,6 +17,7 @@ import cv2
 import numpy as np
 import json
 import sys
+import os
 
 class EASTProcessTrain(object):
     def __init__(self, params):
@@ -52,7 +53,7 @@ class EASTProcessTrain(object):
         label_infor = label_infor.decode()
         label_infor = label_infor.encode('utf-8').decode('utf-8-sig')
         substr = label_infor.strip("\n").split("\t")
-        img_path = self.img_set_dir + substr[0]
+        img_path = os.path.join(self.img_set_dir, substr[0])
         label = json.loads(substr[1])
         nBox = len(label)
         wordBBs, txts, txt_tags = [], [], []

ppocr/data/rec/dataset_traversal.py

@@ -185,6 +185,7 @@ class SimpleReader(object):
         if params['mode'] != 'test':
             self.img_set_dir = params['img_set_dir']
             self.label_file_path = params['label_file_path']
+        self.use_gpu = params['use_gpu']
         self.char_ops = params['char_ops']
         self.image_shape = params['image_shape']
         self.loss_type = params['loss_type']
@@ -213,6 +214,15 @@ class SimpleReader(object):
         if self.mode != 'train':
             process_id = 0
 
+        def get_device_num():
+            if self.use_gpu:
+                gpus = os.environ.get("CUDA_VISIBLE_DEVICES", 1)
+                gpu_num = len(gpus.split(','))
+                return gpu_num
+            else:
+                cpu_num = os.environ.get("CPU_NUM", 1)
+                return int(cpu_num)
+
         def sample_iter_reader():
             if self.mode != 'train' and self.infer_img is not None:
                 image_file_list = get_image_file_list(self.infer_img)
@@ -233,10 +243,16 @@ class SimpleReader(object):
                 img_num = len(label_infor_list)
                 img_id_list = list(range(img_num))
                 random.shuffle(img_id_list)
-                if sys.platform == "win32":
+                if sys.platform == "win32" and self.num_workers != 1:
                     print("multiprocess is not fully compatible with Windows."
                           "num_workers will be 1.")
                     self.num_workers = 1
+                if self.batch_size * get_device_num(
+                ) * self.num_workers > img_num:
+                    raise Exception(
+                        "The number of the whole data ({}) is smaller than the batch_size * devices_num * num_workers ({})".
+                        format(img_num, self.batch_size * get_device_num() *
+                               self.num_workers))
                 for img_id in range(process_id, img_num, self.num_workers):
                     label_infor = label_infor_list[img_id_list[img_id]]
                     substr = label_infor.decode('utf-8').strip("\n").split("\t")

ppocr/data/rec/img_tools.py

@@ -360,7 +360,7 @@ def process_image(img,
         text = char_ops.encode(label)
         if len(text) == 0 or len(text) > max_text_length:
             logger.info(
-                "Warning in ppocr/data/rec/img_tools.py:line362: Wrong data type."
+                "Warning in ppocr/data/rec/img_tools.py: Wrong data type."
                 "Excepted string with length between 1 and {}, but "
                 "got '{}'. Label is '{}'".format(max_text_length,
                                                  len(text), label))

ppocr/modeling/backbones/rec_mobilenet_v3.py

@@ -31,16 +31,28 @@ __all__ = [
 
 class MobileNetV3():
     def __init__(self, params):
-        self.scale = params['scale']
-        model_name = params['model_name']
+        self.scale = params.get("scale", 0.5)
+        model_name = params.get("model_name", "small")
+        large_stride = params.get("large_stride", [1, 2, 2, 2])
+        small_stride = params.get("small_stride", [2, 2, 2, 2])
+
+        assert isinstance(large_stride, list), "large_stride type must " \
+            "be list but got {}".format(type(large_stride))
+        assert isinstance(small_stride, list), "small_stride type must " \
+            "be list but got {}".format(type(small_stride))
+        assert len(large_stride) == 4, "large_stride length must be " \
+            "4 but got {}".format(len(large_stride))
+        assert len(small_stride) == 4, "small_stride length must be " \
+            "4 but got {}".format(len(small_stride))
+
         self.inplanes = 16
         if model_name == "large":
             self.cfg = [
                 # k, exp, c,  se,     nl,  s,
-                [3, 16, 16, False, 'relu', 1],
-                [3, 64, 24, False, 'relu', (2, 1)],
+                [3, 16, 16, False, 'relu', large_stride[0]],
+                [3, 64, 24, False, 'relu', (large_stride[1], 1)],
                 [3, 72, 24, False, 'relu', 1],
-                [5, 72, 40, True, 'relu', (2, 1)],
+                [5, 72, 40, True, 'relu', (large_stride[2], 1)],
                 [5, 120, 40, True, 'relu', 1],
                 [5, 120, 40, True, 'relu', 1],
                 [3, 240, 80, False, 'hard_swish', 1],
@@ -49,7 +61,7 @@ class MobileNetV3():
                 [3, 184, 80, False, 'hard_swish', 1],
                 [3, 480, 112, True, 'hard_swish', 1],
                 [3, 672, 112, True, 'hard_swish', 1],
-                [5, 672, 160, True, 'hard_swish', (2, 1)],
+                [5, 672, 160, True, 'hard_swish', (large_stride[3], 1)],
                 [5, 960, 160, True, 'hard_swish', 1],
                 [5, 960, 160, True, 'hard_swish', 1],
             ]
@@ -58,15 +70,15 @@ class MobileNetV3():
         elif model_name == "small":
             self.cfg = [
                 # k, exp, c,  se,     nl,  s,
-                [3, 16, 16, True, 'relu', (2, 1)],
-                [3, 72, 24, False, 'relu', (2, 1)],
+                [3, 16, 16, True, 'relu', (small_stride[0], 1)],
+                [3, 72, 24, False, 'relu', (small_stride[1], 1)],
                 [3, 88, 24, False, 'relu', 1],
-                [5, 96, 40, True, 'hard_swish', (2, 1)],
+                [5, 96, 40, True, 'hard_swish', (small_stride[2], 1)],
                 [5, 240, 40, True, 'hard_swish', 1],
                 [5, 240, 40, True, 'hard_swish', 1],
                 [5, 120, 48, True, 'hard_swish', 1],
                 [5, 144, 48, True, 'hard_swish', 1],
-                [5, 288, 96, True, 'hard_swish', (2, 1)],
+                [5, 288, 96, True, 'hard_swish', (small_stride[3], 1)],
                 [5, 576, 96, True, 'hard_swish', 1],
                 [5, 576, 96, True, 'hard_swish', 1],
             ]
@@ -78,7 +90,7 @@ class MobileNetV3():
 
         supported_scale = [0.35, 0.5, 0.75, 1.0, 1.25]
         assert self.scale in supported_scale, \
-            "supported scale are {} but input scale is {}".format(supported_scale, scale)
+            "supported scales are {} but input scale is {}".format(supported_scale, self.scale)
 
     def __call__(self, input):
         scale = self.scale

ppocr/modeling/heads/rec_ctc_head.py

@@ -32,6 +32,7 @@ class CTCPredict(object):
         self.char_num = params['char_num']
         self.encoder = SequenceEncoder(params)
         self.encoder_type = params['encoder_type']
+        self.fc_decay = params.get("fc_decay", 0.0004)
 
     def __call__(self, inputs, labels=None, mode=None):
         encoder_features = self.encoder(inputs)
@@ -39,7 +40,7 @@ class CTCPredict(object):
             encoder_features = fluid.layers.concat(encoder_features, axis=1)
         name = "ctc_fc"
         para_attr, bias_attr = get_para_bias_attr(
-            l2_decay=0.0004, k=encoder_features.shape[1], name=name)
+            l2_decay=self.fc_decay, k=encoder_features.shape[1], name=name)
         predict = fluid.layers.fc(input=encoder_features,
                                   size=self.char_num + 1,
                                   param_attr=para_attr,