add doc for ocr

doc/COMPILE.md

@@ -209,6 +209,7 @@ Please use the example under `python/examples` to verify.
 |     WITH_AVX     | Compile Paddle Serving with AVX intrinsics | OFF  |
 |     WITH_MKL     |  Compile Paddle Serving with MKL support   | OFF  |
 |     WITH_GPU     |   Compile Paddle Serving with NVIDIA GPU   | OFF  |
+|     WITH_OPENCV  |    Compile Paddle Serving with OPENCV      | OFF  |
 |  CUDNN_LIBRARY   |    Define CuDNN library and header path    |      |
 | CUDA_TOOLKIT_ROOT_DIR |       Define CUDA PATH                |      |
 |   TENSORRT_ROOT  |           Define TensorRT PATH             |      |
@@ -247,3 +248,80 @@ The following is the base library version matching relationship used by the Padd
 ### How to make the compiler detect the CuDNN library
 
 Download the corresponding CUDNN version from NVIDIA developer official website and decompressing it, add `-DCUDNN_ROOT` to cmake command, to specify the path of CUDNN.
+
+### WITH_OPENCV Option
+
+Compile the serving C + + server part. If WITH_OPENCV=ON and opencv library is not installed, please refer to the following instructions (if opencv library is installed, you can skip it)
+#### Compile opencv
+
+* First of all, you need to download the source code compiled package in the Linux environment from the opencv official website. Taking opencv3.4.7 as an example, the download command is as follows.
+
+```
+wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
+tar -xf 3.4.7.tar.gz
+```
+
+Finally, you can see the folder of `opencv-3.4.7/` in the current directory.
+
+* Compile opencv, the opencv source path (`root_path`) and installation path (`install_path`) should be set by yourself. Enter the opencv source code path and compile it in the following way.
+
+
+```shell
+root_path=your_opencv_root_path
+install_path=${root_path}/opencv3
+
+rm -rf build
+mkdir build
+cd build
+
+cmake .. \
+    -DCMAKE_INSTALL_PREFIX=${install_path} \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DBUILD_SHARED_LIBS=OFF \
+    -DWITH_IPP=OFF \
+    -DBUILD_IPP_IW=OFF \
+    -DWITH_LAPACK=OFF \
+    -DWITH_EIGEN=OFF \
+    -DCMAKE_INSTALL_LIBDIR=lib64 \
+    -DWITH_ZLIB=ON \
+    -DBUILD_ZLIB=ON \
+    -DWITH_JPEG=ON \
+    -DBUILD_JPEG=ON \
+    -DWITH_PNG=ON \
+    -DBUILD_PNG=ON \
+    -DWITH_TIFF=ON \
+    -DBUILD_TIFF=ON
+
+make -j
+make install
+```
+
+Among them, `root_path` is the downloaded opencv source code path, and `install_path` is the installation path of opencv. After `make install` is completed, the opencv header file and library file will be generated in this folder for later OCR source code compilation.
+
+
+
+The final file structure under the opencv installation path is as follows.
+
+```
+opencv3/
+|-- bin
+|-- include
+|-- lib
+|-- lib64
+|-- share
+```
+
+#### compile C++ Server under the condition of WITH_OPENCV=ON
+
+In the compile command, add `DOPENCV_DIR=${OPENCV_DIR}` and `DWITH_OPENCV=ON`，for example：
+``` shell
+OPENCV_DIR=your_opencv_dir #`your_opencv_dir` is the installation path of OpenCV library。
+mkdir server-build-cpu && cd server-build-cpu
+cmake -DPYTHON_INCLUDE_DIR=$PYTHON_INCLUDE_DIR/ \
+    -DPYTHON_LIBRARIES=$PYTHON_LIBRARIES \
+    -DPYTHON_EXECUTABLE=$PYTHON_EXECUTABLE \
+    -DOPENCV_DIR=${OPENCV_DIR} \
+    -DWITH_OPENCV=ON
+    -DSERVER=ON ..
+make -j10
+```
\ No newline at end of file

doc/COMPILE_CN.md

@@ -211,6 +211,7 @@ make
 |     WITH_MKL     |  Compile Paddle Serving with MKL support   | OFF  |
 |     WITH_GPU     |   Compile Paddle Serving with NVIDIA GPU   | OFF  |
 |     WITH_TRT     |    Compile Paddle Serving with TensorRT    | OFF  |
+|     WITH_OPENCV  |    Compile Paddle Serving with OPENCV      | OFF  |
 |  CUDNN_LIBRARY   |    Define CuDNN library and header path    |      |
 | CUDA_TOOLKIT_ROOT_DIR |       Define CUDA PATH                |      |
 |   TENSORRT_ROOT  |           Define TensorRT PATH             |      |
@@ -248,3 +249,78 @@ Paddle Serving通过PaddlePaddle预测库支持在GPU上做预测。WITH_GPU选
 ### 如何让Paddle Serving编译系统探测到CuDNN库
 
 从NVIDIA developer官网下载对应版本CuDNN并在本地解压后，在cmake编译命令中增加`-DCUDNN_LIBRARY`参数，指定CuDNN库所在路径。
+
+### WITH_OPENCV选项
+
+编译Serving C++ Server部分，若开启WITH_OPENCV选项，若没有安装openCV库，可参考以下说明（已安装则可跳过）:
+#### 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。
+
+```
+wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
+tar -xf 3.4.7.tar.gz
+```
+
+最终可以在当前目录下看到`opencv-3.4.7/`的文件夹。
+
+* 编译opencv，设置opencv源码路径(`root_path`)以及安装路径(`install_path`)。进入opencv源码路径下，按照下面的方式进行编译。
+
+```shell
+root_path=your_opencv_root_path
+install_path=${root_path}/opencv3
+
+rm -rf build
+mkdir build
+cd build
+
+cmake .. \
+    -DCMAKE_INSTALL_PREFIX=${install_path} \
+    -DCMAKE_BUILD_TYPE=Release \
+    -DBUILD_SHARED_LIBS=OFF \
+    -DWITH_IPP=OFF \
+    -DBUILD_IPP_IW=OFF \
+    -DWITH_LAPACK=OFF \
+    -DWITH_EIGEN=OFF \
+    -DCMAKE_INSTALL_LIBDIR=lib64 \
+    -DWITH_ZLIB=ON \
+    -DBUILD_ZLIB=ON \
+    -DWITH_JPEG=ON \
+    -DBUILD_JPEG=ON \
+    -DWITH_PNG=ON \
+    -DBUILD_PNG=ON \
+    -DWITH_TIFF=ON \
+    -DBUILD_TIFF=ON
+
+make -j
+make install
+```
+
+
+其中`root_path`为下载的opencv源码路径，`install_path`为opencv的安装路径，`make install`完成之后，会在该文件夹下生成opencv头文件和库文件，用于后面的OCR代码编译。
+
+最终在安装路径下的文件结构如下所示。
+
+```
+opencv3/
+|-- bin
+|-- include
+|-- lib
+|-- lib64
+|-- share
+```
+
+#### 开启WITH_OPENCV选项编译C++ Server
+
+在编译命令中，加入`DOPENCV_DIR=${OPENCV_DIR}` 和 `DWITH_OPENCV=ON`选项，例如：
+``` shell
+OPENCV_DIR=your_opencv_dir #`your_opencv_dir`为opencv库的安装路径。
+mkdir server-build-cpu && cd server-build-cpu
+cmake -DPYTHON_INCLUDE_DIR=$PYTHON_INCLUDE_DIR/ \
+    -DPYTHON_LIBRARIES=$PYTHON_LIBRARIES \
+    -DPYTHON_EXECUTABLE=$PYTHON_EXECUTABLE \
+    -DOPENCV_DIR=${OPENCV_DIR} \
+    -DWITH_OPENCV=ON
+    -DSERVER=ON ..
+make -j10
+```
\ No newline at end of file

python/examples/ocr/README.md

@@ -15,6 +15,29 @@ tar -xzvf ocr_det.tar.gz
 wget --no-check-certificate https://paddle-serving.bj.bcebos.com/ocr/test_imgs.tar
 tar xf test_imgs.tar
 ```
+## C++ OCR Service
+
+### Start Service
+
+```
+#Select a startup mode according to CPU / GPU device
+After the -- model parameter, the folder path of multiple model files is passed in to start the prediction service of multiple model concatenation.
+#for cpu user
+python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293
+#for gpu user
+python -m paddle_serving_server_gpu.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
+```
+
+### Client Prediction
+#The pre-processing and post-processing is in the C + + server part, the image's Base64 encoded string is passed into the C + + server
+so the value of parameter `feed_var` which is in the file `ocr_det_client/serving_client_conf.prototxt` should be changed.
+for this case, `feed_type` should be 3(which means the data type is string),`shape` should be 1.
+
+By passing in multiple client folder paths, the client can be started for multi model prediction.
+```
+python ocr_c_client_bytes.py ocr_det_client ocr_rec_client
+```
+
 
 ## Web Service
 

python/examples/ocr/README_CN.md

@@ -15,6 +15,28 @@ wget --no-check-certificate https://paddle-serving.bj.bcebos.com/ocr/test_imgs.t
 tar xf test_imgs.tar
 ```
 
+## C++ OCR Service服务
+
+### 启动服务
+
+```
+#根据CPU/GPU设备选择一种启动方式
+通过--model后，指定多个模型文件的文件夹路径来启动多模型串联的预测服务。
+#for cpu user
+python -m paddle_serving_server.serve --model ocr_det_model ocr_rec_model --port 9293
+#for gpu user
+python -m paddle_serving_server_gpu.serve --model ocr_det_model ocr_rec_model --port 9293 --gpu_id 0
+```
+
+### 启动客户端
+#由于需要在C++Server部分进行前后处理，传入C++Server的仅仅是图片的base64编码的字符串，故第一个模型的Client配置需要修改
+即`ocr_det_client/serving_client_conf.prototxt`中`feed_var`字段
+对于本示例而言，`feed_type`应修改为3(数据类型为string),`shape`为1.
+通过在客户端启动后加入多个client模型的client配置文件夹路径，启动client进行预测。
+```
+python ocr_c_client_bytes.py ocr_det_client ocr_rec_client
+```
+
 ## Web Service服务
 
 ### 启动服务