PaddleOCR服务器端部署_C++

1.环境准备

1.1搭建PaddleOCR的docker环境

首先按照如下方法搭建PaddleOCR的docket环境

https://blog.csdn.net/u013171226/article/details/115125137

1.2 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
cd opencv-3.4.7

编译opencv,设置opencv源码路径(root_path)以及安装路径(install_path)，然后用下面的命令进行编译，生成opencv的头文件和库文件。

mkdir install
root_path=/paddle/opencv-3.4.7
install_path=/paddle/opencv-3.4.7/install
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 -j8
make install

1.3编译Paddle预测库

首先从github上下载代码：

git clone https://github.com/PaddlePaddle/Paddle.git

然后进行cmake配置，

rm -rf build
mkdir build
cd build
cmake  .. \
    -DWITH_CONTRIB=OFF \
    -DWITH_MKL=ON \
    -DWITH_MKLDNN=ON  \
    -DWITH_TESTING=OFF \
    -DCMAKE_BUILD_TYPE=Release \
    -DWITH_INFERENCE_API_TEST=OFF \
    -DON_INFER=ON \
    -DWITH_PYTHON=ON
make -j8
make install

执行make的时候出现下面的错误：

fatal: unable to access 'https://gitlab.com/libeigen/eigen.git/': gnutls_handshake() failed: Error in the pull function.
fatal: unable to access 'https://github.com/pybind/pybind11.git/': gnutls_handshake() failed: The TLS connection was non-properly terminated.
fatal: unable to access 'https://github.com/sandyhouse/gloo.git/': Failed to connect to github.com port 443: Connection timed out

网上去找方法也没有解决，最后发现把同样的命令再多执行几遍就好了。应该是我电脑网络问题，尝试的时候不要make clean,就重复执行make -j8。