ubuntu16.04编译seetaface

来源：互联网发布：淘宝客服每人的数据编辑：程序博客网时间：2024/05/16 09:14

本文大部分内容来自：
http://www.cnblogs.com/makefile/p/6059833.html
和
http://blog.csdn.net/u013718481/article/details/52994346?locationNum=15&fps=1
侵删。
该编译测试过程作为记录备忘。

1，下载seetaface源码

git clone https://github.com/seetaface/SeetaFaceEngine.git

2、安装opencv

sudo apt-get install libopencv-dev

3、升级cmake

sudo add-apt-repository ppa:george-edison55/cmake-3.xsudo apt-get updatesudo apt-get install cmake

4、安装解压工具

sudo apt-get install unrar

5，编译facedetection

mkdir ~/seeta/seetaface将下载文档中FaceDetection,FaceAlignment,FaceiDentification三个文件夹负责到~/seeta/seetafacecd ~/seeta/seetaface/FaceDetection/#新建一个build文件夹mkdir buildcd buildcmake ..sudo make -j4

6、测试facedetection
在当前目录下有一个facedet_test文件

#命令原型是./facedet_test image_path model_path./facedrt_test ../data/0_1_1.jpg ../model/seeta_fd_frontal_v1.0.bin

7、编译facealignment

cd ~/seeta/seetaface/FaceAlignmentmkdir buildcd buildcmake ..#将FaceDetection/include/face_detection.h和#FaceDetection/build/libseeta_facedet_lib_so分别拷贝到#FaceAlignment/include和FaceAlignment/build目录下#将FaceAlignment/src/cfan.cpp里面所有的isnan修改成std::isnansudo make -j4

8、测试facealignment
编译成功，但测试提示‘段错误’，应该是模型或者图片路径出错，因该模块不需单独使用，暂时不管了。

9、编译faceidentification

cd ~/seeta/seetaface/FaceIdentificationmkdir buildcd build将libseeta_facedet_lib.so,libseeta_fa_lib.so拷贝到~/seeta/seetaface/FaceIdentification/build目录下将face_alignment.h,face_detection.h拷贝到~/seeta/seetaface/FaceIdentification/include目录下在src/test/CMakeLists.txt文件循环前添加link_directories(${PROJECT_BINARY_DIR})修改src/test/CMakeLists.txt，添加两个链接文件  add_executable(${BIN} ${f})  target_link_libraries(${BIN} viplnet ${OpenCV_LIBS} seeta_facedet_lib seeta_fa_lib)将model目录中的模型解压cmake .. sudo make -j4

0 1