Linux硬件加速开源人脸识别引擎SeetaFace：第一步配置开源代码

1. 安装OpenCV 这个一开始配置&＃xff0c;消耗时间&＃xff0c;主要就交叉编译的问题&＃xff0c;网上查一下&＃xff0c;最后test一下成功就OK

2. copy开源Seetaface
   

3. 第一步进入FaceDetection
   PS&＃xff1a;因为build下是别人生成的额&＃xff0c;我生成的都放在build2下&＃xff0c;一样的
   &＃xff01;&＃xff01;&＃xff01;&＃xff01;&＃xff01;&＃xff01;操作步骤必须和Readme一样&＃xff01;&＃xff01;&＃xff01;&＃xff01;&＃xff01;
   我们在Linux上操作所以只要做这部分&＃xff1a;

How to Build in Linux

1. Build

mkdir build
cd build
cmake ..
make -j${nproc}2. Run demo
-shell
./build/facedet_test image_file model/seeta_fd_frontal_v1.0.bin

这一步为生成seeta_fd_frontal_v1.0.bin&＃xff0c;后面需要使用&＃xff01;
我运行test的结果&＃xff1a;

1. 第二步进入FaceAlignment
   同样根据Readme

### Build in Linuxmkdir build//copy the "face detection lib" and "face_detection.h" to the //directory "build" for building the test example.cd build
cmake ..
makeIf everything goes fine, move on to test the program. Note: you should copy the face detetion model [seeta_fd_frontal_v1.0.bin](../FaceDetection/model/seeta_fd_frontal_v1.0.bin) to the directory "build" before testing.cd ..
./build/fa_testThe alignment results are stored in "result.jpg".

运行test后build下为&＃xff1a;

6. 第三步进入Indentification
同样根据Readme

Linux & Mac OS

//Change current working directory to &＃96;SeetaFace/FaceIdentification&＃96; //and run the following command:mkdir build
cd build
cmake .. && make//If everything goes fine, move on to test the program:
./build/src/test/test_face_recognizer.bin

要把之前需要用到的lib和bin拷贝过来&＃xff0c;因为识别需要之前的人脸标注和特征点

运行test完成表明配置完成了&＃xff01;

自己根据项目改的结果
一些数据也被注释掉了。反正要出好多数据

程序运行终于的问题总结:

1、mkdir build 将src/test 下的facedetection cpp 加入头文件include 在build 下make2、./build2/facedet_test image_file ./model/seeta_fd_frontal_v1.0.bin3、提示&＃xff1a;copy the "face detection lib":libseeta_facedet_lib.a and "face_detection.h" to the directory "build" for building the test example.4、在Alignment里build2下运行./fa_test 5、Identification问题&＃xff1a;/usr/bin/ld: cannot find -lseeta_facedet_lib/usr/bin/ld: cannot find -lseeta_fa_lib6、要在make之后的FaceIdentification的build2中加入图像 pic1 pic2 pic1_g pic2_g
还要加入seeta_fa_v1.1bin & seeta_fd_frontal_v1.0.bin 这两个其他文件的moudle7、首先在build2下 进行 ./src/test/test_face_verification.bin 成功8、在到Identification下的src 的test中对test_face_recognizer.cpp修改需要添加如下缺少的代码后重新再build2下make#include
#include #include "face_identification.h"
#include "common.h"#include "math.h"
#include "time.h"
#include
#include
#include <string>
#include #include
#include #include "ctime"#include "common_net.h"
#include "bias_adder_net.h"
#include "bn_net.h"
#include "conv_net.h"
#include "eltwise_net.h"
#include "inner_product_net.h"
#include "max_pooling_net.h"
#include "spatial_transform_net.h"
#include "pad_net.h"using namespace seeta;
REGISTER_NET_CLASS(Common);
REGISTER_NET_CLASS(BiasAdder);
REGISTER_NET_CLASS(Bn);
REGISTER_NET_CLASS(Conv);
REGISTER_NET_CLASS(Eltwise);
REGISTER_NET_CLASS(InnerProduct);
REGISTER_NET_CLASS(MaxPooling);
REGISTER_NET_CLASS(SpatialTransform);
REGISTER_NET_CLASS(Pad);1、按照READme操作&＃xff0c;Detection-----Alignment------Identification新建build文件夹&＃xff0c;在下面生成文件