安装openpose

1、安装opencv
下载opencv
(1)安装依赖：
sudo apt-get install build-essentia
sudo apt-get install cmake
sudo apt-get install build-essential libgtk2.0-dev libavcodec-dev libavformat-dev libjpeg.dev libtiff4.dev libswscale-dev libjasper-dev
（2）解压OPENCV
cd opencv
mkdir build
cd build
cmake .
make
sudo make install
(3)测试：pkg-config --cflags --libs opencv

licaibiao@ubuntu:~/test/OpenCV$ pkg-config --cflags --libs opencv
-I/usr/local/include/opencv -I/usr/local/include -L/usr/local/lib -lopencv_shape -lopencv_stitching -lopencv_objdetect -lopencv_superres -lopencv_videostab -lopencv_calib3d -lopencv_features2d -lopencv_highgui -lopencv_videoio -lopencv_imgcodecs -lopencv_video -lopencv_photo -lopencv_ml -lopencv_imgproc -lopencv_flann -lopencv_core

(4)运行一个最简单的程序

#include <cv.h>
#include <highgui.h>
#include <opencv2/core/core.hpp>
 #include <opencv2/highgui/highgui.hpp>
 
using namespace cv;
int main( int argc, char** argv )
{
    Mat image;
    image = imread( argv[1], 1 );
 
    if( argc != 2 || !image.data )
    {
        printf( "No image data \n" );
        return -1;
    }
 
    namedWindow( "Display Image", CV_WINDOW_AUTOSIZE );
    imshow( "Display Image", image );
    waitKey(0);
 
    return 0;
}

cmake运行：
首先制作一个CMakeLists.txt文件，

project( DisplayImage )
find_package( OpenCV REQUIRED )
add_executable( DisplayImage DisplayImage.cpp )
target_link_libraries( DisplayImage ${OpenCV_LIBS} )

执行：cmake .
make

g++执行，g++ test.cpp -o test1 pkg-config --cflags --libs opencv（注意左右的引号是左上角的）

添加链接描述
2、安装Caffe 可能要将nvidia-cuda-toolkits 卸载 https://github.com/NVIDIA/DIGITS/issues/1400#issuecomment-357024396
https://blog.csdn.net/yhaolpz/article/details/71375762
https://blog.csdn.net/yhaolpz/article/details/71375762
安装Caffe之前首先安装好cuda+cudnn
(1)查看cuda版本：nvcc -V
查看cat /usr/local/cuda/include/cudnn.h | grep CUDNN_MAJOR -A 2
(2)
sudo cp Makefile.config.example Makefile.config
sudo gedit Makefile.config

3、安装openpose
安装openpose的前提是安装好opencv,caffe,cuda,cudnn
几篇参考：
安装Caffe
安装openpose详细教程
安装openpose教程2
caffe下载地址gitee
openpose下载地址gitee

4、安装STGCN,
依赖：openpose,pytorch(>0.4),ffmpeg,
其他依赖：PyYAML sk-video
下载STGCN
下载后
cd torchlight
python setup.py install (可能需要sudo权限)
cd …
bash tools/get_models.sh

python main.py demo --openpose [–video --device ]
example: sudo python main.py demo --openpose /home/ray/openposeT/openpose/build --video /home/ray/Desktop/STGCN/st-gcn/resource/media/ta_chi2.mp4 --device 0