1.安装cmake sudo apt install cmake tar -zxv -f cmake-3.13.3.tar.gz cd cmake-3.13.3 ./bootstrap make make install 2.安装openssl和编译依赖 sudo apt install openssl sudo apt install libssl-dev
https://github.com/NVIDIA-AI-IOT/trt_pose This project features multi-instance pose estimation accelerated by NVIDIA TensorRT. It is ideal for applications where low latency is necessary. It includes Training scripts to train on any keypoint task data in MSCOCO format A collection of models that may be easily optimized with TensorRT using torch2trt This project can be used easily for the task of human pose estimation, or extended for something new. contains convert pytorch model into tensorrt model
https://github.com/NVIDIA-AI-IOT/trt_pose This project features multi-instance pose estimation accelerated by NVIDIA TensorRT. It is ideal for applications where low latency is necessary. It includes Training scripts to train on any keypoint task data in MSCOCO format A collection of models that may be easily optimized with TensorRT using torch2trt This project can be used easily for the task of human pose estimation, or extended for something new. Below are models pre-trained on the MSCOCO dataset. The throughput in FPS is shown for each platform
1）下载cmake-3.8.2.tar.gz : https://cmake.org/files/ 2) 在主文件夹下新建tools/文件夹，将cmake-3.8.2.tar.gz解压之后放在tools/中，为了防止出现权限不足问题，直接对文件更改权限： 解压：sudo tar -zxvf cmake-3.8.2.tar.gz 赋权限：sudo chmod -R 777 cmake-3.8.2 3)a安装gcc-c++: sudo apt-get install build-essential 或者直接执行这两条命令 sudo apt-get install gcc sudo apt-get install g++ 4)进入文件夹下执行以下命令： sudo ./bootstrap sudo make sudo make install 5)查看是否安装成功以及安装版本： cmake --version
dlib-19.7 附安装教程，亲测可用，完美运行 https://blog.csdn.net/qq_42393859/article/details/90512030
