简单记录下,AlphaPose在win10系统下的编译,过程较为顺利!,先看效果
官方github 地址,
https://github.com/MVIG-SJTU/AlphaPose
本次编译的版本:
Aug 2020: v0.4.0 version of AlphaPose is released! Stronger tracking! Include whole body(face,hand,foot) keypoints!
官方的install guide
https://github.com/MVIG-SJTU/AlphaPose/blob/master/docs/INSTALL.md
windows的安装要求
Windows users should install Visual Studio due to the problem mentioned here. If you do not want to install Visual Studio and want to use AlphaPose, you can refer to our previous version that do not require Visual Studio.
For Windows user, if you meet error with PyYaml, you can download and install it manually from here: https://pyyaml.org/wiki/PyYAML. If your OS platform is Windows, make sure that Windows C++ build tool like visual studio 15+ or visual c++ 2015+ is installed for training.
所以要求就是:
C++ 的编译器是 vs2013-Vs2017,其他版本肯定不行,因为博主编译用的vs2019,然后失败了,卸载就行了,换成要求的版本
cmd命令安装即可
1. Create a conda virtual environment.
conda create -n alphapose python=3.6 -y
conda activate alphapose
2. Install PyTorch
conda install pytorch1.1.0 torchvision0.3.0,
//没有明确要求,可以根据自己的情况灵活更改,末尾我加上自己的环境配置
3. Get AlphaPose
git clone https://github.com/MVIG-SJTU/AlphaPose.git
cd AlphaPose
//下载工程代码之后,记得下载相关的模型文件,https://github.com/MVIG-SJTU/AlphaPose/blob/master/docs/MODEL_ZOO.md,我用的是26个关键点
4. install
export PATH=/usr/local/cuda/bin/: P A T H e