yolov5在Centos系统上部署的环境搭建
yolov5在Centos系统上部署的环境搭建
一.安装Anaconda3
1.下载Anaconda3安装包 :
https://repo.anaconda.com/archive/
wget https://repo.anaconda.com/archive/Anaconda3-2020.02-Linux-x86_64.sh
2.执行安装命令:
bash Anaconda3-2018.12-Linux-x86_64.sh
3.选择安装路径:
Anaconda3 will now be installed into this location:/root/anaconda3 - Press ENTER to confirm the location - Press CTRL-C to abort the installation - Or specify a different location below
[/root/anaconda3] >>> /usr/local/anaconda3
4.选择是否安装VSCode,输入no来结束安装
Do you wish to proceed with the installation of Microsoft VSCode? [yes|no]>>> Please answer 'yes' or 'no':>>> no
5.配置环境变量
vi /etc/profile
在尾部加下如下
export PATH=/opt/module/anaconda3/bin:$PATH
按下esc再键入 :wq 保存退出
最后执行如下使环境变量生效
source /etc/profile
6.验证安装,输入如下命令:
conda list
略........
7.创建python3环境
conda create -n pytorch python=3.7
8.切换到python3
source activate pytorch
二.安装pytorch的GPU版本
1.来到官网 https://pytorch.org/get-started/locally/
根据自己的环境,进行选择,网站会给出相应的安装命令。我这里的环境是linux
、pip
、cuda 11.2
pip3 install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
Looking in links: https://download.pytorch.org/whl/torch_stable.html
pip install ipython
安装完pytorch
后,我们在ipython
中查看安装的结果
说明GPU
版本的pytorch
安装成功
2.YOLOv5测试
首先还是把源码clone
到本地
zip解压:
unzip yolov5_deepsort_car.zip
3.安装项目依赖:
(pytorch) [root@107 yolov5_deepsort_car]# pip install -r requirements.txt -i https://pypi.douban.com/simple
linux下安装Anaconda3如果遇到找不到bzip2:
解决办法:yum -y install bzip2
参考地址1:https://blog.csdn.net/u011435933/article/details/107045530/
参考地址3:https://xugaoxiang.com/2020/06/17/yolov5/