**
基于conda环境下YOLOv5安装和运行步骤
**
作者使用的环境为ubuntu16.04
ROS版本:kinetic
一 更换阿里云源
(1)命令行输入:
sudo gedit /etc/apt/sources.list
(2)在sources.list中用aliyun替换原来的源:
deb http://mirrors.aliyun.com/ubuntu/ xenial main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial main
deb http://mirrors.aliyun.com/ubuntu/ xenial-updates main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-updates main
deb http://mirrors.aliyun.com/ubuntu/ xenial universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial universe
deb http://mirrors.aliyun.com/ubuntu/ xenial-updates universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-updates universe
deb http://mirrors.aliyun.com/ubuntu/ xenial-security main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-security main
deb http://mirrors.aliyun.com/ubuntu/ xenial-security universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-security universe
(3)更新源:
sudo apt-get update
(4)可能会出现错误:
An error occurred during the signature verification. The repository is not updated and the previous index files will be used. GPG error: http://packages.ros.org/ros/ubuntu xenial InRelease: The following signatures were invalid: KEYEXPIRED 1622248854 | |
---|---|
解决办法:
首先要删除旧的密钥:
16.04以后的版本:
sudo apt-key del 421C365BD9FF1F717815A3895523BAEEB01FA116
然后添加新的密钥:
sudo -E apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654
更新:
sudo apt update
二 下载cuda、NVIDIA
(1)cuda下载
参考博客:https://blog.csdn.net/weixin_44401286/article/details/109203890
下载链接的页面中有对应的cuda版本,这里我选择的是cuda 10.2、ZEDSDK for Ubuntu 16这两个驱动版本https://developer.nvidia.com/cuda-10.2-download-archive?target_os=Linux&target_arch=x86_64&target_distro=Ubuntu&target_version=1604&target_type=deblocal
(2)根据cuda下载界面提示,采用如下方式下载:
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/cuda-ubuntu1604.pin
sudo mv cuda-ubuntu1604.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget http://developer.download.nvidia.com/compute/cuda/10.2/Prod/local_installers/cuda-repo-ubuntu1604-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb
cuda-repo-ubuntu1604-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb安装包可在百度网盘自行下载,链接:https://pan.baidu.com/s/1yVaMLR7ByI1y1vMti3xa9Q
提取码:1234
sudo dpkg -i cuda-repo-ubuntu1604-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb
sudo apt-key add /var/cuda-repo-10-2-local-10.2.89-440.33.01/7fa2af80.pub
sudo apt-get update
sudo apt-get -y install cuda #sudo apt-get install cuda-10.2
(3)安装好之后在~/.bashrc文件末尾添加如下:
export PATH=/usr/local/cuda/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda/lib64
(4)重启电脑
三 Anaconda3安装
(1)下载Anaconda3-2020.07-Linux-x86_64.sh
wget https://repo.anaconda.com/archive/Anaconda3-2020.07-Linux-x86_64.sh
安装包可在百度网盘自行下载,链接:https://pan.baidu.com/s/1j4NRMw_1oA27F-RneOD6yw
提取码:1234
(2)找到此安装包路径,并在当前路径下开启命令行,执行:
bash Anaconda3-2020.07-Linux-x86_64.sh
按yes;
指定安装路径;
按yes,出现下图界面,则说明安装成功;
(3)添加路径,在bashrc文件中输入:
sudo gedit ~/.bashrcexport PATH=$PATH:/home/software/anaconda3/bin
(4)在bashrc末尾添加:
conda deactivate
(5)重新打开新的命令行,输入,激活conda环境:
conda activate
四 YOLOv5安装
YOLOv5安装包和权重文件,自行提取
链接:https://pan.baidu.com/s/1aDn8WSfFtkSsttGFHdawrQ
提取码:1234
(1)激活conda环境;
conda activate
(2)将权重文件yolov5.pt放至weights文件夹,仔细阅读README.md;
(3)进入yolov5-3.1,可打开requirements.txt文件,查看并下载所需的软件包:
pip --default-timeout=100 install -r requirements.txt -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com --ignore-installed
(4)若出现以下类似错误,可单独下载所需的包(需要根据实际情况多次运行);
图片
pip install absl-py==0.4 -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com
(6)在bashrc文件下,指定python3.8编译;
sudo gedit ~/.bashrc
#在bashrc中添加python路径
export PYTHONPATH="/home/ubuntu16.04/anaconda3/lib/python3.8/site-packages:$PYTHONPATH"
(7)安装好需要的包之后,连接好摄像头运行:
python detect.py --weights weights/yolov5s.pt --source 0 --view-img
参考网址:
https://www.bilibili.com/video/BV1QT4y1J7rm/?spm_id_from=333.788.recommend_more_video.2 //目标检测YOLOv5,速度更快,最快可达140fps,体积更小,只有v4的1/9,基于pytorch框架,更易于移植