YOLOv5笔记（一）环境搭建

YOLOv5 笔记（一）环境搭建

环境搭建

系统和硬件版本 Ubuntu 22.04 LTS，RTX 3060

0. 安装 Anaconda

Anaconda 官网下载对应的 .sh 格式安装文件

配置 Anaconda 国内镜像

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --set show_channel_urls yes

1. 创建 YOLOv5 虚拟环境

conda create -n yolo python=3.7

conda activate yolov5

2. 安装 cuda

下载地址：cuda

wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-ubuntu2204.pin
sudo mv cuda-ubuntu2204.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/11.7.0/local_installers/cuda-repo-ubuntu2204-11-7-local_11.7.0-515.43.04-1_amd64.deb
sudo dpkg -i cuda-repo-ubuntu2204-11-7-local_11.7.0-515.43.04-1_amd64.deb
sudo cp /var/cuda-repo-ubuntu2204-11-7-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda

将 nvcc 增加至环境变量
vi ~/.bashrc
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64
export PATH=$PATH:/usr/local/cuda/bin
export CUDA_HOME=$CUDA_HOME:/usr/local/cuda
source ~/.bashrc

查看 nvcc 版本，判断是否安装成功

nvcc --version

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0

3. 安装 Pytorch

前往Pytorch 官网 查看可下载的 torch 版本

conda activate yolov5

conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch

4. 下载 YOLOV5 代码

git clone https://github.com/ultralytics/yolov5.git

cd yolov5

pip install -r requirements.txt

5. 训练测试

使用自带 coco128 数据集记性训练测试

python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights weights/yolov5s.pt

6. 推理测试

python detect.py --source ./data/images/ --weights weights/yolov5s.pt