Yolov5环境安装配置学习笔记（1）

1、安装好anaconda

2、conda create -n yolov5 python=3.8

3、conda activate yolov5 或者 activate yolov5

conda无法使用activate_conda-script.py: error: argument command: invalid -CSDN博客
https://blog.csdn.net/hjxu2016/article/details/134248789

4、conda install pytorch torchvision torchaudio cpuonly -c pytorch

【Pytorch官网】PyTorch

选择conda版本，选择cpu版本，下面得到安装指令

5、验证torch版本

python

import torch

torch.__version__

6、安装好vscode并安装Python插件

7、下载yolov5.zip源码，并解压

yolov5: 同步更新官方最新版 Yolov5，发行版提供模型下载地址, Yolo8已发布: https://gitee.com/monkeycc/ultralytics

8、进入解压的文件并运行以下命令安装相关包

pip install -U -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

9、右下角切换编译器，用vscode打开项目文件夹yolov5-master，存放图片到路径yolov5-master\data\images，运行detect.py

 

10、  识别结果

YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients, 16.4 GFLOPs
image 1/4 E:\yolov5-master\yolov5-master\data\images\bus.jpg: 640x480 4 persons, 1 bus, 79.9ms

image 2/4 E:\yolov5-master\yolov5-master\data\images\family.jpg: 448x640 5 persons, 5 cups, 1 fork, 3 bowls, 1 sandwich, 1 chair, 1 dining table, 70.2ms

image 3/4 E:\yolov5-master\yolov5-master\data\images\jnu.webp: 448x640 20 persons, 4 bicycles, 2 potted plants, 68.3ms

image 4/4 E:\yolov5-master\yolov5-master\data\images\zidane.jpg: 384x640 2 persons, 2 ties, 67.0ms

Speed: 0.2ms pre-process, 71.4ms inference, 0.5ms NMS per image at shape (1, 3, 640, 640)

14 persons,1 chair,2 potted plants。

  参考资料：

        【基于Ubuntu下Yolov5的目标识别】保姆级教程 | 虚拟机安装 - Ubuntu安装 - 环境配置(Anaconda/Pytorch/Vscode/Yolov5) |全过程图文by.Akaxi_ubuntu yolo-CSDN博客
https://blog.csdn.net/Akaxi1/article/details/134222652