一、准备条件

1.下载yolov8

https://github.com/ultralytics/ultralytics

2.安装python

https://www.python.org/ftp/python/3.8.0/python-3.8.0-amd64.exe

3.安装依赖
进入ultralytics-main，执行：

pip install -r requirements.txt
pip install -U ultralytics

二、标注

1.安装pyqt5

pip install pyqt5 -i https://pypi.tuna.tsinghua.edu.cn/simple

2.安装labelme

pip install labelme -i https://pypi.tuna.tsinghua.edu.cn/simple

3.启动
labelimg 图片文件路径 标注的类别txt文件路径 标注结果txt文件路径

labelimg D:/Desktop/BicycleImgs/JPEGImages D:/Desktop/BicycleImgs/predefined_classes.txt D:/Desktop/BicycleImgs/Annotations

predefined_classes.txt内容：

E-bike

三、训练

1.到ultralytics所在的目录：

D:\workspace_all\pyCharm\ultralytics-main\ultralytics

2.放置位置如下：

3.ebike.yaml内容如下：

# Helmet
train: datasets/ebike/train
val: datasets/ebike/valid
test: datasets/ebike/test

# Classes
names:
  0: E-bike

4.在命令行，执行如下命令，进行训练：

yolo task=detect mode=train model=./models/yolov8s.pt data=./ebike.yaml epochs=300 batch=16

5.训练结果