Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

基于6.2版本自动标注出现如下错误 #20

Open
freetan opened this issue Oct 18, 2022 · 3 comments
Open

基于6.2版本自动标注出现如下错误 #20

freetan opened this issue Oct 18, 2022 · 3 comments

Comments

@freetan
Copy link

freetan commented Oct 18, 2022

环境:python3.9 anacoda pytorch1.12 通过yolov5 6.2 版本 已经训练出模型,但是运行程序报错
image

@tangtang666
Copy link
Contributor

我测试了6.2 是可以的 你是不是用的是export.py 生成的模型 不是train.py 生成的pt模型

@XuHandsome
Copy link

+1

@XuHandsome
Copy link

XuHandsome commented Oct 30, 2022

yolov5 issue
找到了这个. 解决方法, 另外遇到一些其他问题,下面直接执行解决掉:

习惯构造linux命令,大概就是走官仓复制yolo.py到libs/models目录下

cd /opt/
git clone https://github.com/cnyvfang/labelGo-Yolov5AutoLabelImg.git
git clone https://github.com/ultralytics/yolov5.git
cp -Raf yolov5/utils labelGo-Yolov5AutoLabelImg/
cp -Raf yolov5/models/yolo.py labelGo-Yolov5AutoLabelImg/libs/models
pip install Ipython

上面执行完倒是可以调起来yolo5了, 但是发现新问题:
点击"auto lable",选择train.py训练好的权重文件".pt"后,报错如下:
image

看起来从权重里拿到的label序号之类的是数字类型, 但是这里在用+运算符去加str类型的换行符, 懒得深究了,不管出于什么原因, 秉承着能跑就行的原则, 临时改了下libs/autoLabeler.py第65行,顺利跑起来了..如下
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants