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

天池语义分割代码求教 #14

Open
jinghehehe opened this issue Feb 19, 2021 · 3 comments
Open

天池语义分割代码求教 #14

jinghehehe opened this issue Feb 19, 2021 · 3 comments

Comments

@jinghehehe
Copy link

您好,我尝试使用您的baseline,现想去掉混合精度训练,如图,但是损失变为nan,不知道具体原因,请大佬解惑。
微信图片_20210219114030

@DLLXW
Copy link
Owner

DLLXW commented Feb 21, 2021

您好,我尝试使用您的baseline,现想去掉混合精度训练,如图,但是损失变为nan,不知道具体原因,请大佬解惑。
微信图片_20210219114030

train.py里面·的·@autocast()要删掉,但我不清楚是不是这个原因哈,为NaN的话你可以尝试调节下学习率啥的,或者是标签有问题

@jinghehehe
Copy link
Author

jinghehehe commented Feb 22, 2021 via email

@ChenMeng130
Copy link

ChenMeng130 commented Mar 10, 2022

image

RuntimeWarning: invalid value encountered in true_divide
iu = np.diag(self.hist) / (self.hist.sum(axis=1) + self.hist.sum(axis=0) - np.diag(self.hist))
您好,请问为什么会有除数为0的报错,我用了已经用process.py处理过数据集,请大佬解惑
我给self.hist加了个很小的值,应该可以除数为0的问题

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