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.

Sign up for GitHub

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

Jump to bottom

Loss is Nan #96

Open
SeinoNana opened this issue Nov 29, 2021 · 6 comments
Open

Loss is Nan #96

SeinoNana opened this issue Nov 29, 2021 · 6 comments

Comments

@SeinoNana
Copy link

hi, i am sorry to trouble you.
But why my loss values are Nan
image
@ZhengWugeng
Copy link

Maybe you try a smaller initial learning rate?

@JOOHYUN-KANG
Copy link

Did you solve it?

@dongttttttttt
Copy link

Hi, I'm having the same problem you're having, do you know how to fix it?Thanks!

@Pearyong
Copy link

hello,could you please how you can solve this problem ? i need you

@Pearyong
Copy link

Pearyong commented Nov 2, 2023

hi, i am sorry to trouble you. But why my loss values are Nan image

i konw how to deal wiht the problem, you can rm env and then install python 3.10 ,and the question is solved .

@bigKursen
Copy link

hi, i am sorry to trouble you. But why my loss values are Nan image

i konw how to deal wiht the problem, you can rm env and then install python 3.10 ,and the question is solved .

do you change torchvison cudatoolkkit or somethingelse version?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
6 participants
@ZhengWugeng @SeinoNana @JOOHYUN-KANG @dongttttttttt @Pearyong @bigKursen