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

NaN when training on kitti dataset #165

Open
FelippeRoza opened this issue Jan 22, 2020 · 0 comments
Open

NaN when training on kitti dataset #165

FelippeRoza opened this issue Jan 22, 2020 · 0 comments

Comments

@FelippeRoza
Copy link

I'm trying to train a model for kitti dataset, but always get NaN for the losses. I've already tried to change the learning rate and checked the input format, as suggested in #128, but everything looks right.

I guess it may be related to the weird dimensions of kitti dataset, but not sure about how to solve it.
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
1 participant
@FelippeRoza