-
Notifications
You must be signed in to change notification settings - Fork 19
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
Implementation of loss in the paper #4
Comments
Hello, The one to use is In our case the bounds were computed at the dataloader level from one of the class in bounds.py, though in the end they could come from anywhere. This code was already quite flexible (in the sense you can bound any function, not just size), you could simplify it a bit if you stick to a sizeloss or something like that. The bounds tensor, inside the
Depending on your setting, you could modify that to simplify it a bit if it is not needed. Let me know, Hoel |
Hello!
Which loss in losses.py is proposed by the paper?
It seems Pathak is the one to be compared.
The text was updated successfully, but these errors were encountered: