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

batch proportion instead of batch size #17

Open
topepo opened this issue Dec 4, 2020 · 1 comment
Open

batch proportion instead of batch size #17

topepo opened this issue Dec 4, 2020 · 1 comment

Comments

@topepo
Copy link
Member

topepo commented Dec 4, 2020

This would be much easier to tune

@dfalbel
Copy link
Collaborator

dfalbel commented Dec 4, 2020

I think we usually tune the batch_size to be small as possible while making good estimates of the gradient and that shouldn't depend on the dataset size.

Maybe we could accept both integers and fractions and just interpret (0-1] as fractions and >1 as batch_size?

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

2 participants