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

batch norm updates #13

Open
edgarriba opened this issue Apr 10, 2017 · 1 comment
Open

batch norm updates #13

edgarriba opened this issue Apr 10, 2017 · 1 comment

Comments

@edgarriba
Copy link

Hi, any hint about how does batch norm update and why you do the following?

bn_updates = [(p, m * 0.05 + p * 0.95) for p, m in pop_updates]

Just trying to mimic the same behavior in Pytorch but not sure what are p and m and when this update happens during the execution.
@IshmaelBelghazi
Copy link
Owner

This line estimate the population statistics during training using a moving average. p and m stand for the parameters before and after the update respectively.

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
2 participants
@IshmaelBelghazi @edgarriba