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

Why are BatchNorm layers frozen during training? #6

Open
zeakey opened this issue May 28, 2018 · 0 comments
Open

Why are BatchNorm layers frozen during training? #6

zeakey opened this issue May 28, 2018 · 0 comments

Comments

@zeakey
Copy link

zeakey commented May 28, 2018

So I notice that all your batchnorm layers are frozen with lr_mult=0.
I'm not very familiar with the detailed tricks of caffe's batchnorm layer.

Why did you freeze the batchnorm layers and what is the effect of doing so?

@zeakey zeakey changed the title Why are BatchNorm layers freezed during training? Why are BatchNorm layers frozen during training? May 28, 2018
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

1 participant