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

There is no L1 weightDecay in Torch. #120

Open

amirkhango opened this issue Jun 15, 2016 · 1 comment

amirkhango commented Jun 15, 2016

The weightDecay in Torch refers to L2, Yes?
So How can I implemment L1 weightDecay?

Kaixhin commented Aug 16, 2016

Example code for L1 and L2 weight decay (which is added manually in the training loop) can be found here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment