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

Use Adam optimizer for quick start #620

Merged
merged 1 commit into from
Dec 28, 2022

Conversation

mattdangerw
Copy link
Member

AdamW is still in experimental, has some bad bugs in tf 2.9 (which is default on colab), and may need some other tricks to really do best (e.g. a learning rate with some decay).

For now, let's keep it simple and robust with Adam, and ship some compilation defaults soon that remove the need for this at all!

@mattdangerw mattdangerw requested a review from jbischof December 28, 2022 19:14
Copy link
Contributor

@jbischof jbischof left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. In the "getting started" guide we can easily control the pip install, but this code is "grab and go" and should not be fragile.

@mattdangerw mattdangerw merged commit d1500aa into keras-team:master Dec 28, 2022
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

Successfully merging this pull request may close these issues.

2 participants