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

Rephrase documentation of adabelief #2704

Merged
merged 1 commit into from
May 18, 2022
Merged

Rephrase documentation of adabelief #2704

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion tensorflow_addons/optimizers/adabelief.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ def __init__(
rectify: boolean. Whether to apply learning rate rectification as
from RAdam.
total_steps: An integer. Total number of training steps. Enable
warmup by setting a positive value.
warmup by setting a value greater than zero.
Copy link
Contributor

Choose a reason for hiding this comment

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

I think that it was correct:
http://oeis.org/A000027
http://oeis.org/A001477

Copy link
Contributor Author

@denadai2 denadai2 May 18, 2022 •
edited
Loading

Choose a reason for hiding this comment

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

nice. However, "greater than zero" I think requires less expertise to be understood. I thought zero was a positive number for example, and I have a PhD.

Copy link
Contributor

@bhack bhack May 18, 2022 •
edited
Loading

Choose a reason for hiding this comment

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

There could be some confusion with signed zero but on integer I think it is hard to be confused. I will merge this as it is just an alternative.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

thanks

warmup_proportion: A floating point value. The proportion of
increasing steps.
min_lr: A floating point value. Minimum learning rate after warmup.
Expand Down