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

Address Shawns CR on previous PR #270

Merged
merged 1 commit into from
Oct 29, 2024
Merged

Address Shawns CR on previous PR #270

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
4 changes: 3 additions & 1 deletion fl4health/utils/nnunet_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -430,8 +430,10 @@ def __init__(
initial_lr (float): The initial learning rate of the optimizer.
max_steps (int): The maximum total number of steps across all FL rounds.
exponent (float): Controls how quickly LR descreases over time. Higher values
lead to more rapdid descent.
lead to more rapdid descent. Defaults to 0.9.
Copy link
Collaborator

Choose a reason for hiding this comment

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

Super minor but I think rapdid is supposed to be rapid?

steps_per_lr (int): The number of steps per LR before decaying.
(ie 10 means the LR will be constant for 10 steps prior to being decreased to the subsequent value).
Defaults to 250 as that is the default for nnunet (decay LR once an epoch and epoch is 250 steps).
"""
self.optimizer = optimizer
self.initial_lr = initial_lr
Expand Down