Skip to content

fix EMAModel.use_ema_warmup#9812

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

Closed
chenguolin wants to merge 1 commit into from
Closed

fix EMAModel.use_ema_warmup#9812

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
5 changes: 1 addition & 4 deletions src/diffusers/training_utils.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -341,9 +341,6 @@ def __init__(
)
parameters = parameters.parameters()

# set use_ema_warmup to True if a torch.nn.Module is passed for backwards compatibility
use_ema_warmup = True

if kwargs.get("max_value", None) is not None:
deprecation_message = "The `max_value` argument is deprecated. Please use `decay` instead."
deprecate("max_value", "1.0.0", deprecation_message, standard_warn=False)
Expand DownExpand Up@@ -414,7 +411,7 @@ def get_decay(self, optimization_step: int) -> float:
if self.use_ema_warmup:
cur_decay_value = 1 - (1 + step / self.inv_gamma) ** -self.power
else:
cur_decay_value = (1 + step) / (10 + step)
cur_decay_value = self.decay

cur_decay_value = min(cur_decay_value, self.decay)
# make sure decay is not smaller than min_decay
Expand Down