Skip to content

Fix batch_invstd none in BatchNorm2D #421

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

Merged
merged 1 commit into from
Nov 8, 2022
Merged

Fix batch_invstd none in BatchNorm2D #421

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 tinygrad/nn/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ def __call__(self, x):
else:
batch_mean, batch_var = self.running_mean, self.running_var
# NOTE: this can be precomputed for static inference. if you manually update running_var, you have to reset this
if not hasattr(self, "batch_invstd"):
if not hasattr(self, "batch_invstd") or not self.batch_invstd:
self.batch_invstd = batch_var.add(self.eps)**-0.5
batch_invstd = self.batch_invstd

Expand Down