Skip to content

Make batch norm mask shape error more descriptive #19829

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 2 commits into from
Jun 11, 2024
+9 −0
Merged

Make batch norm mask shape error more descriptive #19829

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
54e2729
Made batch norm mask shape error more descriptive
pandyah5 Jun 10, 2024
0502951
Added shape info in mask error message to help with degugging
pandyah5 Jun 11, 2024
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
9 changes: 9 additions & 0 deletions keras/src/layers/normalization/batch_normalization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,6 +214,15 @@ def compute_output_shape(self, input_shape):
return input_shape

def call(self, inputs, training=None, mask=None):
# Check if the mask has one less dimension than the inputs.
if mask is not None:
if len(mask.shape) != len(inputs.shape) - 1:
# Raise a value error
raise ValueError(
"The mask provided should be one dimension less than the inputs. "
f"Received: mask.shape={mask.shape}, inputs.shape={inputs.shape}"
)

input_dtype = standardize_dtype(inputs.dtype)
if input_dtype in ("float16", "bfloat16"):
# BN is prone to overflowing for float16/bfloat16 inputs, so we opt
Expand Down