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

Jump to bottom

Update MeanAbsoluteError loss reduction #20254

Draft
wants to merge 2 commits into
base: master
Choose a base branch
from
Draft

Update MeanAbsoluteError loss reduction #20254

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9bb31c7
Update MeanAbsoluteError loss reduction
divyashreepathihalli Sep 12, 2024
d16d8dd
update losses MAE
divyashreepathihalli Sep 12, 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
11 changes: 8 additions & 3 deletions keras/src/losses/loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,7 +123,7 @@ def squeeze_or_expand_to_same_rank(x1, x2, expand_rank_1=True):
return x1, x2


def reduce_values(values, reduction="sum_over_batch_size"):
def reduce_values(values, reduction="sum_over_batch_size", sample_weight=None):
if (
reduction is None
or reduction == "none"
Expand All @@ -132,7 +132,12 @@ def reduce_values(values, reduction="sum_over_batch_size"):
):
return values
loss = ops.sum(values)
if reduction == "sum_over_batch_size":
if sample_weight is not None and reduction == "sum_over_batch_size":
loss /= ops.cast(
ops.sum(sample_weight),
loss.dtype,
)
elif reduction == "sum_over_batch_size":
loss /= ops.cast(
ops.prod(ops.convert_to_tensor(ops.shape(values), dtype="int32")),
loss.dtype,
Expand Down Expand Up @@ -169,7 +174,7 @@ def reduce_weighted_values(
values = values * sample_weight

# Apply reduction function to the individual weighted losses.
loss = reduce_values(values, reduction)
loss = reduce_values(values, reduction, sample_weight)
return loss


Expand Down
Loading