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

Add smooth_l1_loss to Paddle frontend and test #18470

Closed
wants to merge 4 commits into from
Closed

Add smooth_l1_loss to Paddle frontend and test #18470

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a545701
added Sigmoid activation to Paddle frontend and test
Jul 5, 2023
17f83a3
Add smooth_l1_loss to Paddle frontend and test
Jul 6, 2023
5bbdd98
Delete unrelated commit
peterwisu Jul 6, 2023
baf95d6
Delete test_paddle_activation.py
peterwisu Jul 6, 2023
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
211 changes: 0 additions & 211 deletions ivy/functional/frontends/paddle/nn/functional/activation.py
View file
Open in desktop

This file was deleted.

23 changes: 23 additions & 0 deletions ivy/functional/frontends/paddle/nn/functional/loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,3 +101,26 @@ def cosine_embedding_loss(
out = ivy.sum(out)

return out


@with_supported_dtypes({"2.5.0 and below": ("float32", "float64")}, "paddle")
@to_ivy_arrays_and_back
def smooth_l1_loss(
input,
label,
reduction='mean',
delta=1.0,
name=None,
):
sum_diff = ivy.abs(input - label).astype(label.dtype)
condition = sum_diff <= delta
out = ivy.where(condition, 0.5 * ivy.pow(ivy.abs(input - label), 2).astype(label.dtype),
(delta * ivy.abs(ivy.abs(input - label))).astype(label.dtype)
- (0.5 * ivy.pow(delta, 2)).astype(label.dtype))
if reduction == "none":
pass
elif reduction == "mean":
out = ivy.mean(out)
elif reduction == "sum":
out = ivy.sum(out)
return out.astype(label.dtype)
Loading
Loading