fix: TorchFix Errors

[isaaccorley]

Running the torchfix linter results in the following errors. This PR fixes these.

segmentation_models_pytorch/base/heads.py:13:13: TOR101 Use of deprecated function torch.nn.UpsamplingBilinear2d
segmentation_models_pytorch/decoders/deeplabv3/decoder.py:108:19: TOR101 Use of deprecated function torch.nn.UpsamplingBilinear2d
segmentation_models_pytorch/losses/_functional.py:229:33: TOR106 Use `torch.log1p(x)` instead of `torch.log(1 + x)`. It is more accurate for small values of `x`.

[Copilot]

Pull request overview

This PR addresses deprecation warnings from the torchfix linter by replacing deprecated PyTorch functions with their modern equivalents. The changes improve code accuracy and prevent future compatibility issues.

• Replaced torch.nn.UpsamplingBilinear2d with torch.nn.Upsample(mode="bilinear") in two locations
• Replaced torch.log(1 + x) with torch.log1p(x) for improved numerical accuracy

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
segmentation_models_pytorch/base/heads.py	Updated upsampling layer to use non-deprecated API
segmentation_models_pytorch/decoders/deeplabv3/decoder.py	Updated upsampling layer to use non-deprecated API
segmentation_models_pytorch/losses/_functional.py	Improved numerical accuracy in wing loss calculation

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[codecov]

Codecov Report

❌ Patch coverage is 66.66667% with 1 line in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
segmentation_models_pytorch/losses/_functional.py	0.00%	1 Missing ⚠️

Files with missing lines	Coverage Δ
segmentation_models_pytorch/base/heads.py	94.44% <ø> (ø)
...ation_models_pytorch/decoders/deeplabv3/decoder.py	98.68% <100.00%> (ø)
segmentation_models_pytorch/losses/_functional.py	60.33% <0.00%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Copilot]

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Setting align_corners=True changes the upsampling behavior compared to the deprecated UpsamplingBilinear2d which used align_corners=False by default. This could affect model output and should be verified against existing trained models. Consider using align_corners=False to maintain backward compatibility unless the behavior change is intentional.

Suggested change

	nn.Upsample(mode="bilinear", scale_factor=upsampling, align_corners=True)
	nn.Upsample(mode="bilinear", scale_factor=upsampling, align_corners=False)

[qubvel]

@isaaccorley can we keep the previous behaviour with align_corners=False?

[isaaccorley]

I actually tried this initially but this caused the logit tests to fail. I believe this means that the original pretrained checkpoints used align_corners=True.

[qubvel]

Thanks for the update! Just a question re align corners

[qubvel]

@isaaccorley can we keep the previous behaviour with align_corners=False?