Explicitly set reduction for Focal loss

[simonreise]

Focal loss have a reduction parameter, but it is not set as a self.reduction value.

This does not affect loss functionality, but it can be misleading, because by default __init__ function of _Loss sets self.reduction to "mean".

For example:

>>> loss = smp.losses.FocalLoss(..., reduction="none")
>>> loss.reduction
'mean'

This can make checks like this fail, while they should pass

if hasattr(loss, "reduction") and loss.reduction != "none":
    raise ValueError("basic loss must have reduction = none")

This is a purely cosmetical addition that should not affect anything but can improve user experience

[qubvel]

Thanks, makes sense!

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 1 line in your changes missing coverage. Please review.

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

Files with missing lines	Coverage Δ
segmentation_models_pytorch/losses/focal.py	27.02% <0.00%> (-0.76%)	⬇️

🚀 New features to boost your workflow:

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