Scaleinvariantsignaldistortionratio

scaleinvariantsignaldistortionratio

Metric ScaleInvariantSignalDistortionRatio from torchmetrics (torchmetrics.ScaleInvariantSignalDistortionRatio)

When to invoke this skill

The user has predictions + ground truth and asks to evaluate with ScaleInvariantSignalDistortionRatio, or mentions torchmetrics.ScaleInvariantSignalDistortionRatio directly, or wants the standard torchmetrics implementation.

Reference signature

from torchmetrics import ScaleInvariantSignalDistortionRatio

# _ScaleInvariantSignalDistortionRatio(zero_mean: bool = False, **kwargs: Any) -> None

Library docstring

Wrapper for deprecated import.

>>> from torch import tensor
>>> target = tensor([3.0, -0.5, 2.0, 7.0])
>>> preds = tensor([2.5, 0.0, 2.0, 8.0])
>>> si_sdr = _ScaleInvariantSignalDistortionRatio()
>>> si_sdr(preds, target)
tensor(18.4030)

Quick recipe

import torchmetrics as _m
score = _m.ScaleInvariantSignalDistortionRatio(y_true, y_pred)

Don'ts

• Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
• Always check the library version's argument order — sklearn is (y_true, y_pred) while torchmetrics is (preds, target).