# Scaleinvariantsignaldistortionratio

> Compute the ScaleInvariantSignalDistortionRatio metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute ScaleInvariantSignalDistortionRatio, or asks how to score with ScaleInvariantSignalDistortionRatio.

- Skill: `qhjqhj00/scaleinvariantsignaldistortionratio` (Agent Skill)
- Install (CLI): `npx skillmds add qhjqhj00/scaleinvariantsignaldistortionratio`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qhjqhj00/scaleinvariantsignaldistortionratio/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: qhjqhj00 (https://skillmd.com/u/qhjqhj00)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/qhjqhj00/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

```python
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

```python
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)`.