Signalnoiseratio

---
name: signalnoiseratio
description: Compute the SignalNoiseRatio metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute SignalNoiseRatio, or asks how to score with SignalNoiseRatio.
metadata:
  skill_kind: metric
  source_lib: torchmetrics
  import_path: torchmetrics.SignalNoiseRatio
  source: library_introspection
---

# signalnoiseratio

> Metric `SignalNoiseRatio` from `torchmetrics` (torchmetrics.SignalNoiseRatio)

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics import SignalNoiseRatio

# _SignalNoiseRatio(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])
>>> snr = _SignalNoiseRatio()
>>> snr(preds, target)
tensor(16.1805)
```

## Quick recipe

```python
import torchmetrics as _m
score = _m.SignalNoiseRatio(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)`.