Totalvariation

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

# totalvariation

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

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics import TotalVariation

# _TotalVariation(reduction: Literal['mean', 'sum', 'none', None] = 'sum', **kwargs: Any) -> None
```

## Library docstring

```
Wrapper for deprecated import.

>>> from torch import rand
>>> tv = _TotalVariation()
>>> img = rand(5, 3, 28, 28)
>>> tv(img)
tensor(7546.8018)
```

## Quick recipe

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