Spectralanglemapper

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

# spectralanglemapper

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

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics import SpectralAngleMapper

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

## Library docstring

```
Wrapper for deprecated import.

>>> from torch import rand
>>> preds = rand([16, 3, 16, 16])
>>> target = rand([16, 3, 16, 16])
>>> sam = _SpectralAngleMapper()
>>> sam(preds, target)
tensor(0.5914)
```

## Quick recipe

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