qhjqhj00 spectralanglemapper
Metric
SpectralAngleMapperfromtorchmetrics(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
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
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).