SpectralAngleMapper#

class deepinv.loss.metric.SpectralAngleMapper(metric=None, complex_abs=False, train_loss=False, reduction=None, norm_inputs=None, center_crop=None)[source]#

Bases: Metric

Spectral Angle Mapper (SAM).

Calculates spectral similarity between estimated and target multispectral images.

Wraps the torchmetrics Spectral Angle Mapper function. Note that our reduction parameter follows our uniform convention (see below).

Note

By default, no reduction is performed in the batch dimension.

Example:

>>> import torch
>>> from deepinv.loss.metric import SpectralAngleMapper
>>> m = SpectralAngleMapper()
>>> x_net = x = torch.ones(3, 2, 8, 8) # B,C,H,W
>>> m(x_net, x)
tensor([0., 0., 0.])
Parameters:

  • train_loss (bool) – use metric as a training loss, by returning one minus the metric.

  • reduction (str) – a method to reduce metric score over individual batch scores. mean: takes the mean, sum takes the sum, none or None no reduction will be applied (default).

  • norm_inputs (str) – normalize images before passing to metric. l2 normalizes by \(\ell_2\) spatial norm, min_max normalizes by min and max of each input.

  • center_crop (int, tuple[int], None) – If not None (default), center crop the tensor(s) before computing the metrics. If an int is provided, the cropping is applied equally on all spatial dimensions (by default, all dimensions except the first two). If tuple of int, cropping is performed over the last len(center_crop) dimensions. If positive values are provided, a standard center crop is applied. If negative (or zero) values are passed, cropping will be done by removing center_crop pixels from the borders (useful when tensors vary in size across the dataset).

Examples using SpectralAngleMapper:#

Remote sensing with satellite images

Remote sensing with satellite images