torchgeo.losses

TorchGeo losses.

class torchgeo.losses.QRLoss(*args, **kwargs)

Bases: Module

The QR (forward) loss between class probabilities and predictions.

This loss is defined in ‘Resolving label uncertainty with implicit generative models’.

New in version 0.2.

forward(probs, target)

Computes the QR (forwards) loss on prior.

Parameters:

• probs (Tensor) – probabilities of predictions, expected shape B x C x H x W.

• target (Tensor) – prior probabilities, expected shape B x C x H x W.

Returns:

qr loss

Return type:

Tensor

class torchgeo.losses.RQLoss(*args, **kwargs)

Bases: Module

The RQ (backwards) loss between class probabilities and predictions.

This loss is defined in ‘Resolving label uncertainty with implicit generative models’.

New in version 0.2.

forward(probs, target)

Computes the RQ (backwards) loss on prior.

Parameters:

• probs (Tensor) – probabilities of predictions, expected shape B x C x H x W

• target (Tensor) – prior probabilities, expected shape B x C x H x W

Returns:

qr loss

Return type:

Tensor