credit.losses.almost_fair_crps

credit.losses.almost_fair_crps#

Classes#

AlmostFairKCRPSLoss

Calculates CRPS loss that has corrections for very small ensembles.

Module Contents#

class credit.losses.almost_fair_crps.AlmostFairKCRPSLoss(alpha=1.0, reduction='mean', no_autocast=True)#

Bases: torch.nn.Module

Calculates CRPS loss that has corrections for very small ensembles.

alpha = 1.0#
reduction = 'mean'#
no_autocast = True#
batched_forward#
forward(target, pred)#
single_sample_forward(target, pred)#
Parameters:

  • target – shape (1, c, t, lat, lon)

  • pred – shape (ensemble, c, t, lat, lon)

Returns:

shape (c, t, lat, lon)

Return type:

crps

_kernel_crps(preds: torch.Tensor, targets: torch.Tensor, alpha: float)#
Parameters:

  • preds – (c, t, lat, lon, ensemble)

  • targets – (c, t, lat, lon)

Returns:

(c, t, lat, lon)

Return type:

crps