DistributionNLL

class torch_uncertainty.metrics.regression.DistributionNLL(reduction='mean', **kwargs)

The Negative Log Likelihood Metric.

Parameters:

• reduction (str, optional) –

  Determines how to reduce over the \(B\)/batch dimension:

  • 'mean' [default]: Averages score across samples

  • 'sum': Sum score across samples

  • 'none' or None: Returns score per sample

• kwargs – Additional keyword arguments, see Advanced metric settings.

Inputs:

• probs: \((B, C)\)

• target: \((B)\)

where \(B\) is the batch size and \(C\) is the number of classes.

Warning

Make sure that the probabilities in probs are normalized to sum to one.

Raises:

ValueError – If reduction is not one of 'mean', 'sum', 'none' or None.

compute()

Computes NLL based on inputs passed in to update previously.

update(dist, target, padding_mask=None)

Update state with the predicted distributions and the targets.

Parameters:

• dist (torch.distributions.Distribution) – Predicted distributions.

• target (Tensor) – Ground truth labels.

• padding_mask (Tensor, optional) – The padding mask. Defaults to None. Sets the loss to 0 for padded values.