MeanAbsoluteErrorInverse¶
- class torch_uncertainty.metrics.regression.MeanAbsoluteErrorInverse(unit='km', **kwargs)[source]¶
Mean Absolute Error of the inverse predictions (iMAE).
\[\text{iMAE} = \frac{1}{N}\sum_i^N | \frac{1}{y_i} - \frac{1}{\hat{y_i}} |\]- Where \(y\) is a tensor of target values, and \(\hat{y}\) is a
tensor of predictions.
- Both are scaled by a factor of
unit_factor
depending on the unit
given.- As input to
forward
andupdate
the metric accepts the following input:
preds
(Tensor
): Predictions from modeltarget
(Tensor
): Ground truth values
- As output of
forward
andcompute
the metric returns the following output:
mean_absolute_inverse_error
(Tensor
): A tensor with themean absolute error over the state
- Parameters:
unit – Unit for the computation of the metric. Must be one of ‘mm’, ‘m’, ‘km’. Defauts to ‘km’.
kwargs – Additional keyword arguments.