MeanSquaredErrorInverse#

class torch_uncertainty.metrics.regression.MeanSquaredErrorInverse(squared=True, num_outputs=1, unit='km', **kwargs)[source]#

Mean Squared Error of the inverse predictions (iMSE).

\[\text{iMSE} = \frac{1}{N}\sum_i^N(\frac{1}{y_i} - \frac{1}{\hat{y_i}})^2\]

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 and update the metric accepts the following input:

  • preds (Tensor): Predictions from model

  • target (Tensor): Ground truth values

As output of forward and compute the metric returns the following output:

  • mean_squared_error (Tensor): A tensor with the mean squared error

Parameters:

  • squared (bool) – If True, returns MSE. If False, returns RMSE.

  • num_outputs (int) – Number of outputs in multioutput setting.

  • unit (Literal['mm', 'm', 'km']) – Unit for the computation of the metric. Must be one of "mm", "m", "km". Defaults to "km".

  • kwargs – Additional keyword arguments.

update(preds, target)[source]#

Update state with predictions and targets.

Return type:

None