MeanGTRelativeSquaredError¶
- class torch_uncertainty.metrics.MeanGTRelativeSquaredError(squared=True, num_outputs=1, **kwargs)[source]¶
Compute mean squared error relative to the Ground Truth (MSErel or SRE).
\[\text{MSErel} = \frac{1}{N}\sum_i^N \frac{(y_i - \hat{y_i})^2}{y_i}\]Where \(y\) is a tensor of target values, and \(\hat{y}\) is a tensor of predictions.
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:rel_mean_squared_error
(Tensor
): A tensor with the relative mean squared error
- Parameters:
squared – If True returns MSErel value, if False returns RMSErel value.
num_outputs – Number of outputs in multioutput setting
kwargs – Additional keyword arguments, see Advanced metric settings.
- Reference:
As in e.g. From big to small: Multi-scale local planar guidance for monocular depth estimation