candle.uq_keras_utils.mae_contamination_metric

candle.uq_keras_utils.mae_contamination_metric#

candle.uq_keras_utils.mae_contamination_metric(nout)#

This function computes the mean absolute error (mae) for the contamination model. The mae is computed over the prediction. Therefore, the augmentation for the index variable is ignored.

Parameters:

nout (int) – Number of outputs without uq augmentation (in the contamination model the augmentation corresponds to the data index in training).