Softmax#

class scio.scores.Softmax(*, act_norm=None, mode='raw')[source]#

Bases: BaseScoreClassif

Softmax for classification.

Conformity is softmax output.

Parameters:

mode – See BaseScoreClassif.
act_norm – See BaseScore.

References

[HG17]

Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and Out-of-Distribution examples in Neural Networks. In International Conference on Learning Representations. 2017. URL: https://openreview.net/forum?id=Hkg4TI9xl.