[Question]Can I not use the 5 cross-validation?

[LWHYC]

:question: Question

Hi! Since my training set is very small, can I not use cross-validation?

[mibaumgartner]

Dear @LWHYC ,

yes, it is possible to skip the cross-validation by defining a manual data split (nndet_consolidate is only needed if more than one fold is trained). In general, I would stick to the cross-validation scheme since the ensembling of a diverse set of models is usually quite strong during test time.

Best, Michael

[mibaumgartner]

Since there was no update for some time I’ll close this Issue for now. Please feel free to reopen this Issue if the problem persists or open a new one.