22993f853f
When doing classification we need to know the `numPossibleLabels`. If it's set to -1, then we get obscure and confusing null-pointers when accessing labels when calling `ComputationGraph.fit` on the iterator. This PR blocks the user from shooting themselves in the foot. |
||
|---|---|---|
| .. | ||
| deeplearning4j-datasets | ||
| deeplearning4j-datavec-iterators | ||
| deeplearning4j-utility-iterators | ||
| pom.xml | ||