Open henrygouk opened 5 years ago
Describe the bug I've noticed that the validation accuracy logged by dl4j is almost an exact inversion of the test set accuray reported by weka for some binary classification datasets I've been using.
To Reproduce Steps to reproduce the behavior:
Note that this does not happen with all binary classification datasets I have used.
Expected behavior Accuracy reported by dl4j should be similar to what is reported by weka.
I've come up with a temporary workaround: swapping the order that the two classes are defined in the ARFF file.
Describe the bug I've noticed that the validation accuracy logged by dl4j is almost an exact inversion of the test set accuray reported by weka for some binary classification datasets I've been using.
To Reproduce Steps to reproduce the behavior:
Note that this does not happen with all binary classification datasets I have used.
Expected behavior Accuracy reported by dl4j should be similar to what is reported by weka.