I guess the NeuralNetBinaryClassifier expects the output to have one logit, since it’s used for a binary use case.
If you want to use two output units for a binary classification (which would be a multi-class classification with 2 classes), you would have to use another wrapper I guess.
I’m not deeply familiar with skorch, but think that NeuralNetClassifier might work.
CC @ottonemo in case I’m wrong.