Autoencoder + Weights

jh_hs

Hi, I'm training a deep learning model for a classification task with a weights column. I also want to use a pretrained autoencoder to initialize the model. I don't really care about the weights for the autoencoder, but it seems if I don't use a weights column in the autoencoder, I cannot do so later in the classifier. But if I do add a weights colum for the autoencoder, I always get a nullpointer exception. So does the combination just not work? I found no notice of that in the manual.