I am trying to implement the PiX2Pix framework following this source: https://www.tensorflow.org/tutorials/generative/pix2pix?hl=ru , with one exception.
I am trying to make the code work for MINST dataset instead for the facades dataset they used. I have noticed that at the end of the preprocessing of the train_images and the conversion of train_images into train_dataset, the data type of facades dataset comes out to be 'DatasetV1Adapter' but for MNIST, it's 'BatchDataset'. Now, my code is not working and I'm getting an error saying 'too many values to unpack' after I run the training, and I think it has something to do with this difference. Is there any way to convert them from one to the other?
I am new to python and tensorflow and completely lost about this problem. Some help would be very much appriciated. Thank you.