Hello, your Overview section clearly stated:
"If you wish to change the amount and type of layers, you can edit the “src/CVAE_architecture.py” module. "
There are many ways to implement an encoder and decoder. It is also possible to generate smooth X1, X2 using a decoder (conditioned on Y and latent variables). I experimented with that and submitted but you removed my entry accusing me of not using CVAE. I replied to your email I sent you my code so you could verify that I used CVAE architecture.
Please confirm that we are indeed allowed to modify the baseline CVAE. Or you are insisting on the baseline CVAE to be used?
Best regards,
Dmitry Konovalov