parameters of train_gpvvae.py

[ivanov-v-v]

Hello,

I am trying to reproduce your results. I trained VAE for 10000 iterations (using train_vae.py with default parameters). Then, I tried passing VAE weights from 1000, 5000 and 9000 iteration checkpoints as an input for the train_gppvae.py script.

Am I correct in saying that callback.py does the following: it prints a grid of three rows of images, where the first row is ground truth, the second row is VAE reconstruction and the third row is GPPVAE reconstruction?

If my interpretation is correct, then each time GPPVAE yields worse results than VAE and I don't understand why. Could you, please, mention in the readme the exact number of iterations you used for training the VAE? And the exact parameters you were passing to both scripts (train_vae.py and train_gppvae.py) if those differ from the defaults. Also, the kernel heatmaps look different from those presented in your paper, that's what also concerns me.

Thank you in advance!

[MineOgre]

I have the same issue with the experiments, looking forward for any comments on this.

I obtained the following plots after training GPPVAE for 10000 epochs starting with the VAE weights after 2000 epochs of training.