Inference results of the overfitted model are noise
Opened this issue · 4 comments
kirilllzaitsev commented
Having an overfitted 'base' part of the Imagen, I try to sample with it for 300 timesteps and get the following:
During training, it predicts the noise well, and MSE goes down steadily. Somewhat similar is the following issue lucidrains/imagen-pytorch#337.
Could you give any advice on the direction to investigate the issue?
chiho-5 commented
For how many epochs did you train. I think I'm encountering the same problem
sadath-12 commented
same problem
swayampragnya-malla commented
same problem
kirilllzaitsev commented
same problem
Try increasing the number of epochs (for instance, 1500 epochs (1 epoch = 1 gradient step) for a single image) and tuning the learning rate (starting with small values <1e-4)