Closed dawood95 closed 4 years ago
I'm trying to train a similar model. My prior loss doesn't decrease and stays around 60k (for a vector of dimension 256).
Are you referring to the batch norm in point CNF or latent CNF?
Both. If you could share loss curves, that would be very helpful.
The loss doesn't decrease without the batch norm from my end.
I'm trying to train a similar model. My prior loss doesn't decrease and stays around 60k (for a vector of dimension 256).