I'm training a complex model for motion prediction using a VAE, however the KL divergence has a very strange behaviorenter image description here.

A scheleton of the network is the following:

enter image description here

At the end my network compute the MSE loss of the trajectory and the Kullback Leibler loss (with gaussian prior with mean 0 and std equal to 1) given as:

kld_loss = -0.5*torch.sum(1 + sigma - mu.pow(2) - sigma.exp())

Any idea of the possible causes? Do you need further details?

  • $\begingroup$ Yes, do need further details. $\endgroup$ – Kostya May 31 at 17:47
  • $\begingroup$ Added more details @Kostya $\endgroup$ – FraMan May 31 at 19:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.