reconstruction loss in training_obj_disjoint.py

NVlabs / LSGM

The Official PyTorch Implementation of "LSGM: Score-based Generative Modeling in Latent Space" (NeurIPS 2021)

Other

340 stars 49 forks source link

reconstruction loss in training_obj_disjoint.py #1

Closed Xiaohui9607 closed 2 years ago

Xiaohui9607 commented 2 years ago

Hi, I have a question about the reconstruction term in lines 43-45. I didn't see where the parameterization is applied to the encoder distribution to obtain a sample of z_0. Am I missing something? Great work and awesome code btw!

Xiaohui9607 commented 2 years ago

I figure that out, seems that reparameterization is inside nvae. I will close this issue.