blgpb comments

Repositories
Issues
Comments

Results 2 comments of


                                            blgpb

The losses rec, kl both becomes NAN

Thank you for your reply! I have sent you a detailed email. I look forward to your reply! Thank you very much!

The losses rec, kl both becomes NAN

Thank you very much. I have used the soft clipping to prevent the variance from going to 0 (https://github.com/orybkin/sigma-vae-pytorch/blob/master/model.py#L125C10-L125C10). Unfortunately, the problem still exists.