Problem about KL loss when training CVAE model.

[dayunyan]

When I trained CVAE on my own dataset, I found that the results were very poor. Upon inspection, I found that the KL loss is too large at training and validation time, reaching around 10^27, and will not decrease. A closer look shows that the encoder output log_var is 50~60. I have been adjusting for a long time without effect. How to solve this situation?

[sunny12345-bit]

Have you solved this problem？

[dayunyan]

Have you solved this problem？

Not yet, cause I have switched to a different technical approach. The original technology might not be suitable for my dataset, and moreover, VAE itself tend to be less stable during training compared to other models.