[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders"
Apache License 2.0
193
stars
26
forks
source link
Inconsistency between an equation and implementation in expELBO? #7
(Thank you for making whole codes publicly available, especially I really like easy-to-run colab demo!)
In implementation, exp ELBO term is computed both for D(E(x)) and D(z). However the term is only computed for D(z) in Algorithm 1 in paper. Could you elaborate a bit more about the difference?
I've just found the difference described above is mentioned in Appendix (Sec 9.1). It is interesting to see the efforts to make theoretical analysis work in practice.
(Thank you for making whole codes publicly available, especially I really like easy-to-run colab demo!)
In implementation, exp ELBO term is computed both for D(E(x)) and D(z). However the term is only computed for D(z) in Algorithm 1 in paper. Could you elaborate a bit more about the difference?