About prior "z" negative log-likelihood about chainer-glow HOT 1 OPEN

After comparing your codes with OpenAI/glow, I found one possible explanation. Correct me if I am wrong:

Both of you compute negative log-likelihood of "zi in different levels" separately, and then sum them up:

1. OpenAI/glow does this in the "splitting function". They directly add nll of zi in different levels to the "objective".
2. You explicitly compute nll in different levels in the loss function.

But OpenAI/glow does one more step: in the loss function, they calculate the nll of concatenated "zi", which is the prior distribution.

Therefore, this leads to different distributions of "Z" after certain iterations.

from chainer-glow.