Open univanxx opened 1 year ago
Hello! Can anyone explain me one thing: when counting mean3 for 3-rd channel (blue, I suppose), why don't we use samples[:, 2, :, :, :]: https://github.com/NVlabs/NVAE/blob/9fc1a288fb831c87d93a4e2663bc30ccf9225b29/distributions.py#L139-L152
mean3
samples[:, 2, :, :, :]
Also, why do we need to update means with samples when counting log prob? For example, in Tacotron-2 code the are no updates of means.
Hi, did you find an answer to that? I have the same doubt
Hello! Can anyone explain me one thing: when counting
mean3
for 3-rd channel (blue, I suppose), why don't we usesamples[:, 2, :, :, :]
: https://github.com/NVlabs/NVAE/blob/9fc1a288fb831c87d93a4e2663bc30ccf9225b29/distributions.py#L139-L152Also, why do we need to update means with samples when counting log prob? For example, in Tacotron-2 code the are no updates of means.