Skip to content

Navigation Menu

Sign in
Sign up
This repository was archived by the owner on Feb 7, 2025. It is now read-only.

question about conv for mu and sigma in autoencoderkl #400

Unanswered
Can-Zhao asked this question in Q&A
Discussion options

Hi,

In AutoencoderKL, the mu and sigma are results of convolution from h,

z_mu = self.quant_conv_mu(h)
z_log_var = self.quant_conv_log_sigma(h)
.

If h has only one latent channel, then this single channel value needs to have the ability to generate both mu and sigma. It seems difficult intuitively?
I was wondering if you could help me with it. @ericspod Or should I set latent channel to be >1 ?

Thank you!

Best,
Can

You must be logged in to vote

Replies: 1 comment 1 reply

Comment options

I would guess all that matters is how large h is in total, even with 1 channel it's spatial dimensions might be large enough that it has sufficient capacity to represent a compressed form of the input. I would assume this would be like any other VAE in that if your results after encoding/decoding are poor then your capacity is too small and so adding channels could help with that. @Warvito might have more insight on this.

You must be logged in to vote
1 reply
Comment options

Can-Zhao Jun 1, 2023
Collaborator Author

Thank you so much Eric! Yes, if h is large enough, then channel=1 is also fine

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /