VAE with variational nested dropout #60
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi, the input image is normalized between 0-1, did you consider using a nn.Sigmoid() activation layer instead of nn.Tanh() as the output activation of your decoder? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi Authors,
We ask to contribute our new VAE with variational nested dropout (VNDAE) presented in our recent preprint https://arxiv.org/pdf/2101.11353.pdf. It was shown to outperform VAE, BetaVAE, JointVAE and SWAE evaluated under FID and IS, on CelebA, Cifar10, Cifar100, 3D Chairs and Chest X-ray.
Please check our pull request. Thanks.
Best,
Ralph CUI