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.
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?
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