Variational Auto-encoder implementation with self-attention
-
Notifications
You must be signed in to change notification settings - Fork 0
A Variational Autoencoder (VAE) implementation that maps probabilistic latent space using reparameterization trick and variational inference. Uses an encoder-decoder architecture with self-attention layers, an ELBO-based loss function and KL divergence regularization.
winstontsui/VAE
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A Variational Autoencoder (VAE) implementation that maps probabilistic latent space using reparameterization trick and variational inference. Uses an encoder-decoder architecture with self-attention layers, an ELBO-based loss function and KL divergence regularization.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published