VAE EBM
Two sepratae VAEs for images and text data are trained using standard ELBO objective. I then utilize the latent space embeddings of such multi-modalities to jointly train EBMs in an unsupervised manner.
-
Notifications
You must be signed in to change notification settings - Fork 0
akarshp28/multi_modal_ebm
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
VAE EBM
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published