In this notebook we design and train a classic Auto-Encoder model on MNIST data set and learn its latent space using a conditional-GAN architecture. Then we visualize how the interpolation differs within AE's latent codes vs GAN's latent codes to support the idea of GAN better distribution grouping.
-
Notifications
You must be signed in to change notification settings - Fork 0
tGhattas/DL
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Learning latent space of MNIST trained AE using a conditional-GAN architecture
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published