Skip to content

Repository to explore Generative Models

License

Notifications You must be signed in to change notification settings

dannyzekunren/generative

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

generative

Repository to explore Generative Models and in particular image completion methods.

Variational Autodencoders

References:

  1. Image Completion with Deep Learning in TensorFlow
  2. Building Autoencoders in Keras
  3. Tutorial On Variational Autoencoders
  4. What is a Variational Autoencoder?
  5. Auto-Encoding Variational Bayes
  6. Learning Structured Output Representation using Deep Conditional Generative Models

Variational Autoencoders (VAE)

Found in ./vae.keras.py. After about 15 epochs the latent encodings looks like this: (apologies for the lack of a legend.)

image

and we can visualize the latent space manifold:

image

Conditional Variational Autoencoders (CVAE)

Found in ./cvae.keras.py. After about two epochs I am able to generate samples:

image

About

Repository to explore Generative Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%