Skip to content
No description, website, or topics provided.
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
celebA/data
mnist/data
other/images Included graph images. Mar 20, 2019
utils Moved assert exists PATH_FACEDATA. Apr 22, 2019
.gitignore
README.md
constants.py
vae_celebA.ipynb
vae_celebA_colaboratory.ipynb Added vae_celebA_colaboratory.ipynb. Apr 25, 2019
vae_mnist.ipynb
variational_autoencoder.py First commit of celebA project and notebook. Apr 19, 2019

README.md

Variational-autoencoder

A tensorflow implementation of a variational autoencoder.

Requirements:

  1. tensorflow v1.13.1
  2. PIL
  3. matplotlib
  4. IPython.display (for tensorboard visualization in a jupyter notebook)
  5. OpenCV (for face cropping)

Usage:

Run the enclosed vae_mnist.ipynb notebook in a tensorflow environment.

Tensorflow graph:

From the enclosed vae_mnist.ipynb notebook, you can run tensorboard to see the entire computational graph.

A look at the entire tensorflow graph: 

tensorflow graph

A look at the variational autoencoder graph: 

variational autoencoder graph

A look at the encoder graph (three-layer fully-connected): 

encoder graph

A look at the decoder graph (three-layer fully-connected): 

decoder graph

You can’t perform that action at this time.