Variational auto-encoder trained on celebA . All rights reserved.
Switch branches/tags
Nothing to show
Clone or download
Latest commit 084d524 Dec 14, 2017


Hereby we present plain VAE and modified VAE model, both of which are trained on celebA dataset to synthesize facial images.


plain VAE


input image:

randomly generation:

To run the code, you are required to install Tensorflow and Tensorlayer on your machine. how to install Tensorlayer


This is the code for the paper Deep Feature Consistent Variational Autoencoder
In loss function we used a vgg loss.Check this how to load and use a pretrained VGG-16? if you have trouble reading

How to Run

Firstly, download the celebA dataset and VGG-16 weights. After installing all the third-party packages required, we can train the models by:

python # for plain VAE
python # for DFC-VAE