├── samples
    ├── manifold.png
    └── digits_latent_space.png
└── README.md


/samples/manifold.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lyeoni/keras-mnist-VAE/HEAD/samples/manifold.png


--------------------------------------------------------------------------------
/samples/digits_latent_space.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lyeoni/keras-mnist-VAE/HEAD/samples/digits_latent_space.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # keras-mnist-VAE
 2 | Variational AutoEncoder on the MNIST data set using the keras API
 3 | 
 4 | 
 5 | ## Dependencies
 6 | - keras
 7 | - tensorflow
 8 | - numpy
 9 | - scipy
10 | - matplotlib
11 | 
12 | ## Results
13 | - Distribution of labeled data
14 | 
15 | ![alt text](https://github.com/lyeoni/keras-mnist-VAE/blob/master/samples/digits_latent_space.png)
16 | 
17 | - Learned MNIST manifold (2-D latent space)
18 | 
19 | ![alt text](https://github.com/lyeoni/keras-mnist-VAE/blob/master/samples/manifold.png)
20 | 
21 | 
22 | ## Reference
23 | 1. Auto-Encoding Variational Bayes (paper): 
24 | https://arxiv.org/abs/1312.6114
25 | 2. Building Autoencoders in Keras (document): 
26 | https://blog.keras.io/building-autoencoders-in-keras.html
27 | 3. hwalsuklee/tensorflow-mnist-VAE (github): 
28 | https://github.com/hwalsuklee/tensorflow-mnist-VAE/
29 | 


--------------------------------------------------------------------------------