Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/lyeoni/keras-mnist-vae

autoencoder deep-learning generative-model keras mnist vae

Last synced: 2 months ago
JSON representation

Host: GitHub
URL: https://github.com/lyeoni/keras-mnist-vae
Owner: lyeoni
Created: 2018-10-19T06:22:07.000Z (about 6 years ago)
Default Branch: master
Last Pushed: 2018-10-24T07:40:01.000Z (about 6 years ago)
Last Synced: 2023-09-28T11:29:15.328Z (over 1 year ago)
Topics: autoencoder, deep-learning, generative-model, keras, mnist, vae
Language: Jupyter Notebook
Homepage:
Size: 701 KB
Stars: 15
Watchers: 2
Forks: 7
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

README

# keras-mnist-VAE
Variational AutoEncoder on the MNIST data set using the keras API

## Dependencies
- keras
- tensorflow
- numpy
- scipy
- matplotlib

## Results
- Distribution of labeled data

![alt text](https://github.com/lyeoni/keras-mnist-VAE/blob/master/samples/digits_latent_space.png)

- Learned MNIST manifold (2-D latent space)

![alt text](https://github.com/lyeoni/keras-mnist-VAE/blob/master/samples/manifold.png)

## Reference
1. Auto-Encoding Variational Bayes (paper):
https://arxiv.org/abs/1312.6114
2. Building Autoencoders in Keras (document):
https://blog.keras.io/building-autoencoders-in-keras.html
3. hwalsuklee/tensorflow-mnist-VAE (github):
https://github.com/hwalsuklee/tensorflow-mnist-VAE/