https://github.com/ikostrikov/tensorflow-vae-gan-draw

A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Image Generation).
https://github.com/ikostrikov/tensorflow-vae-gan-draw

draw gan recurrent-neural-networks tensorflow vae

Last synced: 2 days ago
JSON representation

A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Image Generation).

• Host: GitHub
• URL: https://github.com/ikostrikov/tensorflow-vae-gan-draw
• Owner: ikostrikov
• License: apache-2.0
• Created: 2015-12-25T03:58:50.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2017-04-18T20:49:55.000Z (over 7 years ago)
• Last Synced: 2023-10-20T20:19:45.992Z (about 1 year ago)
• Topics: draw, gan, recurrent-neural-networks, tensorflow, vae
• Language: Python
• Homepage:
• Size: 32.2 KB
• Stars: 597
• Watchers: 32
• Forks: 172
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# TF-VAE-GAN-DRAW

TensorFlow implementation of [Deep Convolutional Generative Adversarial Networks](http://arxiv.org/pdf/1511.06434.pdf), [Variational Autoencoder (also Deep and Convolutional)](http://arxiv.org/pdf/1312.6114v10.pdf) and [DRAW: A Recurrent Neural Network For Image Generation](http://arxiv.org/pdf/1502.04623v2.pdf).

## Run

VAE/GAN:

```bash

python main.py --working_directory /tmp/gan --model vae

```

DRAW:

```bash

python main-draw.py --working_directory /tmp/gan

```

Deep Convolutional Generative Adversarial Networks produce decent results after 10 epochs using default parameters.

###TODO:

- [ ] More complex data.

- [ ] Add [Adversarial Autoencoder](http://arxiv.org/pdf/1511.05644.pdf)

- [ ] Replace current attention mechanism with Spatial Transformer Layer