https://github.com/jppgks/shenanigan

Toy notebooks as research preparation into generative adversarial networks
https://github.com/jppgks/shenanigan

density-estimation gan generative-adversarial-network

Last synced: 30 days ago
JSON representation

Toy notebooks as research preparation into generative adversarial networks

• Host: GitHub
• URL: https://github.com/jppgks/shenanigan
• Owner: jppgks
• License: other
• Created: 2017-10-18T13:12:03.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-01-07T11:01:21.000Z (about 7 years ago)
• Last Synced: 2024-11-10T04:38:08.759Z (3 months ago)
• Topics: density-estimation, gan, generative-adversarial-network
• Language: Jupyter Notebook
• Homepage:
• Size: 340 KB
• Stars: 0
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# shenanigan

Toy notebooks as research preparation into generative adversarial networks.

## 1. Generating samples from a 1-D Gaussian

![](https://image.ibb.co/dS7OXG/Unknown_3.png)

The [first notebook](/1-generating-samples-from-1D-gaussian.ipynb) in this series tackles a very simple problem: generating samples from a normal distribution.

It serves as a tool to understand GAN basics. The notebook exposes the reader to a well-documented GAN implementation in TensorFlow's eager mode.