December 27, 2019

227 words 2 mins read



The official code repository for examples in the O’Reilly book ‘Generative Deep Learning’

repo name davidADSP/GDL_code
repo link
language Jupyter Notebook
size (curr.) 22614 kB
stars (curr.) 603
created 2019-02-22
license GNU General Public License v3.0

Generative Deep Learning

Teaching Machines to paint, write, compose and play

The official code repository for examples in the O’Reilly book ‘Generative Deep Learning’


This branch uses standalone Keras with a Tensorflow 1.14 backend. See the tensorflow_2 branch for the Keras within Tensorflow 2.0 version of the codebase.


This repository is structured as follows:

The notebooks for each chapter are in the root of the repository, prefixed with the chapter number.

The data folder is where to download relevant data sources (chapter 3 onwards) The run folder stores output from the generative models (chapter 3 onwards) The utils folder stores useful functions that are sourced by the main notebooks

Book Contents

Part 1: Introduction to Generative Deep Learning

  • Chapter 1: Generative Modeling
  • Chapter 2: Deep Learning
  • Chapter 3: Variational Autoencoders
  • Chapter 4: Generative Adversarial Networks

Part 2: Teaching Machines to Paint, Write, Compose and Play

  • Chapter 5: Paint
  • Chapter 6: Write
  • Chapter 7: Compose
  • Chapter 8: Play
  • Chapter 9: The Future of Generative Modeling
  • Chapter 10: Conclusion

Getting started

To get started, first install the required libraries inside a virtual environment:

pip install -r requirements.txt

comments powered by Disqus