Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Deep Learning with Keras

You're reading from  Deep Learning with Keras

Product type Book
Published in Apr 2017
Publisher Packt
ISBN-13 9781787128422
Pages 318 pages
Edition 1st Edition
Languages
Authors (2):
Antonio Gulli Antonio Gulli
Profile icon Antonio Gulli
Sujit Pal Sujit Pal
Profile icon Sujit Pal
View More author details

Table of Contents (16) Chapters

Title Page
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface
Neural Networks Foundations Keras Installation and API Deep Learning with ConvNets Generative Adversarial Networks and WaveNet Word Embeddings Recurrent Neural Network — RNN Additional Deep Learning Models AI Game Playing Conclusion

Keras adversarial GANs for forging MNIST


Keras adversarial (https://github.com/bstriner/keras-adversarial) is an open source Python package for building GANs developed by Ben Striner (https://github.com/bstriner and https://github.com/bstriner/keras-adversarial/blob/master/LICENSE.txt). Since Keras just recently moved to 2.0, I suggest downloading latest Keras adversarial package:

git clone --depth=50 --branch=master https://github.com/bstriner/keras-adversarial.git

And install setup.py:

python setup.py install

Note that compatibility with Keras 2.0 is tracked in this issue https://github.com/bstriner/keras-adversarial/issues/11.

 If the generator G and the discriminator D are based on the same model, M, then they can be combined into an adversarial model; it uses the same input, M, but separates targets and metrics for G and D. The library has the following API call:

adversarial_model = AdversarialModel(base_model=M,
    player_params=[generator.trainable_weights, discriminator.trainable_weights...
lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $15.99/month. Cancel anytime}