Skip to main content

easy wrapper for initializing several GAN networks in keras

Project description

Simple GAN

This is my attempt to make a wrapper class for a GAN in keras which can be used to abstract the whole architecture process.

Build Status

Overview

alt text

Flow Chart

Setting up a Generative Adversarial Network involves having a discriminator and a generator working in tandem, with the ultimate goal being that the generator can come up with samples that are indistinguishable from valid samples by the discriminator.

alt text

Installation

    pip install adversarials

Example

import numpy as np
from keras.datasets import mnist

from adversarials.core import Log
from adversarials import SimpleGAN

if __name__ == '__main__':
    (X_train, _), (_, _) = mnist.load_data()

    # Rescale -1 to 1
    X_train = (X_train.astype(np.float32) - 127.5) / 127.5
    X_train = np.expand_dims(X_train, axis=3)

    Log.info('X_train.shape = {}'.format(X_train.shape))

    gan = SimpleGAN(save_to_dir="./assets/images",
    save_interval=20)
    gan.train(X_train, epochs=40)

Credits

Contribution

You are very welcome to modify and use them in your own projects.

Please keep a link to the original repository. If you have made a fork with substantial modifications that you feel may be useful, then please open a new issue on GitHub with a link and short description.

License (MIT)

This project is opened under the MIT 2.0 License which allows very broad use for both academic and commercial purposes.

A few of the images used for demonstration purposes may be under copyright. These images are included under the "fair usage" laws.

Project details


Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for Adversarials, version 1.0.1
Filename, size File type Python version Upload date Hashes
Filename, size Adversarials-1.0.1-py3.6.egg (28.4 kB) File type Egg Python version 3.6 Upload date Hashes View hashes
Filename, size Adversarials-1.0.1.tar.gz (10.1 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page