Skip to main content

Framework to ease training of generative models based on TensorFlow

Project description

SimpleGAN

License Documentation Status

Framework to ease training of generative models

SimpleGAN is a framework based on TensorFlow to make training of generative models easier. SimpleGAN provides high level APIs with customizability options to user which allows them to train a generative model with few lines of code.

Requirements

Make sure you have the following packages installed

Installation

Latest stable release:

  $ pip install simplegan

Latest Development release:

  $ pip install git+https://github.com/grohith327/EasyGAN.git

Getting Started

DCGAN
>>> from simplegan.gan import DCGAN
>>> gan = DCGAN()
>>> train_ds = gan.load_data(use_mnist = True)
>>> samples = gan.get_sample(train_ds, n_samples = 5)
>>> gan.fit(train_ds = train_ds)
>>> generated_samples = gan.generate_samples(n_samples = 5)
Convolutional Autoencoder
>>> from simplegan.autoencoder import ConvolutionalAutoencoder
>>> autoenc = ConvolutionalAutoencoder()
>>> train_ds, test_ds = autoenc.load_data(use_cifar10 = True)
>>> train_sample = autoenc.get_sample(data = train_ds, n_samples = 5)
>>> test_sample = autoenc.get_sample(data = test_ds, n_samples = 1)
>>> autoenc.fit(train_ds = train_ds, epochs = 5, optimizer = 'RMSprop', learning_rate = 0.002)
>>> generated_samples = autoenc.generate_samples(test_ds = test_ds.take(1))

To have a look at more examples in detail, check here

Documentation

Check out the docs page

Provided models

  • Autoencoders
    • Vanilla Autoencoder
    • Convolutional Autoencoder
    • Variational Autoencoder [Paper]
    • Vector Quantized - Variational Autoencoder [Paper]
  • Generative Adversarial Networks(GANs)

Contributing

We appreciate all contributions. If you are planning to perform bug-fixes, add new features or models, please file an issue and discuss before making a pull request.

Contributors

Project details


Download files

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

Source Distribution

simplegan-0.2.7.tar.gz (27.1 kB view hashes)

Uploaded source

Built Distribution

simplegan-0.2.7-py3-none-any.whl (57.2 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page