Skip to main content

Keras based unsupervised learning framework.

Project description

Keras Unsupervised

Keras framework based unsupervised learning framework

On Keras, to develop semi-supervised learning and unsupervised learning via backpropagation, Keras framework based unsupervised learning libraries are necessary. For this reason, we focus on developing EBM (Energy based model) unsupervised learning modules, and autoencoder and GAN (Generative Adversarial Networks) modules which are based on unsupervised learning via backpropagation, and Keras layers and Tensorflow and Tensorflow-probability backend interfaces for unsupervied learning, and relevant utils. As a symbolic computation backend, Tensorflow is only applied.

Tasks

  • Plain RBM, DBN.
  • GAN, Style-based GAN.
  • AutoEncoder.
  • First release, documentation.
  • BM, DBM.
  • Convolutional RBM, DBN.
  • Second release, documentation.

Tasks status

GAN and Style-based GAN are being developed.

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

keras-unsupervised-0.1.0.dev1.tar.gz (40.9 kB view hashes)

Uploaded Source

Built Distribution

keras_unsupervised-0.1.0.dev1-py3-none-any.whl (57.7 kB view hashes)

Uploaded Python 3

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