Metadata-Version: 2.1
Name: keras-unsupervised
Version: 1.1.1.dev1
Summary: Keras based unsupervised learning framework.
Home-page: https://github.com/tonandr/keras_unsupervised
Author: Inwoo Chung
Author-email: gutomitai@gmail.com
License: UNKNOWN
Project-URL: Bug Reports, https://github.com/tonandr/keras_unsupervised/issues
Project-URL: Source, https://github.com/tonandr/keras_unsupervised/
Keywords: keras deepleaning unsupervised semisupervised restricted-botlzmann-machine deep-belief-network autoencoder generative-adversarial-networks
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python :: 3.6
Requires-Python: ==3.6
Description-Content-Type: text/markdown
License-File: LICENSE

# 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
- [X] Plain RBM, DBN.
- [X] GAN, Style-based GAN.
- [ ] AutoEncoder.
- [ ] First release, documentation.
- [ ] BM, DBM.
- [ ] Convolutional RBM, DBN.
- [ ] Second release, documentation.

## Tasks status

[GAN and Autoencoder are being tested.](https://github.com/tonandr/keras_unsupervised/tree/master/examples/style_based_gan)


