https://github.com/tonandr/keras_unsupervised

Keras framework for unsupervised learning
https://github.com/tonandr/keras_unsupervised

autoencoder deep-belief-network generative-adversarial-networks keras restricted-boltzmann-machine semi-supervised-learning styled-based-gan unsupervised-learning

Last synced: 23 days ago
JSON representation

Keras framework for unsupervised learning

• Host: GitHub
• URL: https://github.com/tonandr/keras_unsupervised
• Owner: tonandr
• License: bsd-3-clause
• Created: 2019-05-24T12:30:47.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-10-22T12:47:35.000Z (about 1 year ago)
• Last Synced: 2024-10-01T16:08:18.033Z (about 1 month ago)
• Topics: autoencoder, deep-belief-network, generative-adversarial-networks, keras, restricted-boltzmann-machine, semi-supervised-learning, styled-based-gan, unsupervised-learning
• Language: Python
• Size: 8.51 MB
• Stars: 3
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Security: SECURITY.md

Awesome Lists containing this project

README

        
# 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, I 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 unsupervised learning, and relevant utils. As a symbolic computation backend, Tensorflow is only applied.

# Tasks

- [X] Plain RBM, DBN.

- [X] GAN, Style-based GAN.

## Tasks status

This project is closed with the final 1.1.3.dev1 version.