A composable GAN built for developers, researchers, and artists. HyperGAN builds generative adversarial networks in PyTorch and makes them easy to train and share. HyperGAN is currently in pre-release and open beta. Everyone will have different goals when using hypergan. HyperGAN is currently beta. We are still searching for a default cross-data-set configuration. Each of the examples supports search. Automated search can help find good configurations. If you are unsure, you can start with the 2d-distribution.py. Check out random_search.py for possibilities, you'll likely want to modify it. The examples are capable of (sometimes) finding a good trainer, like 2d-distribution. Mixing and matching components seems to work.

Features

  • Hyperparameter tuning, or doing something like trying softmax loss with gradient penalty, can all be done in the JSON configuration file
  • Custom research
  • Use hyperGAN in an app
  • Quantize and/or deploy the model
  • Build image datasets
  • HyperGAN is currently beta

Project Samples

HyperGAN Screenshot 1

Project Activity

See All Activity >

Categories

Frameworks, Generative Adversarial Networks (GAN), Generative AI

License

MIT License

Follow HyperGAN

HyperGAN Web Site

Other Useful Business Software
Streamline Azure Security with Palo Alto Networks VM-Series Icon
Streamline Azure Security with Palo Alto Networks VM-Series

Centrally manage physical and virtualized firewalls with Panorama

Improve your security posture and reduce incident response time. Use the VM-Series to natively analyze Azure traffic and dynamically drive policy updates based on workload changes.
Learn more
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of HyperGAN!

Additional Project Details

Programming Language

Python

Related Categories

Python Frameworks, Python Generative Adversarial Networks (GAN), Python Generative AI

Registered

2023-03-21
Report inappropriate content