https://github.com/saran-nns/jaxifier

Generative models using JAX. Currently intended for "Learning" and not for "Production"
https://github.com/saran-nns/jaxifier

Last synced: about 2 months ago
JSON representation

Generative models using JAX. Currently intended for "Learning" and not for "Production"

• Host: GitHub
• URL: https://github.com/saran-nns/jaxifier
• Owner: Saran-nns
• License: mit
• Created: 2021-02-21T17:53:07.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2021-11-16T10:27:56.000Z (over 3 years ago)
• Last Synced: 2025-02-09T15:38:50.273Z (4 months ago)
• Language: Python
• Homepage:
• Size: 8.27 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Jaxifier

Normalizing Flow models using Pytorch, Tensorflow and XLA accellarated JAX which allows for automatically parallelising code across multiple accelerators such as GPUs and TPUs.

The repository is under active developement.

- [x] Linear Flow : [x] PyTorch [x] TensorFlow [x] Jax

- [x] Non-Linear Flow: [x] PyTorch [x] TensorFlow [x] Jax

- [x] Affine Flow: [x] PyTorch [x] TensorFlow [x] Jax

- [ ] Planar Flow: [ ] PyTorch [ ] TensorFlow [ ] Jax

- [ ] Radial Flow

- [ ] Coupling and Autoregressive Flows

- [ ] RealNVPs

- [ ] GLOW