nicola-decao/s-vae-pytorch
Pytorch implementation of Hyperspherical Variational Auto-Encoders
This library helps machine learning researchers and practitioners implement and experiment with a specific type of variational auto-encoder called Hyperspherical VAEs (S-VAEs) within their PyTorch projects. It takes input data and processes it using specialized distributions (like von Mises-Fisher) to produce more robust and meaningful latent representations. Data scientists, AI researchers, and deep learning engineers working on generative models or complex data embeddings would find this useful.
386 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner working with PyTorch and need to implement or experiment with Hyperspherical Variational Auto-Encoders for your generative models or dimensionality reduction tasks.
Not ideal if you are not working with PyTorch or are looking for a complete, out-of-the-box solution rather than a library to integrate into your own machine learning models.
Stars
386
Forks
61
Language
Python
License
MIT
Last pushed
Mar 21, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nicola-decao/s-vae-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)