yukara-ikemiya/minimal-sqvae

A minimal Pytorch Implementation of Stochastically Quantized Variational AutoEncoder (SQ-VAE) by Sony

34
/ 100
Emerging

This project offers a straightforward way to compress images or other data into a smaller, discrete representation while preserving key features, and then reconstruct them. It takes raw image data as input and produces a compressed representation that can be used to generate reconstructed images. Machine learning researchers and practitioners working on efficient data representation or generative models would use this.

No commits in the last 6 months.

Use this if you need a flexible and minimal implementation of a Stochastically Quantized Variational AutoEncoder (SQ-VAE) for research or experimentation with discrete data representations.

Not ideal if you are looking for a pre-trained model for immediate real-world deployment or a user-friendly application without any coding.

deep-learning generative-models image-compression representation-learning machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

34

Forks

4

Language

Python

License

MIT

Last pushed

Oct 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yukara-ikemiya/minimal-sqvae"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.