Nikolai10/FSQ

TensorFlow implementation of "Finite Scalar Quantization: VQ-VAE Made Simple" (ICLR 2024)

26
/ 100
Experimental

This tool helps machine learning engineers and researchers simplify the process of quantizing continuous data into discrete representations. You input raw numerical data, and it outputs a quantized version, along with an index into a codebook representing that discrete value. This is particularly useful for tasks involving data compression or preparing data for generative models.

No commits in the last 6 months.

Use this if you are a machine learning practitioner working with TensorFlow and need a straightforward way to convert continuous numerical data into discrete codes, for instance, when building Variational Autoencoders or other generative models.

Not ideal if you are not a machine learning engineer or do not work with TensorFlow, or if your primary goal is not data quantization or generative modeling.

machine-learning-engineering data-quantization generative-models model-compression deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Dec 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nikolai10/FSQ"

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