Nikolai10/FSQ
TensorFlow implementation of "Finite Scalar Quantization: VQ-VAE Made Simple" (ICLR 2024)
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.
Stars
21
Forks
1
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
open-mmlab/mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
Xilinx/brevitas
Brevitas: neural network quantization in PyTorch
fastmachinelearning/qonnx
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
google/qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
tensorflow/model-optimization
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization...