ritheshkumar95/pytorch-vqvae

Vector Quantized VAEs - PyTorch Implementation

41
/ 100
Emerging

This project helps machine learning researchers working with images or video data to explore and reproduce advanced representation learning techniques. It takes image or video datasets and uses Vector Quantized Variational Autoencoders (VQ-VAEs) to learn compressed, discrete representations. The output is a model capable of reconstructing inputs and generating new, similar data, which is useful for tasks like data compression or creating new samples.

949 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student experimenting with VQ-VAEs for image or video data and need a reproducible PyTorch implementation.

Not ideal if you are looking for a plug-and-play solution for production-ready image generation or a tool for general data analysis outside of representation learning research.

representation-learning generative-models image-synthesis video-analysis machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 23 / 25

How are scores calculated?

Stars

949

Forks

143

Language

Python

License

Last pushed

Jul 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ritheshkumar95/pytorch-vqvae"

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