sony/sqvae

Pytorch implementation of stochastically quantized variational autoencoder (SQ-VAE)

42
/ 100
Emerging

This project offers an improved way to train deep learning models that generate new images or audio. It helps researchers and machine learning engineers create more diverse and higher-quality outputs from their generative models. You provide an existing dataset of images or sounds, and it helps your model learn more effectively from that data to produce new, realistic variations.

193 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or engineer working with generative models for computer vision or speech, and you want to improve the diversity and quality of the generated outputs.

Not ideal if you are not deeply involved in training and researching advanced generative deep learning models.

deep-learning-research generative-AI computer-vision speech-synthesis model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

193

Forks

25

Language

Python

License

Apache-2.0

Last pushed

Jul 20, 2022

Commits (30d)

0

Get this data via API

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

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