1Konny/VQ-VAE

Pytorch Implementation of "Neural Discrete Representation Learning"

32
/ 100
Emerging

This project helps machine learning researchers and practitioners explore discrete latent representations for image data. It takes raw image datasets like MNIST or CIFAR10 as input and outputs reconstructed images, demonstrating how well the model learns to compress and represent visual information. It is designed for those experimenting with advanced generative models.

No commits in the last 6 months.

Use this if you are a machine learning researcher or student interested in understanding and applying Vector Quantized Variational Autoencoders (VQ-VAE) for image generation and representation learning.

Not ideal if you need a pre-trained, production-ready model for immediate use in an application or if you are not comfortable working with Python and PyTorch code.

deep-learning-research generative-models image-synthesis representation-learning computer-vision-experiments
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

92

Forks

12

Language

Jupyter Notebook

License

Last pushed

Mar 23, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/1Konny/VQ-VAE"

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