pi-tau/vae

Pytorch implementation of a Variational Autoencoder trained on CIFAR-10. The encoder and decoder modules are modelled using a resnet-style U-Net architecture with residual blocks.

23
/ 100
Experimental

This project helps machine learning practitioners and researchers explore the capabilities of Variational Autoencoders (VAEs) for generating new images. It takes a dataset of images, learns their underlying patterns, and then outputs novel, synthetic images that resemble the originals but are entirely new. It's designed for those who work with image data and need to create variations or augment datasets.

No commits in the last 6 months.

Use this if you need to generate new, realistic images from an existing dataset for tasks like data augmentation, style transfer, or creative content generation.

Not ideal if your primary goal is simple data compression or dimensionality reduction without the need to generate new data points.

image-generation deep-learning synthetic-data computer-vision generative-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Python

License

Last pushed

Jan 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pi-tau/vae"

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