kundan2510/pixelCNN

Theano reimplementation of pixelCNN architecture

47
/ 100
Emerging

This project offers a deep learning tool for developers to train models that generate new images, pixel by pixel. It takes a dataset of existing images and learns to produce novel images that resemble the training data. This is useful for machine learning engineers or researchers working on generative models and image synthesis.

166 stars. No commits in the last 6 months.

Use this if you are a deep learning practitioner interested in exploring or implementing the PixelCNN architecture for image generation tasks.

Not ideal if you are looking for a high-level, production-ready image generation tool that doesn't require direct interaction with deep learning frameworks like Theano.

deep-learning image-generation generative-models theano computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

166

Forks

34

Language

Python

License

MIT

Last pushed

Jul 23, 2016

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kundan2510/pixelCNN"

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