tmabraham/UPIT

A fastai/PyTorch package for unpaired image-to-image translation.

52
/ 100
Established

This package helps deep learning researchers and practitioners train models for unpaired image-to-image translation. It takes two collections of images (e.g., photos of summer landscapes and photos of winter landscapes) and generates new images that translate the style of one collection to the content of the other. The output is a trained model capable of performing these translations.

137 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are a deep learning researcher or practitioner needing to train CycleGAN, DualGAN, or GANILLA models for image translation without paired examples.

Not ideal if you are looking for a pre-trained model or a user-friendly application for image translation without needing to write code.

deep-learning computer-vision generative-models image-synthesis image-transformation
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

137

Forks

21

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

May 03, 2023

Commits (30d)

0

Dependencies

14

Get this data via API

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

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