adobe-research/beacon-aug

Cross-library augmentation toolbox supporting 300 operators over 8 libraries + AI transforms

21
/ 100
Experimental

This tool helps machine learning engineers and researchers prepare image datasets for training deep learning models. It takes raw images and applies a wide variety of transformations—like flips, rotations, color adjustments, or even AI-generated changes—to create diverse augmented images. This process helps make models more robust and accurate, especially when working with limited original data.

No commits in the last 6 months.

Use this if you are a machine learning practitioner looking to easily access and combine over 300 different image augmentation techniques from various libraries, including specialized Adobe Research transformations, to enhance your deep learning model training.

Not ideal if you are an artist or designer looking for photo editing software, as this tool is specifically for preparing images for machine learning model training, not for general image manipulation.

deep-learning-training computer-vision data-augmentation image-processing model-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

12

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adobe-research/beacon-aug"

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