arcelien/pba

Efficient Learning of Augmentation Policy Schedules

47
/ 100
Emerging

This project helps machine learning researchers and practitioners efficiently train neural networks by automatically generating data augmentation policies. It takes raw image datasets and a specified neural network model as input, and outputs optimized data augmentation schedules that significantly improve model accuracy while dramatically reducing computational time. Anyone working on computer vision tasks with neural networks can use this to get better performance.

508 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner struggling to find effective data augmentation strategies for your neural networks and want to achieve state-of-the-art results with much less computational effort.

Not ideal if you are looking for a general-purpose machine learning library or if your primary task does not involve training neural networks on image data.

deep-learning computer-vision image-classification neural-network-training data-augmentation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

508

Forks

84

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Oct 27, 2019

Commits (30d)

0

Get this data via API

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

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