arcelien/pba
Efficient Learning of Augmentation Policy Schedules
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.
Stars
508
Forks
84
Language
Jupyter Notebook
License
Apache-2.0
Category
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.
Higher-rated alternatives
TorchIO-project/torchio
Medical imaging processing for AI applications.
aleju/imgaug
Image augmentation for machine learning experiments.
makcedward/nlpaug
Data augmentation for NLP
mdbloice/Augmentor
Image augmentation library in Python for machine learning.
BloodAxe/pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming