kakaobrain/fast-autoaugment
Official Implementation of 'Fast AutoAugment' in PyTorch.
When training image classification models, data augmentation helps improve accuracy. This project provides a lightning-fast way to find optimal data augmentation policies for your image datasets. You input your image classification model and dataset, and it outputs a highly effective augmentation policy that leads to better model performance. This is for machine learning engineers and researchers focused on computer vision tasks.
1,611 stars. No commits in the last 6 months.
Use this if you need to dramatically reduce the time it takes to find the best image augmentation strategies for your deep learning models without sacrificing accuracy.
Not ideal if you are not working with image data or already have a fixed, highly effective data augmentation pipeline.
Stars
1,611
Forks
197
Language
Python
License
MIT
Category
Last pushed
Jun 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kakaobrain/fast-autoaugment"
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