affjljoo3581/Differentiable-RandAugment

Optimize RandAugment with differentiable operations

32
/ 100
Emerging

This tool helps machine learning engineers and researchers automatically find the best way to apply image augmentations for their models. Instead of manually testing different augmentation settings (like rotation angles or color shifts), you feed in your image dataset and it automatically learns the optimal image transformation parameters. This results in more robust and accurate image classification or object detection models.

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

Use this if you are training deep learning models on image data and want to automatically optimize the image augmentation strategy without tedious manual hyperparameter tuning.

Not ideal if you are working with non-image data or if you need a simple, fixed set of image augmentations without any optimization.

deep-learning computer-vision image-augmentation model-training hyperparameter-optimization
Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

Language

Python

License

Apache-2.0

Last pushed

Jan 25, 2021

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/affjljoo3581/Differentiable-RandAugment"

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