adobe/antialiased-cnns

pip install antialiased-cnns to improve stability and accuracy

56
/ 100
Established

This tool helps machine learning engineers and researchers improve the reliability and accuracy of their image classification models. By applying an antialiasing technique during the downsampling stages of convolutional neural networks, it ensures that small shifts in an input image don't drastically change the model's prediction. You provide an existing image classification model, and the tool outputs an enhanced version that performs better and more consistently.

1,681 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are building or working with image classification models and need to improve their accuracy and make them more robust to slight variations or shifts in input images.

Not ideal if your project does not involve image data or if you are not using convolutional neural networks for your computer vision tasks.

image-classification computer-vision machine-learning-engineering model-robustness deep-learning
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

1,681

Forks

201

Language

Python

License

Last pushed

Apr 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/adobe/antialiased-cnns"

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