iurada/px-ntk-pruning

Official repository of our work "Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning" accepted at CVPR 2024

31
/ 100
Emerging

This project helps machine learning engineers and researchers reduce the computational costs and memory demands of deep learning models, especially for computer vision tasks. It takes an existing deep learning model (either untrained or pre-trained) and outputs a much smaller, 'sparse' version that performs almost identically but runs more efficiently. The end-user is typically an ML practitioner focused on deploying efficient vision models.

No commits in the last 6 months.

Use this if you need to significantly reduce the size and computational requirements of deep learning models for computer vision applications without sacrificing performance.

Not ideal if your primary goal is to improve model accuracy or if you are not working with deep neural networks for vision tasks.

model-optimization computer-vision deep-learning-deployment resource-constrained-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

26

Forks

6

Language

Python

License

Last pushed

Feb 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iurada/px-ntk-pruning"

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