lucaslie/torchprune

A research library for pytorch-based neural network pruning, compression, and more.

43
/ 100
Emerging

This is a research library for PyTorch-based neural network pruning. It helps machine learning researchers and practitioners make their deep learning models smaller and faster. You input your existing PyTorch neural network, and it outputs a compressed version of that network, often with minimal loss in performance. This is for machine learning engineers, AI researchers, and data scientists working with deep learning models.

163 stars. No commits in the last 6 months.

Use this if you need to reduce the computational cost or memory footprint of your PyTorch neural networks for deployment or efficiency, and want to explore various pruning techniques.

Not ideal if you are looking for a high-level, automated pruning solution without needing to understand different algorithms or manage experimental configurations.

deep-learning-optimization model-compression neural-network-pruning ml-research resource-constrained-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

163

Forks

24

Language

Shell

License

MIT

Last pushed

Nov 28, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lucaslie/torchprune"

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