Eric-mingjie/rethinking-network-pruning

Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

51
/ 100
Established

This project helps machine learning researchers and practitioners develop more efficient deep learning models. It takes various network pruning methods and trained ImageNet models as input, and provides insights and code to show that training a pruned model from scratch can often achieve better accuracy than traditional fine-tuning. The primary users are deep learning researchers focused on model compression and efficiency.

1,516 stars. No commits in the last 6 months.

Use this if you are exploring methods to make your deep neural networks smaller and faster without sacrificing accuracy, specifically in the context of network pruning.

Not ideal if you are looking for a plug-and-play solution for model compression without engaging in research or understanding the underlying implications of pruning strategies.

deep-learning-research model-compression neural-network-efficiency computer-vision machine-learning-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,516

Forks

291

Language

Python

License

MIT

Last pushed

Jun 07, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Eric-mingjie/rethinking-network-pruning"

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