Simplify: A Python library for optimizing pruned neural networks

Neural network pruning allows for impressive theoretical reduction of models sizes and complexity. However it usually offers little practical benefits as it is most often limited to just zeroing out weights, without actually removing the pruned parameters. This precludes from the actual advantages p...

Full description

Saved in:
Bibliographic Details
Published in:SoftwareX 2022-01, Vol.17 (18), p.100907, Article 100907
Main Authors: Bragagnolo, Andrea, Barbano, Carlo Alberto
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Science
Deep learning
Optimization
Pruning
PyTorch
Simplification
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural network pruning allows for impressive theoretical reduction of models sizes and complexity. However it usually offers little practical benefits as it is most often limited to just zeroing out weights, without actually removing the pruned parameters. This precludes from the actual advantages provided by sparsification methods. We propose Simplify, a PyTorch compatible library for achieving effective model simplification. Simplified models benefit of both a smaller memory footprint and a lower inference time, making their deployment to embedded or mobile devices much more efficient.
ISSN:2352-7110
2352-7110
DOI:10.1016/j.softx.2021.100907