Investigating the Not-So-Obvious Effects of Structured Pruning - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Investigating the Not-So-Obvious Effects of Structured Pruning

Abstract

Structured pruning is a popular method to reduce the cost of convolutional neural networks. However, depending on the architecture, pruning introduces dimensional discrepancies which prevent the actual reduction of pruned networks and mask their true complexity. Most papers in the literature overlook these issues. We propose a method that systematically solves them and generate an operational network. We show through experiments the gap between the theoretical pruning ratio and the actual complexity revealed by our method.
Fichier principal
Vignette du fichier
ICML_2022.pdf (262.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03706472 , version 1 (27-06-2022)

Identifiers

  • HAL Id : hal-03706472 , version 1

Cite

Hugo Tessier, Vincent Gripon, Mathieu Léonardon, Matthieu Arzel, David Bertrand, et al.. Investigating the Not-So-Obvious Effects of Structured Pruning. ICML 2022 - Hardware-aware efficient training (HAET), Jul 2022, Baltimore, United States. ⟨hal-03706472⟩
55 View
95 Download

Share

Gmail Facebook X LinkedIn More