Learning Low-Precision Structured Subnetworks Using Joint Layerwise Channel Pruning and Uniform Quantization

Pruning and quantization are core techniques used to reduce the inference costs of deep neural networks. Among the state-of-the-art pruning techniques, magnitude-based pruning algorithms have demonstrated consistent success in the reduction of both weight and feature map complexity. However, we find...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Applied sciences Jg. 12; H. 15; S. 7829
Hauptverfasser:	Zhang, Xinyu, Colbert, Ian, Das, Srinjoy
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.08.2022
Schlagworte:	Algorithms channel pruning Energy consumption joint pruning layerwise pruning Neural networks Performance evaluation quantization Sparsity
ISSN:	2076-3417, 2076-3417
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!