Bit-Weight Adjustment for Bridging Uniform and Non-Uniform Quantization to Build Efficient Image Classifiers

Network quantization, which strives to reduce the precision of model parameters and/or features, is one of the most efficient ways to accelerate model inference and reduce memory consumption, particularly for deep models when performing a variety of real-time vision tasks on edge platforms with cons...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Electronics (Basel) 2023-12, Vol.12 (24), p.5043
Hauptverfasser:	Zhou, Xichuan, Duan, Yunmo, Ding, Rui, Wang, Qianchuan, Wang, Qi, Qin, Jian, Liu, Haijun
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Deep learning Energy consumption Modules Neural networks Performance degradation Scaling factors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!