Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference

While increasingly deep networks are still in general desired for achieving state-of-the-art performance, for many specific inputs a simpler network might already suffice. Existing works exploited this observation by learning to skip convolutional layers in an input-dependent manner. However, we arg...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-01
Hauptverfasser:	Shen, Jianghao, Fu, Yonggan, Wang, Yue, Xu, Pengfei, Wang, Zhangyang, Lin, Yingyan
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational efficiency Computing costs Inference Measurement Model accuracy Source code
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!