A Lightweight Transfer Learning Model with Pruned and Distilled YOLOv5s to Identify Arc Magnet Surface Defects

A Lightweight Transfer Learning Model with Pruned and Distilled YOLOv5s to Identify Arc Magnet Surface Defects

Surface defects in arc magnets constitute the main culprit for performance degradation and safety hazards in permanent magnet motors. Machine-vision methods offer the possibility to identify surface defects automatically. However, the current methods still do not adequately solve the problems of low...

Full description

Bibliographic Details
Main Authors: Qinyuan Huang, Ying Zhou, Tian Yang, Kun Yang, Lijia Cao, Yan Xia
Format: Article
Language:English
Published: MDPI AG 2023-02-01
Series:Applied Sciences
Subjects:
transfer learning
network pruning
knowledge distillation
arc magnet
surface defect identification
YOLOv5
Online Access:https://www.mdpi.com/2076-3417/13/4/2078

Internet

https://www.mdpi.com/2076-3417/13/4/2078

Similar Items