基于改进YOLOv5s的印刷电路板缺陷检测算法
周著国,鲁玉军,吕利叶

Improved YOLOv5s-based algorithm for printed circuit board defect detection
Zhuguo ZHOU,Yujun LU,Liye LV
表 2 不同聚类算法植入后的模型检测性能对比
Tab.2 Comparison of model detection performance after implanting different clustering algorithms
聚类算法P/%mAP/%FLOPs/109
K-means96.394.815.8
K-means++96.895.115.8
Binary K-means96.995.415.8
DBSCAN97.195.815.8
Agglomerative Clustering94.791.815.8
Mean Shift94.190.115.8
HDBK-means97.396.415.8