You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/configs/train_group.md
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -45,7 +45,7 @@ TRAIN Group存放所有和训练相关的配置
45
45
是否在多卡间同步BN的均值和方差。
46
46
47
47
Synchronized Batch Norm跨GPU批归一化策略最早在[MegDet: A Large Mini-Batch Object Detector](https://arxiv.org/abs/1711.07240)
48
-
论文中提出,在[Bag of Freebies for Training Object Detection Neural Networks](https://arxiv.org/pdf/1902.04103.pdf)论文中以Yolov3验证了这一策略的有效性,[PaddleCV/yolov3](https://github.com/PaddlePaddle/models/tree/develop/PaddleCV/yolov3)实现了这一系列策略并比Darknet框架版本在COCO17数据上mAP高5.9.
48
+
论文中提出,在[Bag of Freebies for Training Object Detection Neural Networks](https://arxiv.org/pdf/1902.04103.pdf)论文中以Yolov3验证了这一策略的有效性。
0 commit comments