baowenshuwh

Results 4 issues of baowenshuwh

作者,您好!我用YOLOv5训练了AI-TOD,然后将训练结果拿到cocoeval上做评估,在conf_thres=0.25, iou_thres=0.45的情况下,得到的评估性能似乎太好,请问您论文上的实验评估方式是用cocoeval吗?

您好,在Ghostbottleneck中,有用到expansion ratio进行通道扩张,这个最优的expansion ratio是怎么得到的呢?您能指点指点吗

What is the input image size of Querydet? Where do I set it?

Dear author, in order to use redundant feature information, PConv is proposed in this paper. However, Partial convolution is so similar to Ghost convolution. Ghost convolution uses half of the...