CVPR2016: You Only Look Once:Unified, Real-Time Object Detection
于是输出可以表示为一个S∗S∗(B∗(4+1)+C)S*S*(B*(4+1)+C)S∗S∗(B∗(4+1)+C)的tensor,训练只需要根据数据集准备好这样的tensor进行regression就行