RetinaFace记录
深度可分离卷积
https://yinguobing.com/separable-convolution/#fn2
https://blog.csdn.net/ly18846826264/article/details/105144998
MobileNetv1
https://www.jianshu.com/p/f601fa110eaf
在torch.nn.Conv2d中,group参数用来控制是否对输入的每个通道单独设置卷积:
At groups= in_channels, each input cha
原创
2020-11-18 10:01:28 ·
88 阅读 ·
0 评论