关于1*1 conv kernel

最新推荐文章于 2024-07-03 13:37:05 发布

ForABiggerWorld

最新推荐文章于 2024-07-03 13:37:05 发布

阅读量1.3k

点赞数

本文链接：https://blog.csdn.net/zjucor/article/details/78213389

版权

1x1卷积常被用于深度学习网络中，虽然在信号处理背景下可能显得不寻常。实际上，它在3D体积上进行操作，通过全输入深度进行点积，有助于减少计算复杂度并调整通道数。尽管1x1卷积在二维信号中看似简单，但在深度学习的上下文中，它能有效控制模型复杂性和维度。

摘要由CSDN通过智能技术生成

1x1 convolution. As an aside, several papers use 1x1 convolutions, as first investigated by Network in Network. Some people are at first confused to see 1x1 convolutions especially when they come from signal processing background. Normally signals are 2-dimensional so 1x1 convolutions do not make sense (it’s just pointwise scaling). However, in ConvNets this is not the case because one must remember that we operate over 3-dimensional volumes, and that the filters always extend thr