A formula to find the size of a matrix after convolution

梦想的初衷 提交于 2019-12-02 04:39:50

Yes, there's a formula (see the details in cs231n class):

W2 = (W1 - F + 2*P) / S + 1
H2 = (H1 - F + 2*P) / S + 1

where W1xH1 is the original image size, F is the filter size, S is the stride and P is one more parameter - the padding size. Also note that result channel size equals to the number of filters.

易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!