[英]What are channels in tf.nn.conv2D?
I've looked through some great explanations on what different arguments of tf.nn.conv2D represent, but I still can't understand what exactly in_channels and out_channels represent. 我已经仔细阅读了有关tf.nn.conv2D的不同参数表示的一些很好的解释 ,但是我仍然无法理解in_channels和out_channels究竟代表什么。
Could someone please clarify this for me? 有人可以帮我澄清一下吗?
Lets say you have a image of size 64x64
. 假设您的图片大小为
64x64
。 It is composed of RGB
of 64x64
each, so the input size is 64x64x3
and 3
is the input channel in this case. 它由每个
64x64
的RGB
组成,因此输入大小为64x64x3
,在这种情况下,输入通道为3
。 Now you want to convolve this input with a kernel
of 5x5x3
, you get an output of 64x64x1
(with padding). 现在,您想将此输入与
5x5x3
的kernel
进行5x5x3
,您将获得64x64x1
的输出(带填充)。 Suppose you have 100
such kernels and convolve each one of them with the input, you get 64x64x100
. 假设您有
100
这样的内核,并将每个内核与输入进行卷积,则得到64x64x100
。 Here the output channels are 100
. 这里的输出通道是
100
。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.