tf.nn.conv2D中的通道是什么？

Question

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.

Could someone please clarify this for me?

Answer 1

Lets say you have a image of size 64x64 . It is composed of RGB of 64x64 each, so the input size is 64x64x3 and 3 is the input channel in this case. Now you want to convolve this input with a kernel of 5x5x3 , you get an output of 64x64x1 (with padding). Suppose you have 100 such kernels and convolve each one of them with the input, you get 64x64x100 . Here the output channels are 100 .