Multiple Input and Output Channels

http://d2l.ai/chapter_convolutional-neural-networks/channels.html

It would be nice to have some discussion about using other color representations like HSV/HSL. Would it help to reduce the memory usage by eliminating one dimension of the kernel if we don’t have to aggregate RGB channels?

Hey @lregistros, great question! Actually RGB and HSV/HSL have defined conversion: https://en.wikipedia.org/wiki/HSL_and_HSV#To_RGB, which should be easily implemented :slight_smile: