conceptually, what will the output(s) of a layer represent? What does the output of a subset of stacked layers represent?
the shape of data that each layer expects, and the shape of data the layer will return. (When you stack many layers on top of each other, the input and output shapes must be compatible, like legos).
But if it doesn’t suck, it’s not worth doing. Robert Greene explains in his book, Mastery, that you can learn to love this internal resistance. In his words, “You find a kind of perverse pleasure in moving past the pain this might bring.”