I'm trying to understand exactly what does a convnet do to what, and I have trouble finding the dimensions alongside the convolutions.
If we take VGG 16 architecture, how do I get from 224x224x3 to 112x112x64 ? (The 112 is understandable, it's the last part I don't get)
I thought the CNN was to apply filters/convolutions to layers (for instance, 10 different filters to channel red, 10 to green... : are they the same filters between channels ?), but obviously 64 is not divisible by 3.
And then, how do we get from 64 to 128 ? Do we apply new filters to outputs of previous filters ? (in this case we only have 2 filters applied to previous outputs) Or is it something different ?