Help,I think there is something wrong with this question
“You are working with 3D data. You are building a network layer whose input volume has size 32x32x32x16 (this volume has 16 channels), and applies convolutions with 32 filters of dimension 3x3x3 (no padding, stride 1). What is the resulting output volume?”
the input has 16 channels ,so the filter should be 3*3*3*16
Is depthwise convolution applied here, which does not need the channel dimension
Well, notice that one of the options they give you is that the specified convolution is impossible, but it turns out that is not the correct answer. They are just assuming that they don’t have to mention the channel dimension on the filters, because you just know that it needs to match the input channel dimension. You could argue that this is a bit sloppy, given that they do offer the “impossible” option. It’s a matter of judgement I guess, but you can take the quizzes again with no penalty. That’s not nearly the trickiest question on that quiz! 