I have no Idea, how to calculate the number of the parameters in a MobileNet v2 Bottleneck block.

I watched the videos and read the Notes. But I coudn’t found a special formula or some other hints. May be, there is some answer in earlier courses. At the moment I only take this course. Please give me a hint , what can I do.

The question must have given you more to go on than that. Of course we are not supposed to post the questions and answers in the forums, but new versions of the various quizzes were recently released and a lot of students are having trouble with them. So maybe you can post the question and we can edit it out later.

The most relevant lecture here is probably this one where he walks us through how depthwise separable convolutions work.

Yes, he talked about this. The key point is that you need to understand how pointwise and depthwise convolutions work and specifically how they are applied in a MobilNet “bottleneck” block. They are special cases of the general convolutions we have been doing. In the pointwise case, they are 1 x 1 convolutions. I gave the link above to the lecture that describes depthwise convolutions. One cool thing about MobilNet that it gives us most of the power of normal convolutions with a lot less parameters to train. That’s why the computation of number of parameters is a big deal here and was covered in the lectures in some detail. You need the depthwise lecture I pointed to above and then the MobilNet Architecture lecture to see how the bottleneck block works. Here’s another recent thread which also discusses how to interpret the slides in that lecture.