The answer to the question

*“If you build a neural network that inputs a picture of a person’s face and outputs N landmarks on the face (assume the input image always contains exactly one face), how many output units will the network have?”*

should be **3N** according to me: For each landmark, there will be one probability, one x-coordinate & a y-coordinate. So, 3N in total.

But it’s showing that as wrong & it seems that 2N is given as the right answer. Is that right? Can anyone please explain?

2 Likes

if you refer to the lessons, it doesn’t include the probability, or rather they are supposed to be certain. Only x,y coordinates are needed

1 Like

It is just a landmark, landmark~point; how can we say the probability of being point? So the correct answer is 2N

Same doubt here. Have you find a convincing answer in the meanwhile?