why I have my answer as incorrect?
The formula for YOLO v2 output shape is S*S*B*(1+4+C)
where S is the grid cell count, B is the number of anchor boxes, C is the number of classes, 1 is for the probability that an object is present in that grid cell p_c, and 4 is the two coordinates for the center location (b_x, b_y) plus the two bounding box shape dimensions (b_w, b_h)
S*S*B is the number of detector locations. (1 + 4 + C) is the number of predicted values at each location.
It seems I got confused.
thanks for the clarification.
1 Like