+50 for this amazing article. Just want to clear myself on the statement:

"So if k = 3, we select P3 as our feature maps. We apply the ROI pooling and feed the result to the Fast R-CNN head (Fast R-CNN and Faster R-CNN have the same head) to finish the prediction."

So here we feed the whole P3 generated via FPN right? Because in figure 12 (2nd figure under the heading "FPN with Fast R-CNN or Faster R-CNN)), It seems like we are feeding ROI and not the whole feature map (ie- P3).

Thank you, keep up the good work Jonathan.