Before you start, I highly recommend you to open This google colab notebook in parallel to understand concepts better.
Also, My implementation is heavily based on the “Guide to build Faster RCNN in PyTorch” article.
In this article, I will strictly discuss the implementation of stage one of two-stage object detectors which is the region proposal network (in Faster RCNN).
Two-stage detectors consist of two stages (duh), First stage (network) is used to suggest the region of interest (region of the image where the object might be) and these proposals are then sent to another network (stage two) for the…
+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.
Did you know buildings breathe so that you can breathe fresh? This might sound funny but…
The martian on earth