Good day guys,
I did read about RPN and looked at the source code and found these 2 fnc that I didn’t understand, what purpose do they serve? And why we should ever consider using them? Another question is that batch_size_per_image; is it meant to be the number of the anchors used on the image or the batch size of my data?
batch_size_per_image (int): number of anchors that are sampled during training of the RPN
for computing the loss
pre_nms_top_n (Dict[str, int]): number of proposals to keep before applying NMS. It should
contain two fields: training and testing, to allow for different values depending
on training or evaluation
post_nms_top_n (Dict[str, int]): number of proposals to keep after applying NMS. It should
contain two fields: training and testing, to allow for different values depending
on training or evaluation
I appreciate your time. Thanks!