dear author:
your paper writes "Adopting the K nearest anchor as positive anchors for each ground-truth box", but when reading your code, I saw that you selected K nearest positive samples from pred boxes and anchors respectively. In fact, the number of positive samples corresponding to each GT box is 2k. Is this a later improvement?
we also attention that uniform matching ignore the positive samples which IoU<0.15.does this will cause some very small targets have none positive samples?
dear author:
your paper writes "Adopting the K nearest anchor as positive anchors for each ground-truth box", but when reading your code, I saw that you selected K nearest positive samples from pred boxes and anchors respectively. In fact, the number of positive samples corresponding to each GT box is 2k. Is this a later improvement?
we also attention that uniform matching ignore the positive samples which IoU<0.15.does this will cause some very small targets have none positive samples?