Some questions about region_assigner.py

[TengfeiHou]

Thanks for ur wonderful work!

I try to do some extension depends on ur codes, but when i read the code, I find something strange.

Its in mmdet/core/bbox/assigner/region_assigner.py

In step 4 :Assign -1 to ignore adjacent lvl when use calc_region function ,

d_ignore_region = calc_region(gt_bbox, d_stride, r2, d_featmap_size)
u_ignore_region = calc_region(gt_bbox, u_stride, r2, u_featmap_size)

should r2 and d_stride or u_stride change their place?

I try some example and under this code condition I get strange x,y

gt_box : tensor([473.8398, 384.1748, 804.3822, 467.8830], device='cuda:0') d_ignore_region : x1(tensor(167., dvice='cuda:0'), y2tensor(99., device='cuda:0'), x2:tensor(0., device='cuda:0'), y2:tensor(0., device='cuda:0'))

x1 even larger than x2

but I change their place, the d_ignore_region/u_ignore_region seems normal

So I wonder if the code is something wrong, or I misunderstand someting

Thanks

[thangvubk]

Hi @TengfeiHou, Thank you for reporting the bug. The order should be changed. If the order is not changed some positive boxes of adjacent levels are not ignored. I think it will not change the final results. I will benchmark it again and report it here if it affects the performance.