Confusion about the nms implementation

[chinmay5]

I have some doubts regarding the nms implementation. Specifically, the part inds + 1 being used here:- https://github.com/rbgirshick/fast-rcnn/blob/b612190f279da3c11dd8b1396dd5e72779f8e463/lib/utils/nms.py#L35

The remaining code is quite clear but I am not able to wrap my brain around this particular line

[GitHub-Crow]

you can see xx1 = np.maximum(x1[i], x1[order[1:]]) , x1[order[1:]] is start from 0, so all the indices in xx1 wiil decrease 1. and order is complete (include i).