o ϯi @s6ddlZ  d dejdejdededejf d d ZdS) NnoneHz>boxes1boxes2 reductionepsreturncCs|jdd\}}}}|jdd\}} } } ||ksJd||ks(Jdt||} t|| } t|| }t|| }t|}|| k|| k@}||| |||| |||<||||| || | |}|||}t||}t|| }t|| }t|| }||||}|||||}d|}|dkr|dkr|}|Sd|}|S|d kr|}|S) a Generalized Intersection over Union Loss (Hamid Rezatofighi et. al) https://arxiv.org/abs/1902.09630 Gradient-friendly IoU loss with an additional penalty that is non-zero when the boxes do not overlap and scales with the size of their smallest enclosing box. This loss is symmetric, so the boxes1 and boxes2 arguments are interchangeable. Args: boxes1, boxes2 (Tensor): box locations in XYXY format, shape (N, 4) or (4,). reduction: 'none' | 'mean' | 'sum' 'none': No reduction will be applied to the output. 'mean': The output will be averaged. 'sum': The output will be summed. eps (float): small number to prevent division by zero )dimzbad box: x1 larger than x2zbad box: y1 larger than y2meanrgsum) unbindalltorchmaxmin zeros_likenumelr r )rrrrx1y1x2y2x1gy1gx2gy2gxkis1ykis1xkis2ykis2intsctkmaskunionkioukxc1yc1xc2yc2area_cmiouklossr,G/home/ubuntu/.local/lib/python3.10/site-packages/fvcore/nn/giou_loss.py giou_losss8     $$      r.)rr)rTensorstrfloatr.r,r,r,r-s