a PSic @sxddlmZddlZddlmZddlmZmZdejeje e ejd d d Z dejeje eejejfd d dZ dS))TupleN)_log_api_usage_once)_loss_inter_union_upcast_non_floatnoneHz>)boxes1boxes2 reductionepsreturncCsztjstjsttt|}t|}t|||\}}|dkrf|dkrX| n d| }n|dkrv| }|S)a Gradient-friendly IoU loss with an additional penalty that is non-zero when the distance between boxes' centers isn't zero. Indeed, for two exactly overlapping boxes, the distance IoU is the same as the IoU loss. This loss is symmetric, so the boxes1 and boxes2 arguments are interchangeable. Both sets of boxes are expected to be in ``(x1, y1, x2, y2)`` format with ``0 <= x1 < x2`` and ``0 <= y1 < y2``, and The two boxes should have the same dimensions. Args: boxes1 (Tensor[N, 4]): first set of boxes boxes2 (Tensor[N, 4]): second set of boxes reduction (string, optional): Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: No reduction will be applied to the output. ``'mean'``: The output will be averaged. ``'sum'``: The output will be summed. Default: ``'none'`` eps (float, optional): small number to prevent division by zero. Default: 1e-7 Returns: Tensor: Loss tensor with the reduction option applied. Reference: Zhaohui Zheng et. al: Distance Intersection over Union Loss: https://arxiv.org/abs/1911.08287 meanrgsum) torchjit is_scripting is_tracingrdistance_box_iou_lossr_diou_iou_lossnumelrr)r r r r loss_rU/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/ops/diou_loss.pyr s$"r)r r r rcCst||\}}|||}|jdd\}}}} |jdd\} } } } t|| }t|| }t|| }t| | }||d||d|}||d}| |d}| | d}| | d}||d||d}d|||}||fS)N)dimrr)runbindrminmax)r r r Zintsctunionioux1y1x2y2x1gy1gx2gy2gZxc1Zyc1Zxc2Zyc2diagonal_distance_squaredx_py_px_gy_gcenters_distance_squaredrrrrr<s          r)rr )r ) typingrrutilsr_utilsrrTensorstrfloatrrrrrrs&   6