nms_bev函数

 

def nms_bev(boxes, scores, thresh, pre_max_size=None, post_max_size=None):
    """NMS function GPU implementation (for BEV boxes).

    The overlap of two boxes for IoU calculation is defined as the exact
    overlapping area of the two boxes. In this function, one can also
    set ``pre_max_size`` and ``post_max_size``.

    Args:
        boxes (torch.Tensor): Input boxes with the shape of (N, 5)
            ([x1, y1, x2, y2, ry]).
        scores (torch.Tensor): Scores of boxes with the shape of (N,).
        thresh (float): Overlap threshold of NMS.
        pre_max_size (int, optional): Max size of boxes before NMS.
            Default: None.
        post_max_size (int, optional): Max size of boxes after NMS.
            Default: None.

    Returns:
        torch.Tensor: Indexes after NMS.
    """
    from .nms import nms_rotated

    warnings.warn(
        '`iou3d.nms_bev` is deprecated and will be removed in'
        ' the future. Please, use `nms.nms_rotated`.', DeprecationWarning)
    assert boxes.size(1) == 5, 'Input boxes shape should be (N, 5)'
    order = scores.sort(0, descending=True)[1]

    if pre_max_size is not None:
        order = order[:pre_max_size]
    boxes = _xyxyr2xywhr(boxes)[order]
    scores = scores[order]

    keep = nms_rotated(boxes, scores, thresh)[1]
    keep = order[keep]

    if post_max_size is not None:
        keep = keep[:post_max_size]
    return keep

 

摘自：mmcv.ops.iou3d — mmcv 2.2.0 文档 (mmcv-zh-cn.readthedocs.io)