mmcv.ops.nms_rotated

mmcv.ops.nms_rotated(dets: torch.Tensor, scores: torch.Tensor, iou_threshold: float, labels: Optional[torch.Tensor] = None, clockwise: bool = True) → Tuple[torch.Tensor, torch.Tensor]

Performs non-maximum suppression (NMS) on the rotated boxes according to their intersection-over-union (IoU).

Rotated NMS iteratively removes lower scoring rotated boxes which have an IoU greater than iou_threshold with another (higher scoring) rotated box.

Parameters

• dets (torch.Tensor) – Rotated boxes in shape (N, 5). They are expected to be in (x_ctr, y_ctr, width, height, angle_radian) format.

• scores (torch.Tensor) – scores in shape (N, ).

• iou_threshold (float) – IoU thresh for NMS.

• labels (torch.Tensor, optional) – boxes’ label in shape (N,).

• clockwise (bool) – flag indicating whether the positive angular orientation is clockwise. default True. New in version 1.4.3.

Returns

kept dets(boxes and scores) and indice, which is always the same data type as the input.

Return type

tuple