batched_nms(boxes: torch.Tensor, scores: torch.Tensor, idxs: torch.Tensor, iou_threshold: float) → torch.Tensor¶
Performs non-maximum suppression in a batched fashion.
Each index value correspond to a category, and NMS will not be applied between elements of different categories.
boxes (Tensor[N, 4]) – boxes where NMS will be performed. They are expected to be in
(x1, y1, x2, y2)format with
0 <= x1 < x2and
0 <= y1 < y2.
scores (Tensor[N]) – scores for each one of the boxes
idxs (Tensor[N]) – indices of the categories for each one of the boxes.
iou_threshold (float) – discards all overlapping boxes with IoU > iou_threshold
int64 tensor with the indices of the elements that have been kept by NMS, sorted in decreasing order of scores
- Return type