where can I find this non-max suppression file called in the return statement? (most likely a CPP file)

384 Views Asked by At

This torchvision.ops.nms(boxes, scores, iou_thres) takes me to the boxes.py file in "C:\Users\anaconda\envs\gpu_low\Lib\site-packages\torchvision\ops" where gpu_low is my virtual environment name. In this boxes.py file there is a function nms:

def nms(boxes: Tensor, scores: Tensor, iou_threshold: float) -> Tensor:
    """
    Performs non-maximum suppression (NMS) on the boxes according
    to their intersection-over-union (IoU).

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

    If multiple boxes have the exact same score and satisfy the IoU
    criterion with respect to a reference box, the selected box is
    not guaranteed to be the same between CPU and GPU. This is similar
    to the behavior of argsort in PyTorch when repeated values are present.

    Args:
        boxes (Tensor[N, 4])): boxes to perform NMS on. They
            are expected to be in ``(x1, y1, x2, y2)`` format with ``0 <= x1 < x2`` and
            ``0 <= y1 < y2``.
        scores (Tensor[N]): scores for each one of the boxes
        iou_threshold (float): discards all overlapping boxes with IoU > iou_threshold

    Returns:
        Tensor: int64 tensor with the indices of the elements that have been kept
        by NMS, sorted in decreasing order of scores
    """
    _assert_has_ops()
    #print("nms working")
    return torch.ops.torchvision.nms(boxes, scores, iou_threshold)

Now I can't find torch.ops.torchvision.nms(boxes, scores, iou_threshold) in the return statement

if anybody knows then please help me locate this file/function.(I have already tried finding the location using visual studio code but it can't find the location)

0

There are 0 best solutions below