torchvision.ops.complete_box_iou(boxes1: Tensor, boxes2: Tensor, eps: float = 1e-07) Tensor[source]

Return complete intersection-over-union (Jaccard index) between two sets of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format with 0 <= x1 < x2 and 0 <= y1 < y2. :param boxes1: first set of boxes :type boxes1: Tensor[N, 4] :param boxes2: second set of boxes :type boxes2: Tensor[M, 4] :param eps: small number to prevent division by zero. Default: 1e-7 :type eps: float, optional


the NxM matrix containing the pairwise complete IoU values for every element in boxes1 and boxes2

Return type:

Tensor[N, M]


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources