clip_boxes_to_image

torchvision.ops.clip_boxes_to_image(boxes: Tensor, size: tuple[int, int]) → Tensor

Clip boxes so that they lie inside an image of size size.

Note

For clipping a BoundingBoxes object, consider using the transform ClampBoundingBoxes() instead.

Parameters:

• boxes (Tensor[..., 4]) – boxes in (x1, y1, x2, y2) format with 0 <= x1 < x2 and 0 <= y1 < y2.

• size (Tuple[height, width]) – size of the image

Returns:

clipped boxes

Return type:

Tensor[…, 4]