sanitize_bounding_boxes¶
- torchvision.transforms.v2.functional.sanitize_bounding_boxes(bounding_boxes: Tensor, format: Optional[BoundingBoxFormat] = None, canvas_size: Optional[Tuple[int, int]] = None, min_size: float = 1.0, min_area: float = 1.0) Tuple[Tensor, Tensor] [source]¶
Remove degenerate/invalid bounding boxes and return the corresponding indexing mask.
This removes bounding boxes that:
are below a given
min_size
ormin_area
: by default this also removes degenerate boxes that have e.g. X2 <= X1.have any coordinate outside of their corresponding image. You may want to call
clamp_bounding_boxes()
first to avoid undesired removals.
It is recommended to call it at the end of a pipeline, before passing the input to the models. It is critical to call this transform if
RandomIoUCrop
was called. If you want to be extra careful, you may call it after all transforms that may modify bounding boxes but once at the end should be enough in most cases.- Parameters:
bounding_boxes (Tensor or
BoundingBoxes
) – The bounding boxes to be sanitized.format (str or
BoundingBoxFormat
, optional) – The format of the bounding boxes. Must be left to none ifbounding_boxes
is aBoundingBoxes
object.canvas_size (tuple of python:int, optional) – The canvas_size of the bounding boxes (size of the corresponding image/video). Must be left to none if
bounding_boxes
is aBoundingBoxes
object.min_size (float, optional) –
min_area (float, optional) –
- Returns:
The subset of valid bounding boxes, and the corresponding indexing mask. The mask can then be used to subset other tensors (e.g. labels) that are associated with the bounding boxes.
- Return type:
out (tuple of Tensors)