ClampBoundingBoxes

class torchvision.transforms.v2.ClampBoundingBoxes(clamping_mode: Optional[str] = 'auto')

Clamp bounding boxes to their corresponding image dimensions.

Parameters:

clamping_mode – Default is “auto” which relies on the input box’ clamping_mode attribute. Read more in Clamping Mode, and its effect on transforms for more details on how to use this transform.

Examples using ClampBoundingBoxes:

Transforms on Rotated Bounding Boxes

Transforms on Rotated Bounding Boxes

transform(inpt: BoundingBoxes, params: dict[str, Any]) → BoundingBoxes

Method to override for custom transforms.

See How to write your own v2 transforms