ClampBoundingBoxes

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

Clamp bounding boxes to their corresponding image dimensions.

The clamping is done according to the bounding boxes’ canvas_size meta-data.

Parameters:

clamping_mode – TODOBB more docs. Default is None which relies on the input box’ clamping_mode attribute.

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