ClampBoundingBoxes — Torchvision 0.22 documentation (original) (raw)

class torchvision.transforms.v2.ClampBoundingBoxes[source]¶

Clamp bounding boxes to their corresponding image dimensions.

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

transform(inpt: BoundingBoxes, params: Dict[str, Any]) → BoundingBoxes[source]¶

Method to override for custom transforms.

See How to write your own v2 transforms