BoundingBoxes¶
- class torchvision.tv_tensors.BoundingBoxes(data: Any, *, format: Union[BoundingBoxFormat, str], canvas_size: Tuple[int, int], dtype: Optional[dtype] = None, device: Optional[Union[device, str, int]] = None, requires_grad: Optional[bool] = None)[source]¶
[BETA]
torch.Tensor
subclass for bounding boxes.Note
There should be only one
BoundingBoxes
instance per sample e.g.{"img": img, "bbox": BoundingBoxes(...)}
, although oneBoundingBoxes
object can contain multiple bounding boxes.- Parameters:
data – Any data that can be turned into a tensor with
torch.as_tensor()
.format (BoundingBoxFormat, str) – Format of the bounding box.
canvas_size (two-tuple of python:ints) – Height and width of the corresponding image or video.
dtype (torch.dpython:type, optional) – Desired data type of the bounding box. If omitted, will be inferred from
data
.device (torch.device, optional) – Desired device of the bounding box. If omitted and
data
is atorch.Tensor
, the device is taken from it. Otherwise, the bounding box is constructed on the CPU.requires_grad (bool, optional) – Whether autograd should record operations on the bounding box. If omitted and
data
is atorch.Tensor
, the value is taken from it. Otherwise, defaults toFalse
.
Examples using
BoundingBoxes
:Getting started with transforms v2
Getting started with transforms v2How to write your own v2 transforms
How to write your own v2 transformsTVTensors FAQHow to write your own TVTensor class
How to write your own TVTensor class