Shortcuts

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]

torch.Tensor subclass for bounding boxes.

Note

There should be only one BoundingBoxes instance per sample e.g. {"img": img, "bbox": BoundingBoxes(...)}, although one BoundingBoxes 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 a torch.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 a torch.Tensor, the value is taken from it. Otherwise, defaults to False.

Examples using BoundingBoxes:

Getting started with transforms v2

Getting started with transforms v2

How to write your own v2 transforms

How to write your own v2 transforms

TVTensors FAQ

TVTensors FAQ

How to write your own TVTensor class

How to write your own TVTensor class

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources