Class Boxes

detectron2/structures/boxes.py:133–319

This structure stores a list of boxes as a Nx4 torch.Tensor. It supports some common methods about boxes (`area`, `clip`, `nonempty`, etc), and also behaves like a Tensor (support indexing, `to(device)`, `.device`, and iteration over all boxes) Attributes: tensor (t

class Boxes:
    """
    This structure stores a list of boxes as a Nx4 torch.Tensor.
    It supports some common methods about boxes
    (`area`, `clip`, `nonempty`, etc),
    and also behaves like a Tensor
    (support indexing, `to(device)`, `.device`, and iteration over all boxes)

    Attributes:
        tensor (torch.Tensor): float matrix of Nx4. Each row is (x1, y1, x2, y2).
    """

    def __init__(self, tensor: torch.Tensor):
        """
        Args:
            tensor (Tensor[float]): a Nx4 matrix.  Each row is (x1, y1, x2, y2).
        """
        device = tensor.device if isinstance(tensor, torch.Tensor) else torch.device("cpu")
        tensor = torch.as_tensor(tensor, dtype=torch.float32, device=device)
        if tensor.numel() == 0:
            # Use reshape, so we don't end up creating a new tensor that does not depend on
            # the inputs (and consequently confuses jit)
            tensor = tensor.reshape((0, 4)).to(dtype=torch.float32, device=device)
        assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()

        self.tensor = tensor

    def clone(self) -> "Boxes":
        """
        Clone the Boxes.

        Returns:
            Boxes
        """
        return Boxes(self.tensor.clone())

    # https://github.com/pytorch/pytorch/issues/47405
    @torch.jit.unused
    def to(self, device: torch.device = None):  # noqa
        # Boxes are assumed float32 and does not support to(dtype)
        return Boxes(self.tensor.to(device=device))

    def area(self) -> torch.Tensor:
        """
        Computes the area of all the boxes.

        Returns:
            torch.Tensor: a vector with areas of each box.
        """
        box = self.tensor
        area = (box[:, 2] - box[:, 0]) * (box[:, 3] - box[:, 1])
        return area

    def clip(self, box_size: Tuple[int, int]) -> None:
        """
        Clip (in place) the boxes by limiting x coordinates to the range [0, width]
        and y coordinates to the range [0, height].