Function random_rotations

data/rotation_utils/conversions.py:339–355

Generate random rotations as 3x3 rotation matrices. Args: n: Number of rotation matrices in a batch to return. dtype: Type to return. device: Device of returned tensor. Default: if None, uses the current device for the default tensor type. Returns:

(
    n: int, dtype: Optional[torch.dtype] = None, device: Optional[int] = None
)

def random_rotations(
    n: int, dtype: Optional[torch.dtype] = None, device: Optional[int] = None
) -> torch.Tensor:
    """
    Generate random rotations as 3x3 rotation matrices.

    Args:
        n: Number of rotation matrices in a batch to return.
        dtype: Type to return.
        device: Device of returned tensor. Default: if None,
            uses the current device for the default tensor type.

    Returns:
        Rotation matrices as tensor of shape (n, 3, 3).
    """
    quaternions = random_quaternions(n, dtype=dtype, device=device)
    return quaternion_to_matrix(quaternions)