Class ToTensor

monai/transforms/utility/array.py:383–423

Converts the input image to a tensor without applying any other transformations. Input data can be PyTorch Tensor, numpy array, list, dictionary, int, float, bool, str, etc. Will convert Tensor, Numpy array, float, int, bool to Tensor, strings and objects keep the original. For dict

class ToTensor(Transform):
    """
    Converts the input image to a tensor without applying any other transformations.
    Input data can be PyTorch Tensor, numpy array, list, dictionary, int, float, bool, str, etc.
    Will convert Tensor, Numpy array, float, int, bool to Tensor, strings and objects keep the original.
    For dictionary, list or tuple, convert every item to a Tensor if applicable and `wrap_sequence=False`.

    Args:
        dtype: target data type to when converting to Tensor.
        device: target device to put the converted Tensor data.
        wrap_sequence: if `False`, then lists will recursively call this function, default to `True`.
            E.g., if `False`, `[1, 2]` -> `[tensor(1), tensor(2)]`, if `True`, then `[1, 2]` -> `tensor([1, 2])`.
        track_meta: whether to convert to `MetaTensor` or regular tensor, default to `None`,
            use the return value of ``get_track_meta``.

    """

    backend = [TransformBackends.TORCH]

    def __init__(
        self,
        dtype: torch.dtype | None = None,
        device: torch.device | str | None = None,
        wrap_sequence: bool = True,
        track_meta: bool | None = None,
    ) -> None:
        super().__init__()
        self.dtype = dtype
        self.device = device
        self.wrap_sequence = wrap_sequence
        self.track_meta = get_track_meta() if track_meta is None else bool(track_meta)

    def __call__(self, img: NdarrayOrTensor):
        """
        Apply the transform to `img` and make it contiguous.
        """
        if isinstance(img, MetaTensor):
            img.applied_operations = []  # drops tracking info
        return convert_to_tensor(
            img, dtype=self.dtype, device=self.device, wrap_sequence=self.wrap_sequence, track_meta=self.track_meta
        )


class EnsureType(Transform):