Not able to use monai.transforms.Spacingd with splines.

[YerePhy]

Problem

According to the documentation, I should be able to use monai.transforms.Spacingd if I pass an integer to mode parameter. However, I'm getting the following error:

img_folder = Path("/home/yere/Repositories/brain_tumor/data/BraTS2021/processed/BraTS2021/11")
images = {img: img_folder.joinpath(img+".nii.gz") for img in ["T1", "T1CE", "T2", "FLAIR"]}

pipe = monai.transforms.Compose([
        monai.transforms.LoadImaged(keys=["T1", "T1CE", "T2", "FLAIR"]),
        monai.transforms.Spacingd(keys=["T1", "T1CE", "T2", "FLAIR"], pixdim=(2, 2, 2), mode=3),
        monai.transforms.ConcatItemsd(keys=["T1", "T1CE", "T2", "FLAIR"], name="INPUTS")
])

inputs = pipe(images)
print(
    inputs["FLAIR"].shape,
    inputs["FLAIR"].dtype
)

ValueError                                Traceback (most recent call last)
File ~/.local/lib/python3.9/site-packages/monai/transforms/transform.py:91, in apply_transform(transform, data, map_items, unpack_items, log_stats)
     90         return [_apply_transform(transform, item, unpack_items) for item in data]
---> 91     return _apply_transform(transform, data, unpack_items)
     92 except Exception as e:
     93     # if in debug mode, don't swallow exception so that the breakpoint
     94     # appears where the exception was raised.

File ~/.local/lib/python3.9/site-packages/monai/transforms/transform.py:55, in _apply_transform(transform, parameters, unpack_parameters)
     53     return transform(*parameters)
---> 55 return transform(parameters)

File ~/.local/lib/python3.9/site-packages/monai/transforms/spatial/dictionary.py:416, in Spacingd.__call__(self, data)
    412 for key, mode, padding_mode, align_corners, dtype, scale_extent in self.key_iterator(
    413     d, self.mode, self.padding_mode, self.align_corners, self.dtype, self.scale_extent
    414 ):
    415     # resample array of each corresponding key
--> 416     d[key] = self.spacing_transform(
    417         data_array=d[key],
    418         mode=mode,
    419         padding_mode=padding_mode,
    420         align_corners=align_corners,
    421         dtype=dtype,
    422         scale_extent=scale_extent,
...
    116     else:
    117         _log_stats(data=data)
--> 118 raise RuntimeError(f"applying transform {transform}") from e

RuntimeError: applying transform <monai.transforms.spatial.dictionary.Spacingd object at 0x7f5719f1d550>

Question

What is the correct way of using spline of grade n in monai.transforms.Spacingd?

Specs

python --version: Python 3.9.13
python -c "import monai; print(monai.__version__)": 1.0.1
lsb_release -a:
    No LSB modules are available.
    Distributor ID: Ubuntu
    Description:    Ubuntu 20.04.5 LTS
    Release:        20.04
    Codename:       focal

[wyli]

the default padding_mode doesn't work with the backend,
perhaps you can try one of these values 'grid-mirror', 'grid-constant', 'mirror', 'nearest', 'grid-wrap', 'constant', 'reflect', 'wrap':

>>> from monai.transforms import Spacingd
>>> import torch
>>> x = torch.zeros((4, 100, 100, 100))
>>> output = Spacingd(keys="image", pixdim=(2,2,2),  mode=3, padding_mode="nearest")({"image": x})
>>> output["image"].shape
(4, 50, 50, 50)