All transforms support torch and numpy

monai/transforms/croppad/array.py

@@ -421,6 +421,7 @@ def __call__(self, img: Union[np.ndarray, torch.Tensor]):
         Apply the transform to `img`, assuming `img` is channel-first and
         slicing doesn't apply to the channel dim.
         """
+        img, *_ = convert_data_type(img, np.ndarray)
         sd = min(len(self.slices), len(img.shape[1:]))  # spatial dims
         slices = [slice(None)] + self.slices[:sd]
         return img[tuple(slices)]
@@ -449,6 +450,7 @@ def __call__(self, img: np.ndarray):
         Apply the transform to `img`, assuming `img` is channel-first and
         slicing doesn't apply to the channel dim.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         roi_size = fall_back_tuple(self.roi_size, img.shape[1:])
         center = [i // 2 for i in img.shape[1:]]
         cropper = SpatialCrop(roi_center=center, roi_size=roi_size)
@@ -469,6 +471,7 @@ def __init__(self, roi_scale: Union[Sequence[float], float]):
         self.roi_scale = roi_scale
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         img_size = img.shape[1:]
         ndim = len(img_size)
         roi_size = [ceil(r * s) for r, s in zip(ensure_tuple_rep(self.roi_scale, ndim), img_size)]
@@ -530,6 +533,7 @@ def __call__(self, img: np.ndarray):
         Apply the transform to `img`, assuming `img` is channel-first and
         slicing doesn't apply to the channel dim.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize(img.shape[1:])
         if self._size is None:
             raise AssertionError
@@ -576,6 +580,7 @@ def __call__(self, img: np.ndarray):
         Apply the transform to `img`, assuming `img` is channel-first and
         slicing doesn't apply to the channel dim.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         img_size = img.shape[1:]
         ndim = len(img_size)
         self.roi_size = [ceil(r * s) for r, s in zip(ensure_tuple_rep(self.roi_scale, ndim), img_size)]
@@ -645,6 +650,7 @@ def __call__(self, img: np.ndarray) -> List[np.ndarray]:
         Apply the transform to `img`, assuming `img` is channel-first and
         cropping doesn't change the channel dim.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         return [self.cropper(img) for _ in range(self.num_samples)]
 
 
@@ -801,12 +807,16 @@ def __call__(self, img: np.ndarray, weight_map: Optional[np.ndarray] = None) ->
         Returns:
             A list of image patches
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         if weight_map is None:
             weight_map = self.weight_map
         if weight_map is None:
             raise ValueError("weight map must be provided for weighted patch sampling.")
         if img.shape[1:] != weight_map.shape[1:]:
             raise ValueError(f"image and weight map spatial shape mismatch: {img.shape[1:]} vs {weight_map.shape[1:]}.")
+
+        weight_map, *_ = convert_data_type(weight_map, np.ndarray)  # type: ignore
+
         self.randomize(weight_map)
         _spatial_size = fall_back_tuple(self.spatial_size, weight_map.shape[1:])
         results = []
@@ -942,6 +952,9 @@ def __call__(
         if image is None:
             image = self.image
 
+        image, *_ = convert_data_type(image, np.ndarray)  # type: ignore
+        label, *_ = convert_data_type(label, np.ndarray)  # type: ignore
+
         self.randomize(label, fg_indices, bg_indices, image)
         results: List[np.ndarray] = []
         if self.centers is not None:
@@ -1075,6 +1088,9 @@ def __call__(
         if image is None:
             image = self.image
 
+        image, *_ = convert_data_type(image, np.ndarray)  # type: ignore
+        label, *_ = convert_data_type(label, np.ndarray)  # type: ignore
+
         self.randomize(label, indices, image)
         results: List[np.ndarray] = []
         if self.centers is not None:
@@ -1127,6 +1143,7 @@ def __call__(self, img: np.ndarray, mode: Optional[Union[NumpyPadMode, str]] = N
                 If None, defaults to the ``mode`` in construction.
                 See also: https://numpy.org/doc/1.18/reference/generated/numpy.pad.html
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         return self.padder(self.cropper(img), mode=mode)
 
 
@@ -1161,6 +1178,7 @@ def __call__(self, img: np.ndarray) -> np.ndarray:
         """
         See also: :py:class:`monai.transforms.utils.generate_spatial_bounding_box`.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         bbox = []
 
         for channel in range(img.shape[0]):

monai/transforms/intensity/array.py

@@ -531,6 +531,7 @@ def __call__(self, img: np.ndarray):
         """
         Apply the transform to `img`.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize(data=img)
         if not self._do_transform:
             return img
@@ -731,6 +732,7 @@ def __call__(self, img: np.ndarray):
         """
         Apply the transform to `img`.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         epsilon = 1e-7
         img_min = img.min()
         img_range = img.max() - img_min
@@ -773,6 +775,7 @@ def __call__(self, img: np.ndarray):
         """
         Apply the transform to `img`.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize()
         if self.gamma_value is None:
             raise ValueError("gamma_value is not set.")
@@ -910,10 +913,13 @@ def __call__(self, img: np.ndarray, mask_data: Optional[np.ndarray] = None) -> n
             - ValueError: When ``mask_data`` and ``img`` channels differ and ``mask_data`` is not single channel.
 
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         mask_data = self.mask_data if mask_data is None else mask_data
         if mask_data is None:
             raise ValueError("must provide the mask_data when initializing the transform or at runtime.")
 
+        mask_data, *_ = convert_data_type(mask_data, np.ndarray)  # type: ignore
+
         mask_data = np.asarray(self.select_fn(mask_data))
         if mask_data.shape[0] != 1 and mask_data.shape[0] != img.shape[0]:
             raise ValueError(
@@ -936,7 +942,7 @@ class SavitzkyGolaySmooth(Transform):
             or ``'circular'``. Default: ``'zeros'``. See ``torch.nn.Conv1d()`` for more information.
     """
 
-    backend = [TransformBackends.NUMPY]
+    backend = [TransformBackends.TORCH]
 
     def __init__(self, window_length: int, order: int, axis: int = 1, mode: str = "zeros"):
 
@@ -1000,6 +1006,7 @@ def __call__(self, img: np.ndarray):
             np.ndarray containing envelope of data in img along the specified axis.
 
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         # add one to transform axis because a batch axis will be added at dimension 0
         hilbert_transform = HilbertTransform(self.axis + 1, self.n)
         # convert to Tensor and add Batch axis expected by HilbertTransform
@@ -1026,6 +1033,7 @@ def __init__(self, sigma: Union[Sequence[float], float] = 1.0, approx: str = "er
         self.approx = approx
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         gaussian_filter = GaussianFilter(img.ndim - 1, self.sigma, approx=self.approx)
         input_data = torch.as_tensor(np.ascontiguousarray(img), dtype=torch.float).unsqueeze(0)
         return gaussian_filter(input_data).squeeze(0).detach().numpy()
@@ -1070,6 +1078,7 @@ def randomize(self, data: Optional[Any] = None) -> None:
         self.z = self.R.uniform(low=self.sigma_z[0], high=self.sigma_z[1])
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize()
         if not self._do_transform:
             return img
@@ -1117,6 +1126,7 @@ def __init__(
         self.approx = approx
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         gaussian_filter1 = GaussianFilter(img.ndim - 1, self.sigma1, approx=self.approx)
         gaussian_filter2 = GaussianFilter(img.ndim - 1, self.sigma2, approx=self.approx)
         input_data = torch.as_tensor(np.ascontiguousarray(img), dtype=torch.float).unsqueeze(0)
@@ -1183,6 +1193,7 @@ def randomize(self, data: Optional[Any] = None) -> None:
         self.a = self.R.uniform(low=self.alpha[0], high=self.alpha[1])
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize()
         if not self._do_transform:
             return img
@@ -1227,6 +1238,7 @@ def randomize(self, data: Optional[Any] = None) -> None:
             )
 
     def __call__(self, img: np.ndarray) -> np.ndarray:
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize()
         if not self._do_transform:
             return img
@@ -1713,6 +1725,7 @@ def _transform_holes(self, img: np.ndarray) -> np.ndarray:
         raise NotImplementedError(f"Subclass {self.__class__.__name__} must implement this method.")
 
     def __call__(self, img: np.ndarray):
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         self.randomize(img.shape[1:])
         if self._do_transform:
             img = self._transform_holes(img=img)
@@ -1871,6 +1884,7 @@ def __init__(
         self.dtype = dtype
 
     def __call__(self, img: np.ndarray, mask: Optional[np.ndarray] = None) -> np.ndarray:
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         return equalize_hist(
             img=img,
             mask=mask if mask is not None else self.mask,

monai/transforms/spatial/array.py

@@ -171,6 +171,7 @@ def __call__(
             data_array (resampled into `self.pixdim`), original affine, current affine.
 
         """
+        data_array, *_ = convert_data_type(data_array, np.ndarray)  # type: ignore
         _dtype = dtype or self.dtype or data_array.dtype
         sr = data_array.ndim - 1
         if sr <= 0:
@@ -275,6 +276,7 @@ def __call__(
             data_array (reoriented in `self.axcodes`), original axcodes, current axcodes.
 
         """
+        data_array, *_ = convert_data_type(data_array, np.ndarray)  # type: ignore
         sr = data_array.ndim - 1
         if sr <= 0:
             raise ValueError("data_array must have at least one spatial dimension.")
@@ -392,6 +394,7 @@ def __call__(
             ValueError: When ``self.spatial_size`` length is less than ``img`` spatial dimensions.
 
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         if self.size_mode == "all":
             input_ndim = img.ndim - 1  # spatial ndim
             output_ndim = len(ensure_tuple(self.spatial_size))
@@ -1098,6 +1101,8 @@ class RandAffineGrid(Randomizable, Transform):
 
     """
 
+    backend = AffineGrid.backend
+
     @deprecated_arg(name="as_tensor_output", since="0.6")
     def __init__(
         self,
@@ -1930,6 +1935,7 @@ def __call__(self, img: Union[np.ndarray, torch.Tensor]):
         Args:
             img: data to be transformed, assuming `img` is channel first.
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         if max(self.spatial_channels) > img.ndim - 1:
             raise ValueError(
                 f"input has {img.ndim-1} spatial dimensions, cannot add AddCoordinateChannels channel for "

monai/transforms/utility/array.py

@@ -777,6 +777,9 @@ def __call__(
             output_shape: expected shape of output indices. if None, use `self.output_shape` instead.
 
         """
+        label, *_ = convert_data_type(label, np.ndarray)  # type: ignore
+        if image is not None:
+            image, *_ = convert_data_type(image, np.ndarray)  # type: ignore
         if output_shape is None:
             output_shape = self.output_shape
         fg_indices, bg_indices = map_binary_to_indices(label, image, self.image_threshold)
@@ -826,6 +829,10 @@ def __call__(
             output_shape: expected shape of output indices. if None, use `self.output_shape` instead.
 
         """
+        label, *_ = convert_data_type(label, np.ndarray)  # type: ignore
+        if image is not None:
+            image, *_ = convert_data_type(image, np.ndarray)  # type: ignore
+
         if output_shape is None:
             output_shape = self.output_shape
         indices = map_classes_to_indices(label, self.num_classes, image, self.image_threshold)
@@ -846,6 +853,7 @@ class ConvertToMultiChannelBasedOnBratsClasses(Transform):
     """
 
     def __call__(self, img: np.ndarray) -> np.ndarray:
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         # if img has channel dim, squeeze it
         if img.ndim == 4 and img.shape[0] == 1:
             img = np.squeeze(img, axis=0)
@@ -912,6 +920,9 @@ def __call__(
         if label.shape[0] != 1:
             raise ValueError("Only supports single channel labels!")
 
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
+        label, *_ = convert_data_type(label, np.ndarray)  # type: ignore
+
         # Generate extreme points
         self.randomize(label[0, :])
 
@@ -948,6 +959,7 @@ def __call__(self, img: torch.Tensor):
             img: PyTorch Tensor data for the TorchVision transform.
 
         """
+        img, *_ = convert_data_type(img, torch.Tensor)  # type: ignore
         return self.trans(img)
 
 
@@ -978,7 +990,7 @@ def __init__(self, orig_labels: Sequence, target_labels: Sequence, dtype: DtypeL
         self.dtype = dtype
 
     def __call__(self, img: np.ndarray):
-        img = np.asarray(img)
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         img_flat = img.flatten()
         try:
             out_flat = np.copy(img_flat).astype(self.dtype)
@@ -1034,6 +1046,7 @@ def __call__(
                 mask must have the same shape as input `img`.
 
         """
+        img, *_ = convert_data_type(img, np.ndarray)  # type: ignore
         if meta_data is None:
             meta_data = {}