Args: keys: keys of the corresponding items to be transformed. mode: {``"bilinear"``, ``"nearest"``} or spline interpolation order 0-5 (integers). Interpolation mode to calculate output values. Defaults to ``"bilinear"``. See also: htt
(
self,
keys: KeysCollection,
mode: SequenceStr = GridSampleMode.BILINEAR,
padding_mode: SequenceStr = GridSamplePadMode.BORDER,
align_corners: Sequence[bool] | bool = False,
dtype: Sequence[DtypeLike] | DtypeLike = np.float64,
dst_keys: KeysCollection | None = "dst_affine",
allow_missing_keys: bool = False,
lazy: bool = False,
)
| 173 | backend = SpatialResample.backend |
| 174 | |
| 175 | def __init__( |
| 176 | self, |
| 177 | keys: KeysCollection, |
| 178 | mode: SequenceStr = GridSampleMode.BILINEAR, |
| 179 | padding_mode: SequenceStr = GridSamplePadMode.BORDER, |
| 180 | align_corners: Sequence[bool] | bool = False, |
| 181 | dtype: Sequence[DtypeLike] | DtypeLike = np.float64, |
| 182 | dst_keys: KeysCollection | None = "dst_affine", |
| 183 | allow_missing_keys: bool = False, |
| 184 | lazy: bool = False, |
| 185 | ) -> None: |
| 186 | """ |
| 187 | Args: |
| 188 | keys: keys of the corresponding items to be transformed. |
| 189 | mode: {``"bilinear"``, ``"nearest"``} or spline interpolation order 0-5 (integers). |
| 190 | Interpolation mode to calculate output values. Defaults to ``"bilinear"``. |
| 191 | See also: https://pytorch.org/docs/stable/generated/torch.nn.functional.grid_sample.html |
| 192 | When it's an integer, the numpy (cpu tensor)/cupy (cuda tensor) backends will be used |
| 193 | and the value represents the order of the spline interpolation. |
| 194 | See also: https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.map_coordinates.html |
| 195 | It also can be a sequence, each element corresponds to a key in ``keys``. |
| 196 | padding_mode: {``"zeros"``, ``"border"``, ``"reflection"``} |
| 197 | Padding mode for outside grid values. Defaults to ``"border"``. |
| 198 | See also: https://pytorch.org/docs/stable/generated/torch.nn.functional.grid_sample.html |
| 199 | When `mode` is an integer, using numpy/cupy backends, this argument accepts |
| 200 | {'reflect', 'grid-mirror', 'constant', 'grid-constant', 'nearest', 'mirror', 'grid-wrap', 'wrap'}. |
| 201 | See also: https://docs.scipy.org/doc/scipy/reference/generated/scipy.ndimage.map_coordinates.html |
| 202 | It also can be a sequence, each element corresponds to a key in ``keys``. |
| 203 | align_corners: Geometrically, we consider the pixels of the input as squares rather than points. |
| 204 | See also: https://pytorch.org/docs/stable/nn.functional.html#grid-sample |
| 205 | It also can be a sequence of bool, each element corresponds to a key in ``keys``. |
| 206 | dtype: data type for resampling computation. Defaults to ``float64`` for best precision. |
| 207 | If None, use the data type of input data. To be compatible with other modules, |
| 208 | the output data type is always ``float32``. |
| 209 | It also can be a sequence of dtypes, each element corresponds to a key in ``keys``. |
| 210 | dst_keys: the key of the corresponding ``dst_affine`` in the metadata dictionary. |
| 211 | allow_missing_keys: don't raise exception if key is missing. |
| 212 | lazy: a flag to indicate whether this transform should execute lazily or not. |
| 213 | Defaults to False. |
| 214 | """ |
| 215 | MapTransform.__init__(self, keys, allow_missing_keys) |
| 216 | LazyTransform.__init__(self, lazy=lazy) |
| 217 | self.sp_transform = SpatialResample(lazy=lazy) |
| 218 | self.mode = ensure_tuple_rep(mode, len(self.keys)) |
| 219 | self.padding_mode = ensure_tuple_rep(padding_mode, len(self.keys)) |
| 220 | self.align_corners = ensure_tuple_rep(align_corners, len(self.keys)) |
| 221 | self.dtype = ensure_tuple_rep(dtype, len(self.keys)) |
| 222 | self.dst_keys = ensure_tuple_rep(dst_keys, len(self.keys)) |
| 223 | |
| 224 | @LazyTransform.lazy.setter # type: ignore |
| 225 | def lazy(self, val: bool) -> None: |
nothing calls this directly
no test coverage detected