Deep learning for NeuroImaging in Python.

Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the gallery for the big picture.

class nidl.volume.transforms.preprocessing.spatial.crop_or_pad.CropOrPad(target_shape: int | tuple[int, int, int], padding_mode: str = 'constant', constant_values: float | tuple[float, float, float] = 0.0, **kwargs)[source]¶

Bases: VolumeTransform

Crop and/or pad a 3d volume to match the target shape.

It handles np.ndarray or torch.Tensor as input and returns a consistent output (same type).

Parameters:

target_shape : int or tuple[int, int, int]

Expected output shape. If int, apply the same size across all dimensions.

padding_mode : str in {‘edge’, ‘maximum’, ‘constant’, ‘mean’, ‘median’, ‘minimum’, ‘reflect’, ‘symmetric’}

Possible modes for padding. See more infos in the Numpy documentation.

constant_values : float or tuple[float, float, float]

The values to set the padded values for each axis if the padding mode is ‘constant’.

kwargs : dict

Keyword arguments given to nidl.transforms.Transform.

apply_transform(data: ndarray | Tensor) → ndarray | Tensor[source]¶

Crop and/or pad the input data to match target shape.

Parameters:: data : np.ndarray or torch.Tensor

The input data with shape $(C, H, W, D)$ or $(H, W, D)$ . Transformation is applied across all channels.
Returns:: data : np.ndarray or torch.Tensor

Cropped or padded data with same type as input and shape target_shape.