trw.transforms.affine

Module Contents

Functions

affine_transformation_translation(t: Sequence[float]) → torch.Tensor	Defines an affine translation for 2D or 3D data
affine_transformation_scale(s: Sequence[float]) → torch.Tensor	Defines an affine scaling transformation (2D or 3D)
affine_transformation_rotation2d(angle_radian: float) → torch.Tensor	Defines a 2D rotation transform
affine_transformation_rotation_3d_x(angle_radian: float) → torch.Tensor	Rotation in 3D around the x axis
affine_transformation_rotation_3d_y(angle_radian: float) → torch.Tensor	Rotation in 3D around the y axis
affine_transformation_get_spacing(pst: torch.Tensor) → torch.Tensor	Return the spacing (expansion factor) of the transformation per dimension XY[Z]
affine_transformation_get_origin(pst: torch.Tensor) → torch.Tensor	Return the origin of the transformation per dimension XY[Z]
affine_transformation_rotation_3d_z(angle_radian: float) → torch.Tensor	Rotation in 3D around the y axis
apply_homogeneous_affine_transform(transform: torch.Tensor, position: torch.Tensor)	Apply an homogeneous affine transform (4x4 for 3D or 3x3 for 2D) to a position
apply_homogeneous_affine_transform_zyx(transform: torch.Tensor, position_zyx: torch.Tensor)	Apply an homogeneous affine transform (4x4 for 3D or 3x3 for 2D) to a position
to_voxel_space_transform(matrix: torch.Tensor, image_shape: trw.basic_typing.ShapeCX) → torch.Tensor	Express the affine transformation in image space coordinate in range (-1, 1)
affine_transform(images: trw.basic_typing.TorchTensorNCX, affine_matrices: torch.Tensor, interpolation: str = 'bilinear', padding_mode: str = 'border', align_corners: bool = None) → trw.basic_typing.TorchTensorNCX	Transform a series of images with a series of affine transformations

trw.transforms.affine.affine_transformation_translation(t: Sequence[float]) → torch.Tensor

Defines an affine translation for 2D or 3D data

For a 3D transformation, returns a 4x4 matrix:

1 0 0 X |

M = | 0 1 0 Y |

0 0 1 Z |

0 0 0 1 |

Parameters

t – a (X, Y, Z) or (X, Y) tuple

Returns

a transformation matrix

trw.transforms.affine.affine_transformation_scale(s: Sequence[float]) → torch.Tensor

Defines an affine scaling transformation (2D or 3D)

For a 3D transformation, returns 4x4 matrix:

Sx 0 0 0 |

M = | 0 Sy 0 0 |

0 0 Sz 0 |

0 0 0 1 |

Parameters

s – a (Sx, Sy, Sz) or (Sx, Sy) tuple

Returns

a transformation matrix

trw.transforms.affine.affine_transformation_rotation2d(angle_radian: float) → torch.Tensor

Defines a 2D rotation transform :param angle_radian: the rotation angle in radian

Returns

a 3x3 transformation matrix

trw.transforms.affine.affine_transformation_rotation_3d_x(angle_radian: float) → torch.Tensor

Rotation in 3D around the x axis

See also

https://en.wikipedia.org/wiki/Rotation_matrix

Parameters

angle_radian –

Returns

4x4 torch.Tensor

trw.transforms.affine.affine_transformation_rotation_3d_y(angle_radian: float) → torch.Tensor

Rotation in 3D around the y axis

See also

https://en.wikipedia.org/wiki/Rotation_matrix

Parameters

angle_radian –

Returns

4x4 torch.Tensor

trw.transforms.affine.affine_transformation_get_spacing(pst: torch.Tensor) → torch.Tensor

Return the spacing (expansion factor) of the transformation per dimension XY[Z]

Parameters

pst – a 3x3 or 4x4 transformation matrix

Returns

XY[Z] spacing

trw.transforms.affine.affine_transformation_get_origin(pst: torch.Tensor) → torch.Tensor

Return the origin of the transformation per dimension XY[Z]

Parameters

pst – a 3x3 or 4x4 transformation matrix

Returns

XY[Z] origin

trw.transforms.affine.affine_transformation_rotation_3d_z(angle_radian: float) → torch.Tensor

Rotation in 3D around the y axis

See also

https://en.wikipedia.org/wiki/Rotation_matrix

Parameters

angle_radian –

Returns

4x4 torch.Tensor

trw.transforms.affine.apply_homogeneous_affine_transform(transform: torch.Tensor, position: torch.Tensor)

Apply an homogeneous affine transform (4x4 for 3D or 3x3 for 2D) to a position

Parameters

• transform – an homogeneous affine transformation

• position – XY(Z) position

Returns

a transformed position XY(Z)

trw.transforms.affine.apply_homogeneous_affine_transform_zyx(transform: torch.Tensor, position_zyx: torch.Tensor)

Apply an homogeneous affine transform (4x4 for 3D or 3x3 for 2D) to a position

Parameters

• transform – an homogeneous affine transformation

• position_zyx – (Z)YX position

Returns

a transformed position (Z)YX

trw.transforms.affine.to_voxel_space_transform(matrix: torch.Tensor, image_shape: trw.basic_typing.ShapeCX) → torch.Tensor

Express the affine transformation in image space coordinate in range (-1, 1)

Parameters

• matrix – a transformation matrix for 2D or 3D transformation

• image_shape – the transformation matrix will be mapped to the image space coordinate system (i.e., the matrix is expressed as “voxel”). Should be [C, D, H, W] or [C, H, W] matrix (no N component)

Returns

a 2x3 or 3x4 transform

See:

this is often used with trw.transforms.affine_transform or torch.nn.functional.affine_grid

trw.transforms.affine.affine_transform(images: trw.basic_typing.TorchTensorNCX, affine_matrices: torch.Tensor, interpolation: str = 'bilinear', padding_mode: str = 'border', align_corners: bool = None) → trw.basic_typing.TorchTensorNCX

Transform a series of images with a series of affine transformations

Parameters

• images – 3D or 2D images with shape [N, C, D, H, W] or [N, C, H, W] respectively

• affine_matrices – a list of size N of 3x4 or 2x3 matrices (see trw.transforms.to_voxel_space_transform

• interpolation – the interpolation method. Can be nearest or bilinear

• padding_mode – the padding to be used for resampled voxels outside the image. Can be 'zeros' | 'border' | 'reflection'

• align_corners – Geometrically, we consider the pixels of the input as squares rather than points.

Returns

images transformed