Transforms

Transforms that are used to augment the data.

`Compose`

A class chaining transforms together.

Parameters:

Name	Type	Description	Default
`transform_list`	`list[TransformConfig]`	A list of dictionaries where each dictionary contains the name of a transform and its parameters.	required

Attributes:

Name	Type	Description
`_callable_transforms`	`Callable`	A callable that applies the transforms to the input data.

`transform_with_additional_arrays(patch, target=None, **additional_arrays)`

Apply the transforms to the input data, including additional arrays.

Parameters:

Name	Type	Description	Default
`patch`	`ndarray`	The input data.	required
`target`	`Optional[ndarray]`	Target data, by default None.	`None`
`**additional_arrays`	`NDArray`	Additional arrays that will be transformed identically to `patch` and `target`.	`{}`

Returns:

Type	Description
`NDArray`	The transformed patch.
`NDArray \| None`	The transformed target.
`dict of {str, NDArray}`	Transformed additional arrays. Keys correspond to the keyword argument names.

`Denormalize`

Denormalize an image.

Denormalization is performed expecting a zero mean and unit variance input. This transform expects C(Z)YX dimensions.

Note that an epsilon value of 1e-6 is added to the standard deviation to avoid division by zero during the normalization step, which is taken into account during denormalization.

Parameters:

Name	Type	Description	Default
`image_means`	`list or tuple of float`	Mean value per channel.	required
`image_stds`	`list or tuple of float`	Standard deviation value per channel.	required

`ImageRestorationTTA`

Test-time augmentation for image restoration tasks.

The augmentation is performed using all 90 deg rotations and their flipped version, as well as the original image flipped.

Tensors should be of shape SC(Z)YX.

This transformation is used in the LightningModule in order to perform test-time augmentation.

`backward(x)`

Undo the test-time augmentation.

Parameters:

Name	Type	Description	Default
`x`	`Any`	List of augmented tensors of shape SC(Z)YX.	required

Returns:

Type	Description
`Any`	Original tensor.

`forward(input_tensor)`

Apply test-time augmentation to the input tensor.

Parameters:

Name	Type	Description	Default
`input_tensor`	`Tensor`	Input tensor, shape SC(Z)YX.	required

Returns:

Type	Description
`list of torch.Tensor`	List of augmented tensors.

`N2VManipulate`

Bases: Transform

Default augmentation for the N2V model.

This transform expects C(Z)YX dimensions.

Parameters:

Name	Type	Description	Default
`roi_size`	`int`	Size of the replacement area, by default 11.	`11`
`masked_pixel_percentage`	`float`	Percentage of pixels to mask, by default 0.2.	`0.2`
`strategy`	`Literal['uniform', 'median']`	Replaccement strategy, uniform or median, by default uniform.	`value`
`remove_center`	`bool`	Whether to remove central pixel from patch, by default True.	`True`
`struct_mask_axis`	`Literal['horizontal', 'vertical', 'none']`	StructN2V mask axis, by default "none".	`'none'`
`struct_mask_span`	`int`	StructN2V mask span, by default 5.	`5`
`seed`	`Optional[int]`	Random seed, by default None.	`None`

Attributes:

Name	Type	Description
`masked_pixel_percentage`	`float`	Percentage of pixels to mask.
`roi_size`	`int`	Size of the replacement area.
`strategy`	`Literal['uniform', 'median']`	Replaccement strategy, uniform or median.
`remove_center`	`bool`	Whether to remove central pixel from patch.
`struct_mask`	`Optional[StructMaskParameters]`	StructN2V mask parameters.
`rng`	`Generator`	Random number generator.

`N2VManipulateTorch`

Default augmentation for the N2V model.

This transform expects C(Z)YX dimensions.

Parameters:

Name	Type	Description	Default
`n2v_manipulate_config`	`N2VManipulateConfig`	N2V manipulation configuration.	required
`device`	`str`	The device on which operations take place, e.g. "cuda", "cpu" or "mps".	`None`

Attributes:

Name	Type	Description
`masked_pixel_percentage`	`float`	Percentage of pixels to mask.
`roi_size`	`int`	Size of the replacement area.
`strategy`	`Literal[uniform, median]`	Replacement strategy, uniform or median.
`remove_center`	`bool`	Whether to remove central pixel from patch.
`struct_mask`	`Optional[StructMaskParameters]`	StructN2V mask parameters.
`rng`	`Generator`	Random number generator.

`Normalize`

Bases: Transform

Normalize an image or image patch.

Normalization is a zero mean and unit variance. This transform expects C(Z)YX dimensions.

Not that an epsilon value of 1e-6 is added to the standard deviation to avoid division by zero and that it returns a float32 image.

Parameters:

Name	Type	Description	Default
`image_means`	`list of float`	Mean value per channel.	required
`image_stds`	`list of float`	Standard deviation value per channel.	required
`target_means`	`list of float`	Target mean value per channel, by default None.	`None`
`target_stds`	`list of float`	Target standard deviation value per channel, by default None.	`None`

Attributes:

Name	Type	Description
`image_means`	`list of float`	Mean value per channel.
`image_stds`	`list of float`	Standard deviation value per channel.
`target_means`	`list of float, optional`	Target mean value per channel, by default None.
`target_stds`	`list of float, optional`	Target standard deviation value per channel, by default None.

`TrainDenormalize`

Denormalize an image tensor for training-time tensors.

This class mirrors Denormalize but operates on torch tensors. It expects the input tensor to have shape BC(Z)YX with the channel dimension at index 1.

Parameters:

Name	Type	Description	Default
`image_means`	`list or tuple of float`	Mean value per channel.	required
`image_stds`	`list or tuple of float`	Standard deviation value per channel.	required

`XYFlip`

Bases: Transform

Flip image along X and Y axis, one at a time.

This transform randomly flips one of the last two axes.

This transform expects C(Z)YX dimensions.

Attributes:

Name	Type	Description
`axis_indices`	`List[int]`	Indices of the axes that can be flipped.
`rng`	`Generator`	Random number generator.
`p`	`float`	Probability of applying the transform.
`seed`	`Optional[int]`	Random seed.

Parameters:

Name	Type	Description	Default
`flip_x`	`bool`	Whether to flip along the X axis, by default True.	`True`
`flip_y`	`bool`	Whether to flip along the Y axis, by default True.	`True`
`p`	`float`	Probability of applying the transform, by default 0.5.	`0.5`
`seed`	`Optional[int]`	Random seed, by default None.	`None`

`XYRandomRotate90`

Bases: Transform

Applies random 90 degree rotations to the YX axis.

This transform expects C(Z)YX dimensions.

Attributes:

Name	Type	Description
`rng`	`Generator`	Random number generator.
`p`	`float`	Probability of applying the transform.
`seed`	`Optional[int]`	Random seed.

Parameters:

Name	Type	Description	Default
`p`	`float`	Probability of applying the transform, by default 0.5.	`0.5`
`seed`	`Optional[int]`	Random seed, by default None.	`None`

`get_all_transforms()`

Return all the transforms accepted by CAREamics.

Returns:

Type	Description
`dict`	A dictionary with all the transforms accepted by CAREamics, where the keys are the transform names and the values are the transform classes.