minerva.transforms.random_transform

Classes

`EmptyTransform`	A transform that does nothing to the input data.
`RandomCrop`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.
`RandomFlip`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.
`RandomGrayScale`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.
`RandomRotation`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.
`RandomSolarize`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.
`_RandomSyncedTransform`	Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Module Contents

class minerva.transforms.random_transform.EmptyTransform[source]

Bases: minerva.transforms.transform._Transform

A transform that does nothing to the input data.

__call__(data)[source]: Implement the transformation logic in this method. Usually, the transformation is applied on a single sample of data.

class minerva.transforms.random_transform.RandomCrop(crop_size, num_samples=1, seed=None, pad_mode='reflect')[source]

Bases: _RandomSyncedTransform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Parameters

transform_Transform: A transform that will be applied to the input data.
num_samplesint: The number of samples that will be transformed.
seedOptional[int], optional: The seed that will be used to generate the random state, by default None.

crop_size

pad_mode = 'reflect'

select_transform()[source]

Parameters:

crop_size (Tuple[int, int])
num_samples (int)
seed (Optional[int])
pad_mode (str)

class minerva.transforms.random_transform.RandomFlip(num_samples=1, possible_axis=0, seed=None)[source]

Bases: _RandomSyncedTransform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

A transform that flips the input data along a random axis.

Parameters

num_samplesint: The number of samples that will be transformed.
possible_axisUnion[int, List[int]], optional: Possible axis to be transformed, will be chosen at random, by default 0
seedOptional[int], optional: A seed to ensure deterministic run, by default None

possible_axis = 0

select_transform()[source]: selects the transform to be applied to the data.

Parameters:

num_samples (int)
possible_axis (Union[int, List[int]])
seed (Optional[int])

class minerva.transforms.random_transform.RandomGrayScale(num_samples=1, seed=None, prob=0.1, gray=1.0)[source]

Bases: _RandomSyncedTransform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Parameters

transform_Transform: A transform that will be applied to the input data.
num_samplesint: The number of samples that will be transformed.
seedOptional[int], optional: The seed that will be used to generate the random state, by default None.

gray = 1.0

prob = 0.1

select_transform()[source]

Parameters:

num_samples (int)
seed (Optional[int])
prob (float)
gray (float)

class minerva.transforms.random_transform.RandomRotation(degrees, prob, num_samples=1, seed=None)[source]

Bases: _RandomSyncedTransform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Parameters

transform_Transform: A transform that will be applied to the input data.
num_samplesint: The number of samples that will be transformed.
seedOptional[int], optional: The seed that will be used to generate the random state, by default None.

degrees

prob

select_transform()[source]

Parameters:

degrees (float)
prob (float)
num_samples (int)
seed (Optional[int])

class minerva.transforms.random_transform.RandomSolarize(num_samples=1, seed=None, threshold=128, prob=1.0)[source]

Bases: _RandomSyncedTransform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Parameters

transform_Transform: A transform that will be applied to the input data.
num_samplesint: The number of samples that will be transformed.
seedOptional[int], optional: The seed that will be used to generate the random state, by default None.

prob = 1.0

select_transform()[source]

threshold = 128

Parameters:

num_samples (int)
seed (Optional[int])
threshold (int)
prob (float)

class minerva.transforms.random_transform._RandomSyncedTransform(num_samples=1, seed=None)[source]

Bases: minerva.transforms.transform._Transform

Orchestrate the application of a type of random transform to a list of data, ensuring that the same random state is used for all of them.

Parameters

transform_Transform: A transform that will be applied to the input data.
num_samplesint: The number of samples that will be transformed.
seedOptional[int], optional: The seed that will be used to generate the random state, by default None.

__call__(data)[source]: Implement the transformation logic in this method. Usually, the transformation is applied on a single sample of data.

num_samples = 1

rng

abstract select_transform()[source]

transform

transformations_executed = 0

Parameters:

num_samples (int)
seed (Optional[int])