MAITEImageClassificationAugmentation

class nrtk.interop.MAITEImageClassificationAugmentation(*, augment: PerturbImage, augment_id: str)

Implementation of MAITE Image Classification Augmentation for NRTK perturbers.

Implementation of MAITE Augmentation for NRTK perturbers operating on a MAITE-protocol compliant Image Classification dataset.

Attributes:

augment: PerturbImage

Augmentations to apply to an image.

name: str

Name of the augmentation. Will appear in metadata key.

Methods

__call__(batch: tuple[Sequence[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes]], Sequence[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes]], Sequence[DatumMetadata]]) → tuple[Sequence[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes]], Sequence[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes]], Sequence[DatumMetadata]]

Return a batch of augmented images and metadata.

__init__(*, augment: PerturbImage, augment_id: str) → None

Initialize augmentation wrapper.

Args:

augment:

PerturbImage implementation to apply to an image.

augment_id:

Metadata ID for this augmentation.

__subclasshook__()

Abstract classes can override this to customize issubclass().

This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).