JATICDetectionAugmentationWithMetric

class nrtk.interop.maite.interop.object_detection.augmentation.JATICDetectionAugmentationWithMetric(augmentations: Sequence[Augmentation] | None, metric: ImageMetric, augment_id: str)

Implementation of JATIC augmentation wrapper for NRTK’s Image metrics.

Implementation of JATIC augmentation for NRTK metrics operating on a MAITE-protocol compliant object detection dataset.

Parameters

augmentationsOptional[Sequence[Augmentation]]

Optional task-specific sequence of JATIC augmentations to be applied on a given batch.

metricImageMetric

Image metric to be applied for a given image.

metadata: AugmentationMetadata

Metadata for this augmentation.

Methods

__call__(batch: tuple[Sequence[ArrayLike], Sequence[ObjectDetectionTarget], Sequence[DatumMetadata]]) → tuple[Sequence[ArrayLike], Sequence[ObjectDetectionTarget], Sequence[NRTKDatumMetadata]]

Compute a specified image metric on the given batch.

__init__(augmentations: Sequence[Augmentation] | None, metric: ImageMetric, augment_id: str) → None

Initialize augmentation with metric wrapper

__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).