Reuse

class deeptrack.augmentations.Reuse(feature, uses=2, storage=1, **kwargs)

Bases: Feature

Acts like cache.

Reuse stores the output of a feature and reuses it for subsequent calls, even if it is updated. This is can be used after a time-consuming feature to augment the output of the feature without recalculating it. For example:

pipeline = dt.Reuse(pipeline, uses=2) >> dt.FlipLR()

Here, the output of pipeline is used twice, augmented randomly by FlipLR.

Parameters

featureFeature

The feature to reuse.

usesint

Number of each stored image uses before evaluating feature. Note that the actual total number of uses is uses * storage. Should be constant.

storageint

Number of instances of the output of feature to cache. Should be constant.

Methods Summary

get(image, uses, storage, **kwargs)

Transform an image [abstract method].

Methods Documentation

get(image, uses, storage, **kwargs)

Transform an image [abstract method].

Abstract method that defines how the feature transforms the input. The current value of all properties will be passed as keyword arguments.

Parameters

image‘Image’ or List[‘Image’]

The Image or list of images to transform.

**kwargsDict[str, Any]

The current value of all properties in properties as well as any global arguments.

Returns

‘Image’ or List[‘Image’]

The transformed image or list of images.

Raises

NotImplementedError

Must be overridden by subclasses.