Pool

class deeptrack.math.Pool(pooling_function: Callable, ksize: int | Callable[[...], int] = 3, **kwargs)

Bases: Feature

Downsamples the image by applying a function to local regions of the image.

Parameters

pooling_functionfunction

A function that is applied to each local region of the image. DOES NOT NEED TO BE WRAPPED IN A ANOTHER FUNCTIOn. Must implement the axis argument. Examples include np.mean, np.max, np.min, etc.

ksizeint

Size of the pooling kernel.

cvalnumber

Value to pad edges with if necessary.

func_kwargsdict

Additional parameters sent to the pooling function.

Methods Summary

get(image, ksize, **kwargs)

Transform an image [abstract method].

Methods Documentation

get(image, ksize, **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.