Package ai.djl.modality.cv.output

Class DetectedObjects

java.lang.Object

ai.djl.modality.Classifications

ai.djl.modality.cv.output.DetectedObjects

All Implemented Interfaces:

BytesSupplier, ai.djl.util.JsonSerializable, java.io.Serializable

public class DetectedObjects
extends Classifications

A class representing the detected objects results for a single image in an Application.CV.OBJECT_DETECTION case.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	DetectedObjects.DetectedObject	A DetectedObject represents a single potential detected Object for an image.

Nested classes/interfaces inherited from class ai.djl.modality.Classifications

Classifications.Classification, Classifications.ClassificationsSerializer

Field Summary

Fields inherited from class ai.djl.modality.Classifications

classNames, probabilities

Constructor Summary

Constructors

Constructor	Description
DetectedObjects(java.util.List<java.lang.String> classNames, java.util.List<java.lang.Double> probabilities, java.util.List<BoundingBox> boundingBoxes)	Constructs a DetectedObjects, usually during post-processing.

Method Summary

Modifier and Type	Method	Description
int	getNumberOfObjects()	Returns the number of objects found in an image.
<T extends Classifications.Classification> T	item(int index)	Returns the item at a given index based on the order used to construct the Classifications.
java.lang.String	toJson()

Methods inherited from class ai.djl.modality.Classifications

best, get, getAsString, items, setTopK, toByteBuffer, topK, topK, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface ai.djl.ndarray.BytesSupplier

getAsBytes, getAsObject

Constructor Detail

DetectedObjects

public DetectedObjects(java.util.List<java.lang.String> classNames,
                       java.util.List<java.lang.Double> probabilities,
                       java.util.List<BoundingBox> boundingBoxes)

Constructs a DetectedObjects, usually during post-processing.

All three inputs(classNames, probabilities, boundingBoxes) should be parallel lists.

Parameters:

classNames - the names of the objects that were detected

probabilities - the probability of the objects that were detected

boundingBoxes - the bounding boxes of the objects that were detected

Method Detail

item

public <T extends Classifications.Classification> T item(int index)

Returns the item at a given index based on the order used to construct the Classifications.

Overrides:

item in class Classifications

Type Parameters:

T - the type of classification item for the task

Parameters:

index - the index of the item to return

Returns:

the item at the given index, equivalent to classifications.items().get(index)

getNumberOfObjects

public int getNumberOfObjects()

Returns the number of objects found in an image.

Returns:

the number of objects found in an image

toJson

public java.lang.String toJson()

Specified by:

toJson in interface ai.djl.util.JsonSerializable

Overrides:

toJson in class Classifications