ai.djl.training.metrics

Class SingleShotDetectionAccuracy

java.lang.Object

ai.djl.training.metrics.TrainingMetric

ai.djl.training.metrics.Accuracy

ai.djl.training.metrics.SingleShotDetectionAccuracy

All Implemented Interfaces:

java.lang.Cloneable

public class SingleShotDetectionAccuracy
extends Accuracy

SingleShotDetectionAccuracy is an implementation of Accuracy. It is used while training a Single Shot Detection (SSD) model for object detection. It uses the targets computed by MultiBoxTarget, and computes the class prediction accuracy against the computed targets.

Field Summary

Fields inherited from class ai.djl.training.metrics.Accuracy

axis, index

Constructor Summary

Constructors

Constructor and Description
SingleShotDetectionAccuracy(java.lang.String name) Creates a new instance of SingleShotDetectionAccuracy with the given name.

Method Summary

Modifier and Type	Method and Description
void	update(NDList labels, NDList predictions) Computes and updates the training metrics based on the labels and predictions.

Methods inherited from class ai.djl.training.metrics.Accuracy

addCorrectInstances, addTotalInstances, getValue, reset, update

Methods inherited from class ai.djl.training.metrics.TrainingMetric

checkLabelShapes, checkLabelShapes, duplicate, getName

Methods inherited from class java.lang.Object

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

Constructor Detail

SingleShotDetectionAccuracy

public SingleShotDetectionAccuracy(java.lang.String name)

Creates a new instance of SingleShotDetectionAccuracy with the given name.

Parameters:

name - the name given to the accuracy

Method Detail

update

public void update(NDList labels,
                   NDList predictions)

Description copied from class: Accuracy

Computes and updates the training metrics based on the labels and predictions.

Overrides:

update in class Accuracy

Parameters:

labels - a NDList of labels

predictions - a NDList of predictions