org.openimaj.ml.annotation

Class BatchAnnotator<OBJECT,ANNOTATION>

java.lang.Object

org.openimaj.ml.annotation.AbstractAnnotator<OBJECT,ANNOTATION>

org.openimaj.ml.annotation.BatchAnnotator<OBJECT,ANNOTATION>

Type Parameters:

OBJECT - Type of object being annotated

ANNOTATION - Type of annotation

All Implemented Interfaces:

Classifier<ANNOTATION,OBJECT>, Annotator<OBJECT,ANNOTATION>, BatchTrainer<Annotated<OBJECT,ANNOTATION>>

Direct Known Subclasses:

DenseLinearTransformAnnotator, IndependentPriorRandomAnnotator, LiblinearAnnotator, LinearSVMAnnotator, ModelAnnotator, SVMAnnotator, UniformRandomAnnotator

public abstract class BatchAnnotator<OBJECT,ANNOTATION>
extends AbstractAnnotator<OBJECT,ANNOTATION>
implements BatchTrainer<Annotated<OBJECT,ANNOTATION>>

An Annotator that is trained in "batch" mode; all training examples are presented at once. Calling the BatchTrainer.train(List) method more than once will cause the internal model to be re-initialised using the new data. If you want to implement an Annotator that can be updated, implement the IncrementalAnnotator interface instead.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk)

Constructor Summary

Constructors

Constructor and Description
BatchAnnotator()

Method Summary

Modifier and Type	Method and Description
void	train(GroupedDataset<ANNOTATION,? extends ListDataset<OBJECT>,OBJECT> dataset) Train the annotator with the given grouped dataset.

Methods inherited from class org.openimaj.ml.annotation.AbstractAnnotator

classify

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.openimaj.ml.training.BatchTrainer

train

Methods inherited from interface org.openimaj.ml.annotation.Annotator

annotate, getAnnotations

Constructor Detail

BatchAnnotator

public BatchAnnotator()

Method Detail

train

public void train(GroupedDataset<ANNOTATION,? extends ListDataset<OBJECT>,OBJECT> dataset)

Train the annotator with the given grouped dataset. Internally, the dataset is converted to a list containing exactly one reference to each object in the dataset with (potentially) multiple annotations.

Parameters:

dataset - the dataset to train on