org.apache.tika.detect

Class NNTrainedModel

java.lang.Object

org.apache.tika.detect.TrainedModel

org.apache.tika.detect.NNTrainedModel

public class NNTrainedModel
extends TrainedModel

Field Summary

Fields

Modifier and Type	Field and Description
private int	numOfHidden
private int	numOfInputs
private int	numOfOutputs
private float[][]	Theta1
private float[][]	Theta2

Constructor Summary

Constructors

Constructor and Description
NNTrainedModel(int nInput, int nHidden, int nOutput, float[] nn_params)

Method Summary

Modifier and Type	Method and Description
private void	populateThetas(float[] nn_params)
double	predict(double[] unseen)
float	predict(float[] unseen) The given input vector of unseen is m=(256 + 1) * n= 1 this returns a prediction probability

Methods inherited from class java.lang.Object

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

Field Detail

numOfInputs

private int numOfInputs

numOfHidden

private int numOfHidden

numOfOutputs

private int numOfOutputs

Theta1

private float[][] Theta1

Theta2

private float[][] Theta2

Constructor Detail

NNTrainedModel

public NNTrainedModel(int nInput,
                      int nHidden,
                      int nOutput,
                      float[] nn_params)

Method Detail

populateThetas

private void populateThetas(float[] nn_params)

predict

public double predict(double[] unseen)

Specified by:

predict in class TrainedModel

predict

public float predict(float[] unseen)

The given input vector of unseen is m=(256 + 1) * n= 1 this returns a prediction probability

Specified by:

predict in class TrainedModel