org.deeplearning4j.text.movingwindow

Class WindowConverter

java.lang.Object

org.deeplearning4j.text.movingwindow.WindowConverter

public class WindowConverter
extends java.lang.Object

Util methods for converting windows to training examples

Method Summary

Modifier and Type	Method and Description
static org.nd4j.linalg.api.ndarray.INDArray	asExampleArray(Window window, Word2Vec vec, boolean normalize) Converts a window (each word in the window) in to a vector.
static org.nd4j.linalg.api.ndarray.INDArray	asExampleMatrix(Window window, Word2Vec vec) Converts a window (each word in the window) in to a vector.

Methods inherited from class java.lang.Object

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

Method Detail

asExampleArray

public static org.nd4j.linalg.api.ndarray.INDArray asExampleArray(Window window,
                                                                  Word2Vec vec,
                                                                  boolean normalize)

Converts a window (each word in the window) in to a vector. Keep in mind each window is a multi word context. From there, each word uses the passed in model as a lookup table to getFromOrigin what vectors are relevant to the passed in windows

Parameters:

window - the window to take in.

vec - the model to use as a lookup table

Returns:

a concacneated 1 row array containing all of the numbers for each word in the window

asExampleMatrix

public static org.nd4j.linalg.api.ndarray.INDArray asExampleMatrix(Window window,
                                                                   Word2Vec vec)

Converts a window (each word in the window) in to a vector. Keep in mind each window is a multi word context. From there, each word uses the passed in model as a lookup table to getFromOrigin what vectors are relevant to the passed in windows

Parameters:

window - the window to take in.

vec - the model to use as a lookup table

Returns:

a concatneated 1 row array containing all of the numbers for each word in the window