org.deeplearning4j.spark.impl.graph.scoring

Class CGVaeReconstructionErrorWithKeyFunction<K>

java.lang.Object

org.deeplearning4j.spark.impl.common.score.BaseVaeScoreWithKeyFunctionAdapter<K>

org.deeplearning4j.spark.impl.graph.scoring.CGVaeReconstructionErrorWithKeyFunction<K>

All Implemented Interfaces:

java.io.Serializable, org.datavec.spark.functions.FlatMapFunctionAdapter<java.util.Iterator<scala.Tuple2<K,org.nd4j.linalg.api.ndarray.INDArray>>,scala.Tuple2<K,java.lang.Double>>

public class CGVaeReconstructionErrorWithKeyFunction<K>
extends BaseVaeScoreWithKeyFunctionAdapter<K>

Function to calculate the reconstruction error for a variational autoencoder, that is the first layer in a ComputationGraph.
Note that the VAE must be using a loss function, not a ReconstructionDistribution
Also note that scoring is batched for computational efficiency.

See Also:

CGVaeReconstructionProbWithKeyFunction, Serialized Form

Field Summary

Fields inherited from class org.deeplearning4j.spark.impl.common.score.BaseVaeScoreWithKeyFunctionAdapter

jsonConfig, params

Constructor Summary

Constructors

Constructor and Description
CGVaeReconstructionErrorWithKeyFunction(org.apache.spark.broadcast.Broadcast<org.nd4j.linalg.api.ndarray.INDArray> params, org.apache.spark.broadcast.Broadcast<java.lang.String> jsonConfig, int batchSize)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	computeScore(VariationalAutoencoder vae, org.nd4j.linalg.api.ndarray.INDArray toScore)
VariationalAutoencoder	getVaeLayer()

Methods inherited from class org.deeplearning4j.spark.impl.common.score.BaseVaeScoreWithKeyFunctionAdapter

call

Methods inherited from class java.lang.Object

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

Constructor Detail

CGVaeReconstructionErrorWithKeyFunction

public CGVaeReconstructionErrorWithKeyFunction(org.apache.spark.broadcast.Broadcast<org.nd4j.linalg.api.ndarray.INDArray> params,
                                               org.apache.spark.broadcast.Broadcast<java.lang.String> jsonConfig,
                                               int batchSize)

Parameters:

params - MultiLayerNetwork parameters

jsonConfig - MultiLayerConfiguration, as json

batchSize - Batch size to use when scoring

Method Detail

getVaeLayer

public VariationalAutoencoder getVaeLayer()

Specified by:

getVaeLayer in class BaseVaeScoreWithKeyFunctionAdapter<K>

computeScore

public org.nd4j.linalg.api.ndarray.INDArray computeScore(VariationalAutoencoder vae,
                                                         org.nd4j.linalg.api.ndarray.INDArray toScore)

Specified by:

computeScore in class BaseVaeScoreWithKeyFunctionAdapter<K>