org.deeplearning4j.spark.impl.multilayer.scoring

Class VaeReconstructionErrorWithKeyFunction<K>

java.lang.Object

org.deeplearning4j.spark.util.BasePairFlatMapFunctionAdaptee<java.util.Iterator<scala.Tuple2<K,org.nd4j.linalg.api.ndarray.INDArray>>,K,java.lang.Double>

org.deeplearning4j.spark.impl.multilayer.scoring.VaeReconstructionErrorWithKeyFunction<K>

All Implemented Interfaces:

java.io.Serializable, org.apache.spark.api.java.function.PairFlatMapFunction<java.util.Iterator<scala.Tuple2<K,org.nd4j.linalg.api.ndarray.INDArray>>,K,java.lang.Double>

public class VaeReconstructionErrorWithKeyFunction<K>
extends BasePairFlatMapFunctionAdaptee<java.util.Iterator<scala.Tuple2<K,org.nd4j.linalg.api.ndarray.INDArray>>,K,java.lang.Double>

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

See Also:

VaeReconstructionProbWithKeyFunction, Serialized Form

Field Summary

Fields inherited from class org.deeplearning4j.spark.util.BasePairFlatMapFunctionAdaptee

adapter

Constructor Summary

Constructors

Constructor and Description
VaeReconstructionErrorWithKeyFunction(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

Methods inherited from class org.deeplearning4j.spark.util.BasePairFlatMapFunctionAdaptee

call

Methods inherited from class java.lang.Object

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

Constructor Detail

VaeReconstructionErrorWithKeyFunction

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