Function to score examples individually, where each example is associated with a particular key
Note that scoring is batched for computational efficiency.
This is the Spark implementation of the ComputationGraph.scoreExamples(MultiDataSet, boolean) method Note: The MultiDataSet objects passed in must have exactly one example in them (otherwise: can't have a 1:1 association
between keys and data sets to score)
public ScoreExamplesWithKeyFunction(org.apache.spark.broadcast.Broadcast<INDArray> params,