| Class | Description |
|---|---|
| ArrayPairToPair<K> |
Simple conversion function for SparkComputationGraph
|
| CGVaeReconstructionErrorWithKeyFunction<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 ReconstructionDistributionAlso note that scoring is batched for computational efficiency. |
| CGVaeReconstructionProbWithKeyFunction<K> |
Function to calculate the reconstruction probability for a variational autoencoder, that is the first layer in a
ComputationGraph.
Note that scoring is batched for computational efficiency. |
| GraphFeedForwardWithKeyFunction<K> |
Function to feed-forward examples, and get the network output (for example, class probabilities).
|
| PairToArrayPair<K> |
Simple conversion function for SparkComputationGraph
|
| ScoreExamplesFunction |
Function to score examples individually.
|
| ScoreExamplesWithKeyFunction<K> |
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) methodNote: 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) |
| ScoreFlatMapFunctionCGDataSet |
Function used to score a DataSet using a ComputationGraph
|
| ScoreFlatMapFunctionCGMultiDataSet |
Function used to score a MultiDataSet using a given ComputationGraph
|