org.deeplearning4j.optimize.api

Interface TrainingListener

All Superinterfaces:

IterationListener, java.io.Serializable

All Known Subinterfaces:

RoutingIterationListener

All Known Implementing Classes:

BaseStatsListener, HistogramIterationListener, J7StatsListener, StatsListener

public interface TrainingListener
extends IterationListener

TrainingListener: an extension of IterationListener that adds onEpochStart, onEpochEnd, onForwardPass and onBackwardPass methods

Method Summary

Modifier and Type	Method and Description
void	onBackwardPass(Model model) Called once per iteration (backward pass) after gradients have been calculated, and updated Gradients are available via Model.gradient().
void	onEpochEnd(Model model) Called once at the end of each epoch, when using methods such as MultiLayerNetwork.fit(DataSetIterator), ComputationGraph.fit(DataSetIterator) or ComputationGraph.fit(MultiDataSetIterator)
void	onEpochStart(Model model) Called once at the start of each epoch, when using methods such as MultiLayerNetwork.fit(DataSetIterator), ComputationGraph.fit(DataSetIterator) or ComputationGraph.fit(MultiDataSetIterator)
void	onForwardPass(Model model, java.util.List<org.nd4j.linalg.api.ndarray.INDArray> activations) Called once per iteration (forward pass) for activations (usually for a MultiLayerNetwork), only at training time
void	onForwardPass(Model model, java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> activations) Called once per iteration (forward pass) for activations (usually for a ComputationGraph), only at training time
void	onGradientCalculation(Model model) Called once per iteration (backward pass) before the gradients are updated Gradients are available via Model.gradient().

Methods inherited from interface org.deeplearning4j.optimize.api.IterationListener

invoke, invoked, iterationDone

Method Detail

onEpochStart

void onEpochStart(Model model)

Called once at the start of each epoch, when using methods such as MultiLayerNetwork.fit(DataSetIterator), ComputationGraph.fit(DataSetIterator) or ComputationGraph.fit(MultiDataSetIterator)

onEpochEnd

void onEpochEnd(Model model)

Called once at the end of each epoch, when using methods such as MultiLayerNetwork.fit(DataSetIterator), ComputationGraph.fit(DataSetIterator) or ComputationGraph.fit(MultiDataSetIterator)

onForwardPass

void onForwardPass(Model model,
                   java.util.List<org.nd4j.linalg.api.ndarray.INDArray> activations)

Called once per iteration (forward pass) for activations (usually for a MultiLayerNetwork), only at training time

Parameters:

model - Model

activations - Layer activations (including input)

onForwardPass

void onForwardPass(Model model,
                   java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> activations)

Called once per iteration (forward pass) for activations (usually for a ComputationGraph), only at training time

Parameters:

model - Model

activations - Layer activations (including input)

onGradientCalculation

void onGradientCalculation(Model model)

Called once per iteration (backward pass) before the gradients are updated Gradients are available via Model.gradient(). Note that gradients will likely be updated in-place - thus they should be copied or processed synchronously in this method.

For updates (gradients post learning rate/momentum/rmsprop etc) see onBackwardPass(Model)

Parameters:

model - Model

onBackwardPass

void onBackwardPass(Model model)

Called once per iteration (backward pass) after gradients have been calculated, and updated Gradients are available via Model.gradient().

Unlike onGradientCalculation(Model) the gradients at this point will be post-update, rather than raw (pre-update) gradients at that method call.

Parameters:

model - Model