org.deeplearning4j.optimize.listeners

Class EvaluativeListener

java.lang.Object

org.deeplearning4j.optimize.api.BaseTrainingListener

org.deeplearning4j.optimize.listeners.EvaluativeListener

All Implemented Interfaces:

TrainingListener

public class EvaluativeListener
extends BaseTrainingListener

This TrainingListener implementation provides simple way for model evaluation during training. It can be launched every Xth Iteration/Epoch, depending on frequency and InvocationType constructor arguments

Author:

raver119@gmail.com

Field Summary

Fields

Modifier and Type	Field and Description
protected EvaluationCallback	callback This callback will be invoked after evaluation finished
protected org.nd4j.linalg.dataset.DataSet	ds
protected org.nd4j.linalg.dataset.api.iterator.DataSetIterator	dsIterator
protected IEvaluation[]	evaluations
protected int	frequency
protected AtomicLong	invocationCount
protected InvocationType	invocationType
protected ThreadLocal<AtomicLong>	iterationCount
protected org.nd4j.linalg.dataset.MultiDataSet	mds
protected org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator	mdsIterator

Constructor Summary

Constructors

Constructor and Description
EvaluativeListener(org.nd4j.linalg.dataset.DataSet dataSet, int frequency, InvocationType type)
EvaluativeListener(org.nd4j.linalg.dataset.DataSet dataSet, int frequency, InvocationType type, IEvaluation... evaluations)
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int frequency) Evaluation will be launched after each *frequency* iteration
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int frequency, IEvaluation... evaluations) Evaluation will be launched after each *frequency* iteration
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int frequency, InvocationType type)
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator, int frequency, InvocationType type, IEvaluation... evaluations)
EvaluativeListener(org.nd4j.linalg.dataset.MultiDataSet multiDataSet, int frequency, InvocationType type)
EvaluativeListener(org.nd4j.linalg.dataset.MultiDataSet multiDataSet, int frequency, InvocationType type, IEvaluation... evaluations)
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator, int frequency) Evaluation will be launched after each *frequency* iteration
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator, int frequency, IEvaluation... evaluations) Evaluation will be launched after each *frequency* iteration
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator, int frequency, InvocationType type)
EvaluativeListener(org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator, int frequency, InvocationType type, IEvaluation... evaluations)

Method Summary

Modifier and Type	Method and Description
protected void	evalAtIndex(IEvaluation evaluation, org.nd4j.linalg.api.ndarray.INDArray[] labels, org.nd4j.linalg.api.ndarray.INDArray[] predictions, int index)
protected void	invokeListener(Model model)
void	iterationDone(Model model, int iteration, int epoch) Event listener for each iteration
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, 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, Map<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 class java.lang.Object

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

Field Detail

iterationCount

protected transient ThreadLocal<AtomicLong> iterationCount

frequency

protected int frequency

invocationCount

protected AtomicLong invocationCount

dsIterator

protected transient org.nd4j.linalg.dataset.api.iterator.DataSetIterator dsIterator

mdsIterator

protected transient org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator mdsIterator

ds

protected org.nd4j.linalg.dataset.DataSet ds

mds

protected org.nd4j.linalg.dataset.MultiDataSet mds

evaluations

protected IEvaluation[] evaluations

invocationType

protected InvocationType invocationType

callback

protected transient EvaluationCallback callback

This callback will be invoked after evaluation finished

Constructor Detail

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator,
                          int frequency)

Evaluation will be launched after each *frequency* iteration

Parameters:

iterator -

frequency -

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator,
                          int frequency,
                          @NonNull
                          InvocationType type)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator,
                          int frequency)

Evaluation will be launched after each *frequency* iteration

Parameters:

iterator -

frequency -

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator,
                          int frequency,
                          @NonNull
                          InvocationType type)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator,
                          int frequency,
                          IEvaluation... evaluations)

Evaluation will be launched after each *frequency* iteration

Parameters:

iterator -

frequency -

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.DataSetIterator iterator,
                          int frequency,
                          @NonNull
                          InvocationType type,
                          IEvaluation... evaluations)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator,
                          int frequency,
                          IEvaluation... evaluations)

Evaluation will be launched after each *frequency* iteration

Parameters:

iterator -

frequency -

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.api.iterator.MultiDataSetIterator iterator,
                          int frequency,
                          @NonNull
                          InvocationType type,
                          IEvaluation... evaluations)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.DataSet dataSet,
                          int frequency,
                          @NonNull
                          InvocationType type)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.MultiDataSet multiDataSet,
                          int frequency,
                          @NonNull
                          InvocationType type)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.DataSet dataSet,
                          int frequency,
                          @NonNull
                          InvocationType type,
                          IEvaluation... evaluations)

EvaluativeListener

public EvaluativeListener(@NonNull
                          org.nd4j.linalg.dataset.MultiDataSet multiDataSet,
                          int frequency,
                          @NonNull
                          InvocationType type,
                          IEvaluation... evaluations)

Method Detail

iterationDone

public void iterationDone(Model model,
                          int iteration,
                          int epoch)

Event listener for each iteration

Specified by:

iterationDone in interface TrainingListener

Overrides:

iterationDone in class BaseTrainingListener

Parameters:

model - the model iterating

iteration - the iteration

onEpochStart

public void onEpochStart(Model model)

Description copied from interface: TrainingListener

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

Specified by:

onEpochStart in interface TrainingListener

Overrides:

onEpochStart in class BaseTrainingListener

onEpochEnd

public void onEpochEnd(Model model)

Description copied from interface: TrainingListener

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

Specified by:

onEpochEnd in interface TrainingListener

Overrides:

onEpochEnd in class BaseTrainingListener

onForwardPass

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

Description copied from interface: TrainingListener

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

Specified by:

onForwardPass in interface TrainingListener

Overrides:

onForwardPass in class BaseTrainingListener

Parameters:

model - Model

activations - Layer activations (including input)

onForwardPass

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

Description copied from interface: TrainingListener

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

Specified by:

onForwardPass in interface TrainingListener

Overrides:

onForwardPass in class BaseTrainingListener

Parameters:

model - Model

activations - Layer activations (including input)

onGradientCalculation

public void onGradientCalculation(Model model)

Description copied from interface: TrainingListener

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 TrainingListener.onBackwardPass(Model)

Specified by:

onGradientCalculation in interface TrainingListener

Overrides:

onGradientCalculation in class BaseTrainingListener

Parameters:

model - Model

onBackwardPass

public void onBackwardPass(Model model)

Description copied from interface: TrainingListener

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

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

Specified by:

onBackwardPass in interface TrainingListener

Overrides:

onBackwardPass in class BaseTrainingListener

Parameters:

model - Model

invokeListener

protected void invokeListener(Model model)

evalAtIndex

protected void evalAtIndex(IEvaluation evaluation,
                           org.nd4j.linalg.api.ndarray.INDArray[] labels,
                           org.nd4j.linalg.api.ndarray.INDArray[] predictions,
                           int index)