Package org.deeplearning4j.parallelism

Class InplaceParallelInference

java.lang.Object

org.deeplearning4j.parallelism.ParallelInference

org.deeplearning4j.parallelism.InplaceParallelInference

public class InplaceParallelInference
extends ParallelInference

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
protected static class	InplaceParallelInference.ModelHolder
protected static class	InplaceParallelInference.ModelSelector

Nested classes/interfaces inherited from class org.deeplearning4j.parallelism.ParallelInference

ParallelInference.Builder, ParallelInference.ObservablesProvider

Field Summary

Fields

Modifier and Type	Field	Description
protected List<InplaceParallelInference.ModelHolder>	holders
protected Object	locker
protected InplaceParallelInference.ModelSelector	selector

Fields inherited from class org.deeplearning4j.parallelism.ParallelInference

batchLimit, DEFAULT_BATCH_LIMIT, DEFAULT_INFERENCE_MODE, DEFAULT_NUM_WORKERS, DEFAULT_QUEUE_LIMIT, inferenceMode, loadBalanceMode, model, nanos, queueLimit, workers

Constructor Summary

Constructors

Constructor	Description
InplaceParallelInference()

Method Summary

Modifier and Type	Method	Description
protected org.deeplearning4j.nn.api.Model[]	getCurrentModelsFromWorkers()	This method returns Models used in workers at this moment PLEASE NOTE: This method is NOT thread safe, and should NOT be used anywhere but tests
protected void	init()
<T> T	output(@NonNull org.deeplearning4j.nn.api.ModelAdapter<T> adapter, org.nd4j.linalg.api.ndarray.INDArray[] input, org.nd4j.linalg.api.ndarray.INDArray[] inputMasks, org.nd4j.linalg.api.ndarray.INDArray[] labelsMasks)	This method does forward pass and returns output provided by OutputAdapter
org.nd4j.linalg.api.ndarray.INDArray[]	output(org.nd4j.linalg.api.ndarray.INDArray[] input, org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)	Generate predictions/outputs from the network, optionally using input masks for predictions
void	updateModel(@NonNull org.deeplearning4j.nn.api.Model model)	This method allows to update Model used for inference in runtime, without queue reset

Methods inherited from class org.deeplearning4j.parallelism.ParallelInference

getWorkerCounter, output, output, output, output, output, output, output, output, shutdown

Methods inherited from class java.lang.Object

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

Field Detail

holders

protected List<InplaceParallelInference.ModelHolder> holders

selector

protected InplaceParallelInference.ModelSelector selector

locker

protected final Object locker

Constructor Detail

InplaceParallelInference

public InplaceParallelInference()

Method Detail

init

protected void init()

Overrides:

init in class ParallelInference

updateModel

public void updateModel(@NonNull
                        @NonNull org.deeplearning4j.nn.api.Model model)

Description copied from class: ParallelInference

This method allows to update Model used for inference in runtime, without queue reset

Overrides:

updateModel in class ParallelInference

getCurrentModelsFromWorkers

protected org.deeplearning4j.nn.api.Model[] getCurrentModelsFromWorkers()

Description copied from class: ParallelInference

This method returns Models used in workers at this moment PLEASE NOTE: This method is NOT thread safe, and should NOT be used anywhere but tests

Overrides:

getCurrentModelsFromWorkers in class ParallelInference

Returns:

output

public org.nd4j.linalg.api.ndarray.INDArray[] output(org.nd4j.linalg.api.ndarray.INDArray[] input,
                                                     org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)

Description copied from class: ParallelInference

Generate predictions/outputs from the network, optionally using input masks for predictions

Overrides:

output in class ParallelInference

Parameters:

input - Input to the network

inputMasks - Input masks for the network. May be null.

Returns:

Output from the network

output

public <T> T output(@NonNull
                    @NonNull org.deeplearning4j.nn.api.ModelAdapter<T> adapter,
                    org.nd4j.linalg.api.ndarray.INDArray[] input,
                    org.nd4j.linalg.api.ndarray.INDArray[] inputMasks,
                    org.nd4j.linalg.api.ndarray.INDArray[] labelsMasks)

This method does forward pass and returns output provided by OutputAdapter

Type Parameters:

T -

Parameters:

adapter -

input -

inputMasks -

Returns: