Package org.deeplearning4j.parallelism.inference.observers

Class BasicInferenceObservable

java.lang.Object

java.util.Observable

org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable

All Implemented Interfaces:

InferenceObservable

Direct Known Subclasses:

BatchedInferenceObservable

public class BasicInferenceObservable
extends Observable
implements InferenceObservable

Field Summary

Fields

Modifier and Type	Field	Description
protected Exception	exception

Constructor Summary

Constructors

Constructor	Description
BasicInferenceObservable(org.nd4j.linalg.api.ndarray.INDArray... inputs)
BasicInferenceObservable(org.nd4j.linalg.api.ndarray.INDArray[] inputs, org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)

Method Summary

Modifier and Type	Method	Description
void	addInput(@NonNull org.nd4j.linalg.api.ndarray.INDArray... input)
void	addInput(@NonNull org.nd4j.linalg.api.ndarray.INDArray[] input, org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)
protected void	checkOutputException()
List<org.nd4j.common.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray[],org.nd4j.linalg.api.ndarray.INDArray[]>>	getInputBatches()	Get input batches - and their associated input mask arrays, if any Note that usually the returned list will be of size 1 - however, in the batched case, not all inputs can actually be batched (variable size inputs to fully convolutional net, for example).
org.nd4j.linalg.api.ndarray.INDArray[]	getOutput()
void	setOutputBatches(@NonNull List<org.nd4j.linalg.api.ndarray.INDArray[]> output)
void	setOutputException(Exception exception)

Methods inherited from class java.util.Observable

addObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChanged

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.parallelism.inference.InferenceObservable

addObserver

Field Detail

exception

protected Exception exception

Constructor Detail

BasicInferenceObservable

public BasicInferenceObservable(org.nd4j.linalg.api.ndarray.INDArray... inputs)

BasicInferenceObservable

public BasicInferenceObservable(org.nd4j.linalg.api.ndarray.INDArray[] inputs,
                                org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)

Method Detail

addInput

public void addInput(@NonNull
                     @NonNull org.nd4j.linalg.api.ndarray.INDArray... input)

Specified by:

addInput in interface InferenceObservable

addInput

public void addInput(@NonNull
                     @NonNull org.nd4j.linalg.api.ndarray.INDArray[] input,
                     org.nd4j.linalg.api.ndarray.INDArray[] inputMasks)

Specified by:

addInput in interface InferenceObservable

setOutputBatches

public void setOutputBatches(@NonNull
                             @NonNull List<org.nd4j.linalg.api.ndarray.INDArray[]> output)

Specified by:

setOutputBatches in interface InferenceObservable

getInputBatches

public List<org.nd4j.common.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray[],org.nd4j.linalg.api.ndarray.INDArray[]>> getInputBatches()

Description copied from interface: InferenceObservable

Get input batches - and their associated input mask arrays, if any
Note that usually the returned list will be of size 1 - however, in the batched case, not all inputs can actually be batched (variable size inputs to fully convolutional net, for example). In these "can't batch" cases, multiple input batches will be returned, to be processed

Specified by:

getInputBatches in interface InferenceObservable

Returns:

List of pairs of input arrays and input mask arrays. Input mask arrays may be null.

setOutputException

public void setOutputException(Exception exception)

Specified by:

setOutputException in interface InferenceObservable

getOutput

public org.nd4j.linalg.api.ndarray.INDArray[] getOutput()

Specified by:

getOutput in interface InferenceObservable

checkOutputException

protected void checkOutputException()