BatchedInferenceObservable

java.lang.Object
- java.util.Observable
- - org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable
  - - org.deeplearning4j.parallelism.inference.observers.BatchedInferenceObservable

All Implemented Interfaces:

InferenceObservable
```
public class BatchedInferenceObservable
extends BasicInferenceObservable
implements InferenceObservable
```
This class holds reference input, and implements second use case: BATCHED inference

Field Summary
- Fields inherited from class org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable
  exception

Constructor Summary

Constructors
Constructor and Description

BatchedInferenceObservable()

Constructors
Constructor and Description
`BatchedInferenceObservable()`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`void`	`addInput(INDArray[] input, INDArray[] inputMasks)`
`int`	`getCounter()`
`java.util.List<Pair<INDArray[],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).
`INDArray[]`	`getOutput()`
`protected java.util.List<INDArray[]>`	`getOutputs()` PLEASE NOTE: This method is for tests only
`boolean`	`isLocked()`
`protected void`	`setCounter(int value)`
`void`	`setOutputBatches(java.util.List<INDArray[]> output)`
`void`	`setPosition(int pos)`

Methods inherited from class org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable
addInput, checkOutputException, setOutputException

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
addInput, addObserver, setOutputException

- Constructor Detail
  - BatchedInferenceObservable
```
public BatchedInferenceObservable()
```
- Method Detail
  - addInput
```
public void addInput(INDArray[] input,
                     INDArray[] inputMasks)
```
    Specified by:
    
    addInput in interface InferenceObservable
    
    Overrides:
    
    addInput in class BasicInferenceObservable
  - getInputBatches
```
public java.util.List<Pair<INDArray[],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
    
    Overrides:
    
    getInputBatches in class BasicInferenceObservable
    
    Returns:
    
    List of pairs of input arrays and input mask arrays. Input mask arrays may be null.
  - setOutputBatches
```
public void setOutputBatches(java.util.List<INDArray[]> output)
```
    Specified by:
    
    setOutputBatches in interface InferenceObservable
    
    Overrides:
    
    setOutputBatches in class BasicInferenceObservable
  - getOutputs
```
protected java.util.List<INDArray[]> getOutputs()
```
    PLEASE NOTE: This method is for tests only
    
    Returns:
  - setCounter
```
protected void setCounter(int value)
```
  - setPosition
```
public void setPosition(int pos)
```
  - getCounter
```
public int getCounter()
```
  - isLocked
```
public boolean isLocked()
```
  - getOutput
```
public INDArray[] getOutput()
```
    Specified by:
    
    getOutput in interface InferenceObservable
    
    Overrides:
    
    getOutput in class BasicInferenceObservable

Class BatchedInferenceObservable

Field Summary

Fields inherited from class org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable

Constructor Summary

Method Summary

Methods inherited from class org.deeplearning4j.parallelism.inference.observers.BasicInferenceObservable

Methods inherited from class java.util.Observable

Methods inherited from class java.lang.Object

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

Constructor Detail

BatchedInferenceObservable

Method Detail

addInput

getInputBatches

setOutputBatches

getOutputs

setCounter

setPosition

getCounter

isLocked

getOutput