public class BatchedInferenceObservable extends BasicInferenceObservable implements InferenceObservable
exception| Constructor and Description |
|---|
BatchedInferenceObservable() |
| Modifier and Type | Method and Description |
|---|---|
void |
addInput(INDArray[] input,
INDArray[] inputMasks) |
int |
getCounter() |
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 List<INDArray[]> |
getOutputs()
PLEASE NOTE: This method is for tests only
|
boolean |
isLocked() |
protected void |
setCounter(int value) |
void |
setOutputBatches(List<INDArray[]> output) |
void |
setPosition(int pos) |
addInput, checkOutputException, setOutputExceptionaddObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChangedclone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitaddInput, addObserver, setOutputExceptionpublic void addInput(INDArray[] input, INDArray[] inputMasks)
addInput in interface InferenceObservableaddInput in class BasicInferenceObservablepublic List<Pair<INDArray[],INDArray[]>> getInputBatches()
InferenceObservablegetInputBatches in interface InferenceObservablegetInputBatches in class BasicInferenceObservablepublic void setOutputBatches(List<INDArray[]> output)
setOutputBatches in interface InferenceObservablesetOutputBatches in class BasicInferenceObservableprotected List<INDArray[]> getOutputs()
protected void setCounter(int value)
public void setPosition(int pos)
public int getCounter()
public boolean isLocked()
public INDArray[] getOutput()
getOutput in interface InferenceObservablegetOutput in class BasicInferenceObservableCopyright © 2020. All rights reserved.