public class CnnToFeedForwardPreProcessor extends java.lang.Object implements InputPreProcessor
Constructor and Description |
---|
CnnToFeedForwardPreProcessor() |
CnnToFeedForwardPreProcessor(int inputHeight,
int inputWidth) |
CnnToFeedForwardPreProcessor(int inputHeight,
int inputWidth,
int numChannels) |
Modifier and Type | Method and Description |
---|---|
org.nd4j.linalg.api.ndarray.INDArray |
backprop(org.nd4j.linalg.api.ndarray.INDArray epsilons,
int miniBatchSize)
Reverse the preProcess during backprop.
|
CnnToFeedForwardPreProcessor |
clone() |
Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> |
feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray,
MaskState currentMaskState,
int minibatchSize) |
InputType |
getOutputType(InputType inputType)
For a given type of input to this preprocessor, what is the type of the output?
|
org.nd4j.linalg.api.ndarray.INDArray |
preProcess(org.nd4j.linalg.api.ndarray.INDArray input,
int miniBatchSize)
Pre preProcess input/activations for a multi layer network
|
public CnnToFeedForwardPreProcessor(int inputHeight, int inputWidth, int numChannels)
inputHeight
- the columnsinputWidth
- the rowsnumChannels
- the channelspublic CnnToFeedForwardPreProcessor(int inputHeight, int inputWidth)
public CnnToFeedForwardPreProcessor()
public org.nd4j.linalg.api.ndarray.INDArray preProcess(org.nd4j.linalg.api.ndarray.INDArray input, int miniBatchSize)
InputPreProcessor
preProcess
in interface InputPreProcessor
input
- the input to pre preProcesspublic org.nd4j.linalg.api.ndarray.INDArray backprop(org.nd4j.linalg.api.ndarray.INDArray epsilons, int miniBatchSize)
InputPreProcessor
backprop
in interface InputPreProcessor
epsilons
- which is a pair of the gradient and epsilonpublic CnnToFeedForwardPreProcessor clone()
clone
in interface InputPreProcessor
clone
in class java.lang.Object
public InputType getOutputType(InputType inputType)
InputPreProcessor
getOutputType
in interface InputPreProcessor
inputType
- Type of input for the preprocessorpublic Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)
feedForwardMaskArray
in interface InputPreProcessor