Class Cnn3DToFeedForwardPreProcessor
- java.lang.Object
-
- org.deeplearning4j.nn.conf.preprocessor.Cnn3DToFeedForwardPreProcessor
-
- All Implemented Interfaces:
Serializable
,Cloneable
,InputPreProcessor
public class Cnn3DToFeedForwardPreProcessor extends Object implements InputPreProcessor
- See Also:
- Serialized Form
-
-
Field Summary
Fields Modifier and Type Field Description protected long
inputDepth
protected long
inputHeight
protected long
inputWidth
protected boolean
isNCDHW
protected long
numChannels
-
Constructor Summary
Constructors Constructor Description Cnn3DToFeedForwardPreProcessor()
Cnn3DToFeedForwardPreProcessor(int inputDepth, int inputHeight, int inputWidth)
Cnn3DToFeedForwardPreProcessor(int inputDepth, int inputHeight, int inputWidth, int numChannels, Convolution3D.DataFormat dataFormat)
Cnn3DToFeedForwardPreProcessor(long inputDepth, long inputHeight, long inputWidth, long numChannels, boolean isNCDHW)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description INDArray
backprop(INDArray epsilons, int miniBatchSize, LayerWorkspaceMgr workspaceMgr)
Reverse the preProcess during backprop.Cnn3DToFeedForwardPreProcessor
clone()
Pair<INDArray,MaskState>
feedForwardMaskArray(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?INDArray
preProcess(INDArray input, int miniBatchSize, LayerWorkspaceMgr workspaceMgr)
Pre preProcess input/activations for a multi layer network
-
-
-
Constructor Detail
-
Cnn3DToFeedForwardPreProcessor
public Cnn3DToFeedForwardPreProcessor(long inputDepth, long inputHeight, long inputWidth, long numChannels, boolean isNCDHW)
- Parameters:
inputDepth
- input channelsinputHeight
- input heightinputWidth
- input widthnumChannels
- input channelsisNCDHW
- boolean to indicate data format, i.e. channels first (NCDHW) vs. channels last (NDHWC)
-
Cnn3DToFeedForwardPreProcessor
public Cnn3DToFeedForwardPreProcessor(int inputDepth, int inputHeight, int inputWidth)
-
Cnn3DToFeedForwardPreProcessor
public Cnn3DToFeedForwardPreProcessor(int inputDepth, int inputHeight, int inputWidth, int numChannels, Convolution3D.DataFormat dataFormat)
-
Cnn3DToFeedForwardPreProcessor
public Cnn3DToFeedForwardPreProcessor()
-
-
Method Detail
-
preProcess
public INDArray preProcess(INDArray input, int miniBatchSize, LayerWorkspaceMgr workspaceMgr)
Description copied from interface:InputPreProcessor
Pre preProcess input/activations for a multi layer network- Specified by:
preProcess
in interfaceInputPreProcessor
- Parameters:
input
- the input to pre preProcessminiBatchSize
- Minibatch sizeworkspaceMgr
- Workspace manager- Returns:
- the processed input. Note that the returned array should be placed in the
ArrayType.ACTIVATIONS
workspace via the workspace manager
-
backprop
public INDArray backprop(INDArray epsilons, int miniBatchSize, LayerWorkspaceMgr workspaceMgr)
Description copied from interface:InputPreProcessor
Reverse the preProcess during backprop. Process Gradient/epsilons before passing them to the layer below.- Specified by:
backprop
in interfaceInputPreProcessor
- Parameters:
epsilons
- which is a pair of the gradient and epsilonminiBatchSize
- Minibatch sizeworkspaceMgr
- Workspace manager- Returns:
- the reverse of the pre preProcess step (if any). Note that the returned array should be
placed in
ArrayType.ACTIVATION_GRAD
workspace via the workspace manager
-
clone
public Cnn3DToFeedForwardPreProcessor clone()
- Specified by:
clone
in interfaceInputPreProcessor
- Overrides:
clone
in classObject
-
getOutputType
public InputType getOutputType(InputType inputType)
Description copied from interface:InputPreProcessor
For a given type of input to this preprocessor, what is the type of the output?- Specified by:
getOutputType
in interfaceInputPreProcessor
- Parameters:
inputType
- Type of input for the preprocessor- Returns:
- Type of input after applying the preprocessor
-
feedForwardMaskArray
public Pair<INDArray,MaskState> feedForwardMaskArray(INDArray maskArray, MaskState currentMaskState, int minibatchSize)
- Specified by:
feedForwardMaskArray
in interfaceInputPreProcessor
-
-