Package org.deeplearning4j.preprocessors

Class ReshapePreprocessor

java.lang.Object

org.deeplearning4j.nn.conf.preprocessor.BaseInputPreProcessor

org.deeplearning4j.preprocessors.ReshapePreprocessor

All Implemented Interfaces:

Serializable, Cloneable, InputPreProcessor

public class ReshapePreprocessor
extends BaseInputPreProcessor

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor	Description
ReshapePreprocessor(long[] inputShape, long[] targetShape, boolean hasMiniBatchDimension)
ReshapePreprocessor(long[] inputShape, long[] targetShape, boolean hasMiniBatchDimension, DataFormat dataFormat)

Method Summary

Modifier and Type	Method	Description
INDArray	backprop(INDArray output, int miniBatchSize, LayerWorkspaceMgr workspaceMgr)	Reverse the preProcess during backprop.
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

Methods inherited from class org.deeplearning4j.nn.conf.preprocessor.BaseInputPreProcessor

clone, feedForwardMaskArray

Methods inherited from class java.lang.Object

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

Constructor Detail

ReshapePreprocessor

public ReshapePreprocessor(long[] inputShape,
                           long[] targetShape,
                           boolean hasMiniBatchDimension)

Parameters:

inputShape - Input shape, with or without leading minibatch dimension, depending on value of hasMiniBatchDimension

targetShape - Target shape, with or without leading minibatch dimension, depending on value of hasMiniBatchDimension

hasMiniBatchDimension - If true: shapes should be of the form [minibatch, x, y, ...]; if false: shapes should be of form [x, y, ...]

ReshapePreprocessor

public ReshapePreprocessor(long[] inputShape,
                           long[] targetShape,
                           boolean hasMiniBatchDimension,
                           DataFormat dataFormat)

Parameters:

inputShape - Input shape, with or without leading minibatch dimension, depending on value of hasMiniBatchDimension

targetShape - Target shape, with or without leading minibatch dimension, depending on value of hasMiniBatchDimension

hasMiniBatchDimension - If true: shapes should be of the form [minibatch, x, y, ...]; if false: shapes should be of form [x, y, ...]

dataFormat - May be null. If non-null:

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

Parameters:

input - the input to pre preProcess

miniBatchSize - Minibatch size

workspaceMgr - 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 output,
                         int miniBatchSize,
                         LayerWorkspaceMgr workspaceMgr)

Description copied from interface: InputPreProcessor

Reverse the preProcess during backprop. Process Gradient/epsilons before passing them to the layer below.

Parameters:

output - which is a pair of the gradient and epsilon

miniBatchSize - Minibatch size

workspaceMgr - 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

getOutputType

public InputType getOutputType(InputType inputType)
                        throws InvalidInputTypeException

Description copied from interface: InputPreProcessor

For a given type of input to this preprocessor, what is the type of the output?

Parameters:

inputType - Type of input for the preprocessor

Returns:

Type of input after applying the preprocessor

Throws:

InvalidInputTypeException