org.deeplearning4j.nn.conf.preprocessor

Class ReshapePreProcessor

java.lang.Object

org.deeplearning4j.nn.conf.preprocessor.BaseInputPreProcessor

org.deeplearning4j.nn.conf.preprocessor.ReshapePreProcessor

All Implemented Interfaces:

Serializable, Cloneable, InputPreProcessor

Deprecated.

@Deprecated
public class ReshapePreProcessor
extends BaseInputPreProcessor

Reshape post processor.
Used to reshape activations on forward pass.
Also (optionally, if fromShape != null) used to reshape, weights*deltas during backward pass. Otherwise, no changes are made during backward pass

Author:

Adam Gibson

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
ReshapePreProcessor(int... toShape) Deprecated.
ReshapePreProcessor(int[] fromShape, int[] toShape) Deprecated.
ReshapePreProcessor(int[] fromShape, int[] toShape, boolean dynamic) Deprecated.

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	backprop(org.nd4j.linalg.api.ndarray.INDArray output, int miniBatchSize) Deprecated. Reverse the preProcess during backprop.
ReshapePreProcessor	clone() Deprecated.
InputType	getOutputType(InputType inputType) Deprecated. 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) Deprecated. Pre preProcess input/activations for a multi layer network

Methods inherited from class java.lang.Object

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

Constructor Detail

ReshapePreProcessor

public ReshapePreProcessor(int[] fromShape,
                           int[] toShape,
                           boolean dynamic)

Deprecated.

Parameters:

fromShape - May be null. If null: no change/op during backward pass.

toShape - The shape that activations are reshaped to

dynamic - Infer the number of examples or not Otherwise fromShape is the shape that epsilons (weights*deltas or equiv.) are reshaped to by backprop(...)

ReshapePreProcessor

public ReshapePreProcessor(int... toShape)

Deprecated.

ReshapePreProcessor

public ReshapePreProcessor(int[] fromShape,
                           int[] toShape)

Deprecated.

Method Detail

preProcess

public org.nd4j.linalg.api.ndarray.INDArray preProcess(org.nd4j.linalg.api.ndarray.INDArray input,
                                                       int miniBatchSize)

Deprecated.

Description copied from interface: InputPreProcessor

Pre preProcess input/activations for a multi layer network

Parameters:

input - the input to pre preProcess

Returns:

the processed input

backprop

public org.nd4j.linalg.api.ndarray.INDArray backprop(org.nd4j.linalg.api.ndarray.INDArray output,
                                                     int miniBatchSize)

Deprecated.

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

Returns:

the reverse of the pre preProcess step (if any)

clone

public ReshapePreProcessor clone()

Deprecated.

Specified by:

clone in interface InputPreProcessor

Overrides:

clone in class BaseInputPreProcessor

getOutputType

public InputType getOutputType(InputType inputType)

Deprecated.

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