org.deeplearning4j.util

Class ConvolutionUtils

java.lang.Object

org.deeplearning4j.util.ConvolutionUtils

public class ConvolutionUtils
extends Object

Convolutional shape utilities

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
static org.nd4j.linalg.api.ndarray.INDArray	adapt2dMask(org.nd4j.linalg.api.ndarray.INDArray mask, org.nd4j.linalg.api.ndarray.INDArray output)
static int[]	effectiveKernelSize(int[] kernel, int[] dilation)
static int[]	getDeconvolutionOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation) Get the output size of a deconvolution operation for given input data.
static int[]	getHeightAndWidth(int[] shape) Get the height and width for an image
static int[]	getHeightAndWidth(NeuralNetConfiguration conf) Get the height and width from the configuration
static int[]	getHWDFromInputType(InputType inputType) Get heigh/width/depth as length 3 int[] from the InputType
static int[]	getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode)
static int[]	getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation) Get the output size (height/width) for the given input data and CNN configuration
static int[]	getSameModeBottomRightPadding(int[] outSize, int[] inSize, int[] kernel, int[] strides, int[] dilation) Get bottom and right padding for same mode only.
static int[]	getSameModeTopLeftPadding(int[] outSize, int[] inSize, int[] kernel, int[] strides, int[] dilation) Get top and left padding for same mode only.
static int	numChannels(int[] shape) Returns the number of feature maps for a given shape (must be at least 3 dimensions
static int	numFeatureMap(NeuralNetConfiguration conf)
static org.nd4j.linalg.api.ndarray.INDArray	reshape2dTo4d(org.nd4j.linalg.api.ndarray.INDArray in2d, int[] toShape)
static org.nd4j.linalg.api.ndarray.INDArray	reshape3dMask(org.nd4j.linalg.api.ndarray.INDArray mask)
static org.nd4j.linalg.api.ndarray.INDArray	reshape4dMask(org.nd4j.linalg.api.ndarray.INDArray mask)
static org.nd4j.linalg.api.ndarray.INDArray	reshape4dTo2d(org.nd4j.linalg.api.ndarray.INDArray in)
static org.nd4j.linalg.api.ndarray.INDArray	reshapeMaskIfRequired(org.nd4j.linalg.api.ndarray.INDArray mask, org.nd4j.linalg.api.ndarray.INDArray output)
static void	validateCnnKernelStridePadding(int[] kernelSize, int[] stride, int[] padding) Perform validation on the CNN layer kernel/stride/padding.
static void	validateConvolutionModePadding(ConvolutionMode mode, int[] padding) Check that the convolution mode is consistent with the padding specification
static void	validateShapes(org.nd4j.linalg.api.ndarray.INDArray inputData, int[] eKernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation, int inH, int inW, boolean atrous)

Methods inherited from class java.lang.Object

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

Method Detail

getOutputSize

public static int[] getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] kernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode)

getDeconvolutionOutputSize

public static int[] getDeconvolutionOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                               int[] kernel,
                                               int[] strides,
                                               int[] padding,
                                               ConvolutionMode convolutionMode,
                                               int[] dilation)

Get the output size of a deconvolution operation for given input data. In deconvolution, we compute the inverse of the shape computation of a convolution.

Parameters:

inputData - Input data

kernel - Kernel size (height/width)

strides - Strides (height/width)

padding - Padding (height/width)

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation (height/width)

Returns:

Output size: int[2] with output height/width

getOutputSize

public static int[] getOutputSize(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] kernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode,
                                  int[] dilation)

Get the output size (height/width) for the given input data and CNN configuration

Parameters:

inputData - Input data

kernel - Kernel size (height/width)

strides - Strides (height/width)

padding - Padding (height/width)

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation (height/width)

Returns:

Output size: int[2] with output height/width

validateShapes

public static void validateShapes(org.nd4j.linalg.api.ndarray.INDArray inputData,
                                  int[] eKernel,
                                  int[] strides,
                                  int[] padding,
                                  ConvolutionMode convolutionMode,
                                  int[] dilation,
                                  int inH,
                                  int inW,
                                  boolean atrous)

effectiveKernelSize

public static int[] effectiveKernelSize(int[] kernel,
                                        int[] dilation)

getSameModeTopLeftPadding

public static int[] getSameModeTopLeftPadding(int[] outSize,
                                              int[] inSize,
                                              int[] kernel,
                                              int[] strides,
                                              int[] dilation)

Get top and left padding for same mode only.

Parameters:

outSize -

inSize -

kernel -

strides -

Returns:

getSameModeBottomRightPadding

public static int[] getSameModeBottomRightPadding(int[] outSize,
                                                  int[] inSize,
                                                  int[] kernel,
                                                  int[] strides,
                                                  int[] dilation)

Get bottom and right padding for same mode only.

Parameters:

outSize -

inSize -

kernel -

strides -

Returns:

getHeightAndWidth

public static int[] getHeightAndWidth(NeuralNetConfiguration conf)

Get the height and width from the configuration

Parameters:

conf - the configuration to get height and width from

Returns:

the configuration to get height and width from

numFeatureMap

public static int numFeatureMap(NeuralNetConfiguration conf)

Parameters:

conf - the configuration to get the number of kernels from

Returns:

the number of kernels/filters to apply

getHeightAndWidth

public static int[] getHeightAndWidth(int[] shape)

Get the height and width for an image

Parameters:

shape - the shape of the image

Returns:

the height and width for the image

numChannels

public static int numChannels(int[] shape)

Returns the number of feature maps for a given shape (must be at least 3 dimensions

Parameters:

shape - the shape to get the number of feature maps for

Returns:

the number of feature maps for a particular shape

validateConvolutionModePadding

public static void validateConvolutionModePadding(ConvolutionMode mode,
                                                  int[] padding)

Check that the convolution mode is consistent with the padding specification

validateCnnKernelStridePadding

public static void validateCnnKernelStridePadding(int[] kernelSize,
                                                  int[] stride,
                                                  int[] padding)

Perform validation on the CNN layer kernel/stride/padding. Expect 2d int[], with values > 0 for kernel size and stride, and values >= 0 for padding.

Parameters:

kernelSize - Kernel size array to check

stride - Stride array to check

padding - Padding array to check

reshape4dTo2d

public static org.nd4j.linalg.api.ndarray.INDArray reshape4dTo2d(org.nd4j.linalg.api.ndarray.INDArray in)

reshape2dTo4d

public static org.nd4j.linalg.api.ndarray.INDArray reshape2dTo4d(org.nd4j.linalg.api.ndarray.INDArray in2d,
                                                                 int[] toShape)

reshapeMaskIfRequired

public static org.nd4j.linalg.api.ndarray.INDArray reshapeMaskIfRequired(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                                         org.nd4j.linalg.api.ndarray.INDArray output)

adapt2dMask

public static org.nd4j.linalg.api.ndarray.INDArray adapt2dMask(org.nd4j.linalg.api.ndarray.INDArray mask,
                                                               org.nd4j.linalg.api.ndarray.INDArray output)

reshape3dMask

public static org.nd4j.linalg.api.ndarray.INDArray reshape3dMask(org.nd4j.linalg.api.ndarray.INDArray mask)

reshape4dMask

public static org.nd4j.linalg.api.ndarray.INDArray reshape4dMask(org.nd4j.linalg.api.ndarray.INDArray mask)

getHWDFromInputType

public static int[] getHWDFromInputType(InputType inputType)

Get heigh/width/depth as length 3 int[] from the InputType

Parameters:

inputType - Input type to get

Returns:

Length