org.deeplearning4j.util

Class Convolution1DUtils

java.lang.Object

org.deeplearning4j.util.Convolution1DUtils

public class Convolution1DUtils
extends Object

Method Summary

Modifier and Type	Method and Description
static int	effectiveKernelSize(int kernel, int dilation)
static int	getOutputSize(INDArray inputData, int kernel, int strides, int padding, ConvolutionMode convolutionMode)
static int	getOutputSize(INDArray inputData, int kernel, int strides, int padding, ConvolutionMode convolutionMode, int dilation) Get the output size (height) for the given input data and CNN1D configuration
static long	getOutputSize(long inH, int kernel, int strides, int padding, ConvolutionMode convolutionMode, int dilation) Get the output size (height) for the given input data and CNN1D configuration
static RNNFormat	getRnnFormatFromLayer(Layer layer) Get the RNNFormat for the given layer.
static int	getSameModeBottomRightPadding(int outSize, int inSize, int kernel, int strides, int dilation)
static int	getSameModeTopLeftPadding(int outSize, int inSize, int kernel, int strides, int dilation) Get top padding for same mode only.
static boolean	hasRnnDataFormat(Layer layer) Returns true if the given layer has an RNNFormat.
static INDArray	reshapeWeightArrayOrGradientForFormat(INDArray w, RNNFormat rnnFormat) Reshapes the given weight array or weight gradient to work with the specified RNNFormat
static void	validateCnn1DKernelStridePadding(int kernel, 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(INDArray inputData, int eKernel, int strides, int padding, ConvolutionMode convolutionMode, int dilation, int inShape, 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(INDArray inputData,
                                int kernel,
                                int strides,
                                int padding,
                                ConvolutionMode convolutionMode)

hasRnnDataFormat

public static boolean hasRnnDataFormat(Layer layer)

Returns true if the given layer has an RNNFormat. This is true for: Convolution1DLayer, Subsampling1DLayer SimpleRnn LSTM EmbeddingSequenceLayer

Parameters:

layer - the layer to test

Returns:

true if the input layer has an rnn format false otherwise

getRnnFormatFromLayer

public static RNNFormat getRnnFormatFromLayer(Layer layer)

Get the RNNFormat for the given layer. Throws an IllegalArgumentException if a layer doesn't have an rnn format

Parameters:

layer - the layer to get the format for

Returns:

the format for the layer

reshapeWeightArrayOrGradientForFormat

public static INDArray reshapeWeightArrayOrGradientForFormat(INDArray w,
                                                             RNNFormat rnnFormat)

Reshapes the given weight array or weight gradient to work with the specified RNNFormat

Parameters:

w - the weight array or gradient

rnnFormat - the RNNFormat to use

Returns:

the reshaped array.

getOutputSize

public static long getOutputSize(long inH,
                                 int kernel,
                                 int strides,
                                 int padding,
                                 ConvolutionMode convolutionMode,
                                 int dilation)

Get the output size (height) for the given input data and CNN1D configuration

Parameters:

inH - Input size (height, or channels).

kernel - Kernel size

strides - Stride

padding - Padding

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation

Returns:

Output size (width)

getOutputSize

public static int getOutputSize(INDArray inputData,
                                int kernel,
                                int strides,
                                int padding,
                                ConvolutionMode convolutionMode,
                                int dilation)

Get the output size (height) for the given input data and CNN1D configuration

Parameters:

inputData - Input data

kernel - Kernel size

strides - Stride

padding - Padding

convolutionMode - Convolution mode (Same, Strict, Truncate)

dilation - Kernel dilation

Returns:

Output size (width)

validateShapes

public static void validateShapes(INDArray inputData,
                                  int eKernel,
                                  int strides,
                                  int padding,
                                  ConvolutionMode convolutionMode,
                                  int dilation,
                                  int inShape,
                                  boolean atrous)

effectiveKernelSize

public static int effectiveKernelSize(int kernel,
                                      int dilation)

validateConvolutionModePadding

public static void validateConvolutionModePadding(ConvolutionMode mode,
                                                  int padding)

Check that the convolution mode is consistent with the padding specification

getSameModeTopLeftPadding

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

Get top padding for same mode only.

Parameters:

outSize - Output size (length 2 array, height dimension first)

inSize - Input size (length 2 array, height dimension first)

kernel - Kernel size (length 2 array, height dimension first)

strides - Strides (length 2 array, height dimension first)

dilation - Dilation (length 2 array, height dimension first)

Returns:

Top left padding (length 2 array, height dimension first)

getSameModeBottomRightPadding

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

validateCnn1DKernelStridePadding

public static void validateCnn1DKernelStridePadding(int kernel,
                                                    int stride,
                                                    int padding)

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

Parameters:

kernel - Kernel size to check

stride - Stride to check

padding - Padding to check