Uses of Class
org.deeplearning4j.nn.conf.CNN2DFormat

Packages that use CNN2DFormat

Package	Description
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.inputs
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.layers.convolutional
org.deeplearning4j.nn.conf.preprocessor
org.deeplearning4j.nn.layers.convolution
org.deeplearning4j.nn.layers.convolution.subsampling
org.deeplearning4j.nn.layers.convolution.upsampling
org.deeplearning4j.nn.layers.mkldnn
org.deeplearning4j.nn.layers.normalization
org.deeplearning4j.util

Uses of CNN2DFormat in org.deeplearning4j.nn.conf

Methods in org.deeplearning4j.nn.conf that return CNN2DFormat

Modifier and Type	Method and Description
static CNN2DFormat	CNN2DFormat.valueOf(String name) Returns the enum constant of this type with the specified name.
static CNN2DFormat[]	CNN2DFormat.values() Returns an array containing the constants of this enum type, in the order they are declared.

Uses of CNN2DFormat in org.deeplearning4j.nn.conf.inputs

Methods in org.deeplearning4j.nn.conf.inputs that return CNN2DFormat

Modifier and Type	Method and Description
static CNN2DFormat	InputType.getDefaultCNN2DFormat()

Methods in org.deeplearning4j.nn.conf.inputs with parameters of type CNN2DFormat

Modifier and Type	Method and Description
static InputType	InputType.convolutional(long height, long width, long depth, CNN2DFormat format)
static void	InputType.setDefaultCNN2DFormat(CNN2DFormat defaultCNN2DFormat)

Constructors in org.deeplearning4j.nn.conf.inputs with parameters of type CNN2DFormat

Constructor and Description
InputTypeConvolutional(long height, long width, long channels, CNN2DFormat format)

Uses of CNN2DFormat in org.deeplearning4j.nn.conf.layers

Fields in org.deeplearning4j.nn.conf.layers declared as CNN2DFormat

Modifier and Type	Field and Description
protected CNN2DFormat	SubsamplingLayer.cnn2dDataFormat
protected CNN2DFormat	ConvolutionLayer.cnn2dDataFormat
protected CNN2DFormat	DepthwiseConvolution2D.Builder.cnn2DFormat
protected CNN2DFormat	SubsamplingLayer.BaseSubsamplingBuilder.cnn2DFormat Configure the 2d data format
protected CNN2DFormat	BatchNormalization.cnn2DFormat
protected CNN2DFormat	BatchNormalization.Builder.cnn2DFormat
protected CNN2DFormat	SpaceToDepthLayer.dataFormat
protected CNN2DFormat	SpaceToDepthLayer.Builder.dataFormat Data format for input activations.
protected CNN2DFormat	SeparableConvolution2D.Builder.dataFormat
protected CNN2DFormat	LocalResponseNormalization.dataFormat
protected CNN2DFormat	LocalResponseNormalization.Builder.dataFormat
protected CNN2DFormat	ConvolutionLayer.Builder.dataFormat
static CNN2DFormat	SubsamplingLayer.DEFAULT_FORMAT
protected CNN2DFormat	Upsampling2D.format
protected CNN2DFormat	Upsampling2D.Builder.format
protected CNN2DFormat	LocallyConnected2D.format
protected CNN2DFormat	LocallyConnected2D.Builder.format
protected CNN2DFormat	SpaceToBatchLayer.format
protected CNN2DFormat	SpaceToBatchLayer.Builder.format
protected CNN2DFormat	CnnLossLayer.format
protected CNN2DFormat	CnnLossLayer.Builder.format

Methods in org.deeplearning4j.nn.conf.layers that return CNN2DFormat

Modifier and Type	Method and Description
CNN2DFormat	SpaceToDepthLayer.DataFormat.toFormat() Deprecated.

Methods in org.deeplearning4j.nn.conf.layers with parameters of type CNN2DFormat

Modifier and Type	Method and Description
T	SpaceToDepthLayer.Builder.dataFormat(CNN2DFormat dataFormat) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
SeparableConvolution2D.Builder	SeparableConvolution2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
DepthwiseConvolution2D.Builder	DepthwiseConvolution2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
T	SubsamplingLayer.BaseSubsamplingBuilder.dataFormat(CNN2DFormat cnn2DFormat) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
Upsampling2D.Builder	Upsampling2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
LocallyConnected2D.Builder	LocallyConnected2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
T	SpaceToBatchLayer.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
BatchNormalization.Builder	BatchNormalization.Builder.dataFormat(CNN2DFormat format) Set the input and output array data format.
Deconvolution2D.Builder	Deconvolution2D.Builder.dataFormat(CNN2DFormat format)
LocalResponseNormalization.Builder	LocalResponseNormalization.Builder.dataFormat(CNN2DFormat dataFormat) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
ConvolutionLayer.Builder	ConvolutionLayer.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
ZeroPaddingLayer.Builder	ZeroPaddingLayer.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).
CnnLossLayer.Builder	CnnLossLayer.Builder.format(CNN2DFormat format)
static InputType	InputTypeUtil.getOutputTypeCnnLayers(InputType inputType, int[] kernelSize, int[] stride, int[] padding, int[] dilation, ConvolutionMode convolutionMode, long outputDepth, long layerIdx, String layerName, CNN2DFormat format, Class<?> layerClass)
void	SubsamplingLayer.Builder.setDataFormat(CNN2DFormat format)
void	ConvolutionLayer.Builder.setDataFormat(CNN2DFormat dataFormat)

Constructors in org.deeplearning4j.nn.conf.layers with parameters of type CNN2DFormat

Constructor and Description
Builder(int blockSize, CNN2DFormat dataFormat)

Uses of CNN2DFormat in org.deeplearning4j.nn.conf.layers.convolutional

Methods in org.deeplearning4j.nn.conf.layers.convolutional with parameters of type CNN2DFormat

Modifier and Type	Method and Description
Cropping2D.Builder	Cropping2D.Builder.dataFormat(CNN2DFormat format) Set the data format for the CNN activations - NCHW (channels first) or NHWC (channels last).

Constructors in org.deeplearning4j.nn.conf.layers.convolutional with parameters of type CNN2DFormat

Constructor and Description
Cropping2D(CNN2DFormat dataFormat, int cropTopBottom, int cropLeftRight)
Cropping2D(CNN2DFormat format, int cropTop, int cropBottom, int cropLeft, int cropRight)

Uses of CNN2DFormat in org.deeplearning4j.nn.conf.preprocessor

Fields in org.deeplearning4j.nn.conf.preprocessor declared as CNN2DFormat

Modifier and Type	Field and Description
protected CNN2DFormat	CnnToFeedForwardPreProcessor.format

Constructors in org.deeplearning4j.nn.conf.preprocessor with parameters of type CNN2DFormat

Constructor and Description
CnnToFeedForwardPreProcessor(long inputHeight, long inputWidth, long numChannels, CNN2DFormat format)

Uses of CNN2DFormat in org.deeplearning4j.nn.layers.convolution

Methods in org.deeplearning4j.nn.layers.convolution with parameters of type CNN2DFormat

Modifier and Type	Method and Description
Pair<Gradient,INDArray>	ConvolutionHelper.backpropGradient(INDArray input, INDArray weights, INDArray bias, INDArray delta, int[] kernel, int[] strides, int[] pad, INDArray biasGradView, INDArray weightGradView, IActivation afn, ConvolutionLayer.AlgoMode mode, ConvolutionLayer.BwdFilterAlgo bwdFilterAlgo, ConvolutionLayer.BwdDataAlgo bwdDataAlgo, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
INDArray	ConvolutionHelper.preOutput(INDArray input, INDArray weights, INDArray bias, int[] kernel, int[] strides, int[] pad, ConvolutionLayer.AlgoMode mode, ConvolutionLayer.FwdAlgo fwdAlgo, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)

Uses of CNN2DFormat in org.deeplearning4j.nn.layers.convolution.subsampling

Methods in org.deeplearning4j.nn.layers.convolution.subsampling with parameters of type CNN2DFormat

Modifier and Type	Method and Description
INDArray	SubsamplingHelper.activate(INDArray input, boolean training, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray>	SubsamplingHelper.backpropGradient(INDArray input, INDArray epsilon, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)

Uses of CNN2DFormat in org.deeplearning4j.nn.layers.convolution.upsampling

Methods in org.deeplearning4j.nn.layers.convolution.upsampling that return CNN2DFormat

Modifier and Type	Method and Description
protected CNN2DFormat	Upsampling2D.getFormat()
protected CNN2DFormat	Upsampling1D.getFormat()

Uses of CNN2DFormat in org.deeplearning4j.nn.layers.mkldnn

Methods in org.deeplearning4j.nn.layers.mkldnn with parameters of type CNN2DFormat

Modifier and Type	Method and Description
INDArray	MKLDNNSubsamplingHelper.activate(INDArray input, boolean training, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray>	MKLDNNConvHelper.backpropGradient(INDArray input, INDArray weights, INDArray bias, INDArray delta, int[] kernel, int[] strides, int[] pad, INDArray biasGradView, INDArray weightGradView, IActivation afn, ConvolutionLayer.AlgoMode mode, ConvolutionLayer.BwdFilterAlgo bwdFilterAlgo, ConvolutionLayer.BwdDataAlgo bwdDataAlgo, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray>	MKLDNNSubsamplingHelper.backpropGradient(INDArray input, INDArray epsilon, int[] kernel, int[] strides, int[] pad, PoolingType poolingType, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
Pair<Gradient,INDArray>	MKLDNNBatchNormHelper.backpropGradient(INDArray input, INDArray epsilon, long[] shape, INDArray gamma, INDArray beta, INDArray dGammaView, INDArray dBetaView, double eps, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
INDArray	MKLDNNBatchNormHelper.preOutput(INDArray x, boolean training, long[] shape, INDArray gamma, INDArray beta, INDArray mean, INDArray var, double decay, double eps, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
INDArray	MKLDNNConvHelper.preOutput(INDArray input, INDArray weights, INDArray bias, int[] kernel, int[] strides, int[] pad, ConvolutionLayer.AlgoMode mode, ConvolutionLayer.FwdAlgo fwdAlgo, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)

Uses of CNN2DFormat in org.deeplearning4j.nn.layers.normalization

Methods in org.deeplearning4j.nn.layers.normalization with parameters of type CNN2DFormat

Modifier and Type	Method and Description
Pair<Gradient,INDArray>	BatchNormalizationHelper.backpropGradient(INDArray input, INDArray epsilon, long[] shape, INDArray gamma, INDArray beta, INDArray dGammaView, INDArray dBetaView, double eps, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)
INDArray	BatchNormalizationHelper.preOutput(INDArray x, boolean training, long[] shape, INDArray gamma, INDArray beta, INDArray mean, INDArray var, double decay, double eps, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr)

Uses of CNN2DFormat in org.deeplearning4j.util

Methods in org.deeplearning4j.util that return CNN2DFormat

Modifier and Type	Method and Description
static CNN2DFormat	ConvolutionUtils.getFormatForLayer(Layer layer) Get the format for a given layer.

Methods in org.deeplearning4j.util with parameters of type CNN2DFormat

Modifier and Type	Method and Description
static INDArray	ConvolutionUtils.adapt2dMask(INDArray mask, INDArray output, @NonNull CNN2DFormat format, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static int[]	ConvolutionUtils.getDeconvolutionOutputSize(INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format) Get the output size of a deconvolution operation for given input data.
static int[]	ConvolutionUtils.getOutputSize(INDArray inputData, int[] kernel, int[] strides, int[] padding, ConvolutionMode convolutionMode, int[] dilation, CNN2DFormat format) Get the output size (height/width) for the given input data and CNN configuration
static INDArray	ConvolutionUtils.reshape2dTo4d(INDArray in2d, long[] toShape, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static INDArray	ConvolutionUtils.reshape4dTo2d(INDArray in, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr, ArrayType type)
static INDArray	ConvolutionUtils.reshapeMaskIfRequired(INDArray mask, INDArray output, CNN2DFormat format, LayerWorkspaceMgr workspaceMgr, ArrayType type)