| Modifier and Type | Field and Description |
|---|---|
protected InputType |
MultiLayerConfiguration.Builder.inputType |
| Modifier and Type | Field and Description |
|---|---|
protected List<InputType> |
ComputationGraphConfiguration.GraphBuilder.networkInputTypes |
| Modifier and Type | Method and Description |
|---|---|
InputType |
InputPreProcessor.getOutputType(InputType inputType)
For a given type of input to this preprocessor, what is the type of the output?
|
| Modifier and Type | Method and Description |
|---|---|
Map<String,InputType> |
ComputationGraphConfiguration.GraphBuilder.getLayerActivationTypes()
For the (perhaps partially constructed) network configuration, return a map of activation sizes for each
layer and vertex in the graph.
Note 1: The network configuration may be incomplete, but the inputs have been added to the layer already. Note 2: To use this method, the network input types must have been set using ComputationGraphConfiguration.GraphBuilder.setInputTypes(InputType...)
first |
List<InputType> |
NeuralNetConfiguration.ListBuilder.getLayerActivationTypes()
For the (perhaps partially constructed) network configuration, return a list of activation sizes for each
layer in the network.
Note: To use this method, the network input type must have been set using NeuralNetConfiguration.ListBuilder.setInputType(InputType) first |
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(boolean addPreprocIfNecessary,
boolean overrideInputs,
InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(boolean addPreprocIfNecessary,
InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
List<InputType> |
MultiLayerConfiguration.getLayerActivationTypes(@NonNull InputType inputType)
For the given input shape/type for the network, return a list of activation sizes for each layer in the network.
i.e., list.get(i) is the output activation sizes for layer i |
| Modifier and Type | Method and Description |
|---|---|
void |
ComputationGraphConfiguration.addPreProcessors(boolean addPreprocIfNecessary,
boolean forceOverrideInputs,
InputType... inputTypes)
Add preprocessors automatically, given the specified types of inputs for the network.
|
void |
ComputationGraphConfiguration.addPreProcessors(boolean forceOverrideInputs,
InputType... inputTypes)
Add preprocessors automatically, given the specified types of inputs for the network.
|
void |
ComputationGraphConfiguration.addPreProcessors(InputType... inputTypes)
Add preprocessors automatically, given the specified types of inputs for the network.
|
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(boolean addPreprocIfNecessary,
boolean overrideInputs,
InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(boolean addPreprocIfNecessary,
InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
Map<String,InputType> |
ComputationGraphConfiguration.getLayerActivationTypes(InputType... inputTypes)
For the given input shape/type for the network, return a map of activation sizes for each layer and vertex
in the graph.
|
List<InputType> |
MultiLayerConfiguration.getLayerActivationTypes(@NonNull InputType inputType)
For the given input shape/type for the network, return a list of activation sizes for each layer in the network.
i.e., list.get(i) is the output activation sizes for layer i |
NetworkMemoryReport |
ComputationGraphConfiguration.getMemoryReport(InputType... inputTypes)
Get a
MemoryReport for the given computation graph configuration. |
NetworkMemoryReport |
MultiLayerConfiguration.getMemoryReport(InputType inputType)
Get a
MemoryReport for the given MultiLayerConfiguration. |
InputType |
InputPreProcessor.getOutputType(InputType inputType)
For a given type of input to this preprocessor, what is the type of the output?
|
MultiLayerConfiguration.Builder |
MultiLayerConfiguration.Builder.setInputType(InputType inputType) |
NeuralNetConfiguration.ListBuilder |
NeuralNetConfiguration.ListBuilder.setInputType(InputType inputType) |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.setInputTypes(InputType... inputTypes)
Specify the types of inputs to the network, so that:
(a) preprocessors can be automatically added, and (b) the nIns (input size) for each layer can be automatically calculated and set The order here is the same order as .addInputs(). |
| Modifier and Type | Method and Description |
|---|---|
InputType |
AttentionVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ElementWiseVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
FrozenVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
abstract InputType |
GraphVertex.getOutputType(int layerIndex,
InputType... vertexInputs)
Determine the type of output for this GraphVertex, given the specified inputs.
|
InputType |
L2NormalizeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2Vertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LayerVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
MergeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PoolHelperVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PreprocessorVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReshapeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ScaleVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ShiftVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
StackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SubsetVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
UnstackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Method and Description |
|---|---|
MemoryReport |
ElementWiseVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
FrozenVertex.getMemoryReport(InputType... inputTypes) |
abstract MemoryReport |
GraphVertex.getMemoryReport(InputType... inputTypes)
This is a report of the estimated memory consumption for the given vertex
|
MemoryReport |
L2NormalizeVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
L2Vertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
LayerVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
MergeVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
PoolHelperVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
PreprocessorVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ReshapeVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ScaleVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ShiftVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
StackVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
SubsetVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
UnstackVertex.getMemoryReport(InputType... inputTypes) |
InputType |
AttentionVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ElementWiseVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
FrozenVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
abstract InputType |
GraphVertex.getOutputType(int layerIndex,
InputType... vertexInputs)
Determine the type of output for this GraphVertex, given the specified inputs.
|
InputType |
L2NormalizeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2Vertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LayerVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
MergeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PoolHelperVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PreprocessorVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReshapeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ScaleVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ShiftVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
StackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SubsetVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
UnstackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
DuplicateToTimeSeriesVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LastTimeStepVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReverseTimeSeriesVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Method and Description |
|---|---|
MemoryReport |
DuplicateToTimeSeriesVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
LastTimeStepVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ReverseTimeSeriesVertex.getMemoryReport(InputType... inputTypes) |
InputType |
DuplicateToTimeSeriesVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LastTimeStepVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReverseTimeSeriesVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Class and Description |
|---|---|
static class |
InputType.InputTypeConvolutional |
static class |
InputType.InputTypeConvolutional3D |
static class |
InputType.InputTypeConvolutionalFlat |
static class |
InputType.InputTypeFeedForward |
static class |
InputType.InputTypeRecurrent |
| Modifier and Type | Method and Description |
|---|---|
static InputType |
InputType.convolutional(long height,
long width,
long depth)
Input type for convolutional (CNN) data, that is 4d with shape [miniBatchSize, channels, height, width].
|
static InputType |
InputType.convolutional(long height,
long width,
long depth,
CNN2DFormat format) |
static InputType |
InputType.convolutional3D(Convolution3D.DataFormat dataFormat,
long depth,
long height,
long width,
long channels)
Input type for 3D convolutional (CNN3D) 5d data:
If NDHWC format [miniBatchSize, depth, height, width, channels] If NDCWH |
static InputType |
InputType.convolutional3D(long depth,
long height,
long width,
long channels)
|
static InputType |
InputType.convolutionalFlat(long height,
long width,
long depth)
Input type for convolutional (CNN) data, where the data is in flattened (row vector) format.
|
static InputType |
InputType.feedForward(long size)
InputType for feed forward network data
|
static InputType |
InputType.feedForward(long size,
DataFormat timeDistributedFormat) |
InputType |
InputType.InputTypeConvolutionalFlat.getUnflattenedType() |
static InputType |
InputType.inferInputType(INDArray inputArray) |
static InputType[] |
InputType.inferInputTypes(INDArray... inputArrays) |
static InputType |
InputType.recurrent(long size)
InputType for recurrent neural network (time series) data
|
static InputType |
InputType.recurrent(long size,
long timeSeriesLength)
InputType for recurrent neural network (time series) data
|
static InputType |
InputType.recurrent(long size,
long timeSeriesLength,
RNNFormat format) |
static InputType |
InputType.recurrent(long size,
RNNFormat format) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
ActivationLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BaseRecurrentLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BatchNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CapsuleLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CapsuleStrengthLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cnn3DLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CnnLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ConvolutionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Deconvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Deconvolution3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DepthwiseConvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DropoutLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
EmbeddingSequenceLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
FeedForwardLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
GlobalPoolingLayer.getOutputType(int layerIndex,
InputType inputType) |
abstract InputType |
Layer.getOutputType(int layerIndex,
InputType inputType)
For a given type of input to this layer, what is the type of the output?
|
InputType |
LearnedSelfAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocallyConnected1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocallyConnected2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocalResponseNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
PReLULayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
PrimaryCapsules.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RecurrentAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnOutputLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SelfAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SeparableConvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SpaceToBatchLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SpaceToDepthLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling3DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SubsamplingLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPadding1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPadding3DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPaddingLayer.getOutputType(int layerIndex,
InputType inputType) |
static InputType |
InputTypeUtil.getOutputTypeCnn1DLayers(InputType inputType,
int kH,
int sH,
int padH,
int dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeCnn3DLayers(InputType inputType,
Convolution3D.DataFormat dataFormat,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputChannels,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeCnnLayers(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass)
|
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) |
static InputType |
InputTypeUtil.getOutputTypeDeconv3dLayer(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
Convolution3D.DataFormat dataFormat,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeDeconvLayer(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
| Modifier and Type | Method and Description |
|---|---|
static void |
InputTypeUtil.convertMultipleTypes(InputType[] vertexInputs)
Convert multiple types when multiple are found.
|
LayerMemoryReport |
ActivationLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
AutoEncoder.getMemoryReport(InputType inputType) |
LayerMemoryReport |
BaseOutputLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
BatchNormalization.getMemoryReport(InputType inputType) |
LayerMemoryReport |
CenterLossOutputLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Cnn3DLossLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
CnnLossLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ConvolutionLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
DenseLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
DropoutLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
EmbeddingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
EmbeddingSequenceLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
GlobalPoolingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
GravesBidirectionalLSTM.getMemoryReport(InputType inputType)
Deprecated.
|
LayerMemoryReport |
GravesLSTM.getMemoryReport(InputType inputType)
Deprecated.
|
abstract LayerMemoryReport |
Layer.getMemoryReport(InputType inputType)
This is a report of the estimated memory consumption for the given layer
|
LayerMemoryReport |
LocalResponseNormalization.getMemoryReport(InputType inputType) |
LayerMemoryReport |
LossLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
LSTM.getMemoryReport(InputType inputType) |
LayerMemoryReport |
PReLULayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
RnnLossLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
SpaceToBatchLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
SpaceToDepthLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Subsampling3DLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
SubsamplingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Upsampling1D.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Upsampling2D.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Upsampling3D.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ZeroPadding1DLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ZeroPadding3DLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ZeroPaddingLayer.getMemoryReport(InputType inputType) |
InputType |
ActivationLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BaseRecurrentLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BatchNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CapsuleLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CapsuleStrengthLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cnn3DLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
CnnLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ConvolutionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Deconvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Deconvolution3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DepthwiseConvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DropoutLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
EmbeddingSequenceLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
FeedForwardLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
GlobalPoolingLayer.getOutputType(int layerIndex,
InputType inputType) |
abstract InputType |
Layer.getOutputType(int layerIndex,
InputType inputType)
For a given type of input to this layer, what is the type of the output?
|
InputType |
LearnedSelfAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocallyConnected1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocallyConnected2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocalResponseNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
PReLULayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
PrimaryCapsules.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RecurrentAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnLossLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnOutputLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SelfAttentionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SeparableConvolution2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SpaceToBatchLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SpaceToDepthLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling3DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
SubsamplingLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Upsampling3D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPadding1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPadding3DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPaddingLayer.getOutputType(int layerIndex,
InputType inputType) |
static InputType |
InputTypeUtil.getOutputTypeCnn1DLayers(InputType inputType,
int kH,
int sH,
int padH,
int dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeCnn3DLayers(InputType inputType,
Convolution3D.DataFormat dataFormat,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputChannels,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeCnnLayers(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass)
|
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) |
static InputType |
InputTypeUtil.getOutputTypeDeconv3dLayer(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
Convolution3D.DataFormat dataFormat,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
static InputType |
InputTypeUtil.getOutputTypeDeconvLayer(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
int[] dilation,
ConvolutionMode convolutionMode,
long outputDepth,
long layerIdx,
String layerName,
Class<?> layerClass) |
InputPreProcessor |
ActivationLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
BaseRecurrentLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
BaseUpsamplingLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
BatchNormalization.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Cnn3DLossLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
CnnLossLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Convolution1DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Convolution3D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ConvolutionLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Deconvolution3D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
DropoutLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
EmbeddingSequenceLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
FeedForwardLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
GlobalPoolingLayer.getPreProcessorForInputType(InputType inputType) |
abstract InputPreProcessor |
Layer.getPreProcessorForInputType(InputType inputType)
For the given type of input to this layer, what preprocessor (if any) is required?
Returns null if no preprocessor is required, otherwise returns an appropriate InputPreProcessor for this layer, such as a CnnToFeedForwardPreProcessor |
InputPreProcessor |
LearnedSelfAttentionLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
LocallyConnected1D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
LocallyConnected2D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
LocalResponseNormalization.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
PReLULayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
RecurrentAttentionLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
RnnLossLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
RnnOutputLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
SelfAttentionLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
SpaceToBatchLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
SpaceToDepthLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Subsampling1DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Subsampling3DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
SubsamplingLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Upsampling1D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Upsampling2D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Upsampling3D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ZeroPadding1DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ZeroPadding3DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ZeroPaddingLayer.getPreProcessorForInputType(InputType inputType) |
static InputPreProcessor |
InputTypeUtil.getPreProcessorForInputTypeCnn3DLayers(InputType inputType,
String layerName)
Utility method for determining the appropriate preprocessor for CNN layers, such as
ConvolutionLayer and
SubsamplingLayer |
static InputPreProcessor |
InputTypeUtil.getPreProcessorForInputTypeCnnLayers(InputType inputType,
String layerName)
Utility method for determining the appropriate preprocessor for CNN layers, such as
ConvolutionLayer and
SubsamplingLayer |
static InputPreProcessor |
InputTypeUtil.getPreprocessorForInputTypeRnnLayers(InputType inputType,
RNNFormat rnnDataFormat,
String layerName) |
void |
ActivationLayer.setNIn(InputType inputType,
boolean override) |
void |
BaseRecurrentLayer.setNIn(InputType inputType,
boolean override) |
void |
BatchNormalization.setNIn(InputType inputType,
boolean override) |
void |
CapsuleLayer.setNIn(InputType inputType,
boolean override) |
void |
Cnn3DLossLayer.setNIn(InputType inputType,
boolean override) |
void |
CnnLossLayer.setNIn(InputType inputType,
boolean override) |
void |
Convolution1DLayer.setNIn(InputType inputType,
boolean override) |
void |
Convolution3D.setNIn(InputType inputType,
boolean override) |
void |
ConvolutionLayer.setNIn(InputType inputType,
boolean override) |
void |
Deconvolution3D.setNIn(InputType inputType,
boolean override) |
void |
DepthwiseConvolution2D.setNIn(InputType inputType,
boolean override) |
void |
DropoutLayer.setNIn(InputType inputType,
boolean override) |
void |
EmbeddingSequenceLayer.setNIn(InputType inputType,
boolean override) |
void |
FeedForwardLayer.setNIn(InputType inputType,
boolean override) |
void |
GlobalPoolingLayer.setNIn(InputType inputType,
boolean override) |
abstract void |
Layer.setNIn(InputType inputType,
boolean override)
Set the nIn value (number of inputs, or input channels for CNNs) based on the given input
type
|
void |
LearnedSelfAttentionLayer.setNIn(InputType inputType,
boolean override) |
void |
LocallyConnected1D.setNIn(InputType inputType,
boolean override) |
void |
LocallyConnected2D.setNIn(InputType inputType,
boolean override) |
void |
LocalResponseNormalization.setNIn(InputType inputType,
boolean override) |
void |
NoParamLayer.setNIn(InputType inputType,
boolean override) |
void |
PReLULayer.setNIn(InputType inputType,
boolean override) |
void |
PrimaryCapsules.setNIn(InputType inputType,
boolean override) |
void |
RecurrentAttentionLayer.setNIn(InputType inputType,
boolean override) |
void |
RnnLossLayer.setNIn(InputType inputType,
boolean override) |
void |
RnnOutputLayer.setNIn(InputType inputType,
boolean override) |
void |
SelfAttentionLayer.setNIn(InputType inputType,
boolean override) |
void |
SpaceToBatchLayer.setNIn(InputType inputType,
boolean override) |
void |
SpaceToDepthLayer.setNIn(InputType inputType,
boolean override) |
void |
Subsampling1DLayer.setNIn(InputType inputType,
boolean override) |
void |
Subsampling3DLayer.setNIn(InputType inputType,
boolean override) |
void |
SubsamplingLayer.setNIn(InputType inputType,
boolean override) |
void |
Upsampling2D.setNIn(InputType inputType,
boolean override) |
void |
ZeroPadding1DLayer.setNIn(InputType inputType,
boolean override) |
void |
ZeroPadding3DLayer.setNIn(InputType inputType,
boolean override) |
void |
ZeroPaddingLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
Cropping1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cropping2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cropping3D.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
Cropping1D.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Cropping2D.getMemoryReport(InputType inputType) |
LayerMemoryReport |
Cropping3D.getMemoryReport(InputType inputType) |
InputType |
Cropping1D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cropping2D.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Cropping3D.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
Cropping1D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Cropping2D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Cropping3D.getPreProcessorForInputType(InputType inputType) |
void |
Cropping2D.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
FrozenLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RepeatVector.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
ElementWiseMultiplicationLayer.getMemoryReport(InputType inputType)
This is a report of the estimated memory consumption for the given layer
|
LayerMemoryReport |
FrozenLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
RepeatVector.getMemoryReport(InputType inputType) |
InputType |
FrozenLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RepeatVector.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
FrozenLayer.getPreProcessorForInputType(InputType inputType) |
void |
FrozenLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
Yolo2OutputLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
Yolo2OutputLayer.getMemoryReport(InputType inputType) |
InputType |
Yolo2OutputLayer.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
Yolo2OutputLayer.getPreProcessorForInputType(InputType inputType) |
void |
Yolo2OutputLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
Bidirectional.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LastTimeStep.getOutputType(int layerIndex,
InputType inputType) |
InputType |
TimeDistributed.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
Bidirectional.getMemoryReport(InputType inputType) |
LayerMemoryReport |
SimpleRnn.getMemoryReport(InputType inputType) |
InputType |
Bidirectional.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LastTimeStep.getOutputType(int layerIndex,
InputType inputType) |
InputType |
TimeDistributed.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
Bidirectional.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
TimeDistributed.getPreProcessorForInputType(InputType inputType) |
void |
Bidirectional.setNIn(InputType inputType,
boolean override) |
void |
TimeDistributed.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
SameDiffVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SameDiffLambdaLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
MemoryReport |
SameDiffVertex.getMemoryReport(InputType... inputTypes) |
LayerMemoryReport |
AbstractSameDiffLayer.getMemoryReport(InputType inputType) |
InputType |
SameDiffVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SameDiffLambdaLayer.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
AbstractSameDiffLayer.getPreProcessorForInputType(InputType inputType) |
void |
AbstractSameDiffLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
MaskLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
MaskZeroLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
MaskLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
MaskZeroLayer.getMemoryReport(InputType inputType) |
InputType |
MaskLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
MaskZeroLayer.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
MaskLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
MaskZeroLayer.getPreProcessorForInputType(InputType inputType) |
void |
MaskLayer.setNIn(InputType inputType,
boolean override) |
void |
MaskZeroLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
VariationalAutoencoder.getMemoryReport(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
BaseWrapperLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
BaseWrapperLayer.getMemoryReport(InputType inputType) |
InputType |
BaseWrapperLayer.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
BaseWrapperLayer.getPreProcessorForInputType(InputType inputType) |
void |
BaseWrapperLayer.setNIn(InputType inputType,
boolean override) |
| Constructor and Description |
|---|
Builder(String layerName,
Class<?> layerType,
InputType inputType,
InputType outputType) |
NetworkMemoryReport(@NonNull Map<String,MemoryReport> layerAndVertexReports,
@NonNull Class<?> modelClass,
String modelName,
InputType... networkInputTypes) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
Cnn3DToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ComposableInputPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnn3DPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
Cnn3DToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ComposableInputPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnn3DPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
String |
ComputationGraph.memoryInfo(int minibatch,
InputType... inputTypes)
Generate information regarding memory use for the network, for the given input types and minibatch size.
|
String |
ComputationGraph.summary(InputType... inputTypes)
String detailing the architecture of the computation graph.
|
| Modifier and Type | Method and Description |
|---|---|
static LayerMemoryReport |
LSTMHelpers.getMemoryReport(AbstractLSTM lstmLayer,
InputType inputType) |
static LayerMemoryReport |
LSTMHelpers.getMemoryReport(boolean isGraves,
FeedForwardLayer lstmLayer,
InputType inputType) |
static LayerMemoryReport |
LSTMHelpers.getMemoryReport(GravesBidirectionalLSTM lstmLayer,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
IdentityLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
IdentityLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
KerasFlattenRnnPreprocessor.getOutputType(InputType inputType) |
InputType |
PermutePreprocessor.getOutputType(InputType inputType) |
InputType |
ReshapePreprocessor.getOutputType(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
KerasFlattenRnnPreprocessor.getOutputType(InputType inputType) |
InputType |
PermutePreprocessor.getOutputType(InputType inputType) |
InputType |
ReshapePreprocessor.getOutputType(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
String |
MultiLayerNetwork.memoryInfo(int minibatch,
InputType inputType)
Generate information regarding memory use for the network, for the given input type and minibatch size.
|
String |
MultiLayerNetwork.summary(InputType inputType)
String detailing the architecture of the multilayernetwork.
|
| Modifier and Type | Method and Description |
|---|---|
TransferLearning.GraphBuilder |
TransferLearning.GraphBuilder.setInputTypes(InputType... inputTypes)
Sets the input type of corresponding inputs.
|
| Modifier and Type | Method and Description |
|---|---|
static String |
CrashReportingUtil.generateMemoryStatus(Model net,
int minibatch,
InputType... inputTypes)
Generate memory/system report as a String, for the specified network.
|
static int[] |
ConvolutionUtils.getHWDFromInputType(InputType inputType)
Get heigh/width/channels as length 3 int[] from the InputType
|
Copyright © 2021. All rights reserved.