| 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 |
|---|---|
void |
ComputationGraphConfiguration.addPreProcessors(InputType... inputTypes)
Add preprocessors automatically, given the specified types of inputs for the network.
|
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) |
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 |
ScaleVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PreprocessorVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PoolHelperVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LayerVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
MergeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2NormalizeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SubsetVertex.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 |
ShiftVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ElementWiseVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
UnstackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
StackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2Vertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReshapeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Method and Description |
|---|---|
MemoryReport |
ScaleVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
PreprocessorVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
PoolHelperVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
LayerVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
MergeVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
L2NormalizeVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
SubsetVertex.getMemoryReport(InputType... inputTypes) |
abstract MemoryReport |
GraphVertex.getMemoryReport(InputType... inputTypes)
This is a report of the estimated memory consumption for the given vertex
|
MemoryReport |
ShiftVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ElementWiseVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
UnstackVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
StackVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
L2Vertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
ReshapeVertex.getMemoryReport(InputType... inputTypes) |
InputType |
ScaleVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PreprocessorVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
PoolHelperVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LayerVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
MergeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2NormalizeVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
SubsetVertex.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 |
ShiftVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ElementWiseVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
UnstackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
StackVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
L2Vertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
ReshapeVertex.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) |
| Modifier and Type | Method and Description |
|---|---|
MemoryReport |
DuplicateToTimeSeriesVertex.getMemoryReport(InputType... inputTypes) |
MemoryReport |
LastTimeStepVertex.getMemoryReport(InputType... inputTypes) |
InputType |
DuplicateToTimeSeriesVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
InputType |
LastTimeStepVertex.getOutputType(int layerIndex,
InputType... vertexInputs) |
| Modifier and Type | Class and Description |
|---|---|
static class |
InputType.InputTypeConvolutional |
static class |
InputType.InputTypeConvolutionalFlat |
static class |
InputType.InputTypeFeedForward |
static class |
InputType.InputTypeRecurrent |
| Modifier and Type | Method and Description |
|---|---|
static InputType |
InputType.convolutional(int height,
int width,
int depth)
Input type for convolutional (CNN) data, that is 4d with shape [miniBatchSize, depth, height, width].
|
static InputType |
InputType.convolutionalFlat(int height,
int width,
int depth)
Input type for convolutional (CNN) data, where the data is in flattened (row vector) format.
|
static InputType |
InputType.feedForward(int size)
InputType for feed forward network data
|
InputType |
InputType.InputTypeConvolutionalFlat.getUnflattenedType() |
static InputType |
InputType.inferInputType(org.nd4j.linalg.api.ndarray.INDArray inputArray) |
static InputType[] |
InputType.inferInputTypes(org.nd4j.linalg.api.ndarray.INDArray... inputArrays) |
static InputType |
InputType.recurrent(int size)
InputType for recurrent neural network (time series) data
|
static InputType |
InputType.recurrent(int size,
int timeSeriesLength)
InputType for recurrent neural network (time series) data
|
| Modifier and Type | Method and Description |
|---|---|
InputType |
SubsamplingLayer.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 |
BaseRecurrentLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BatchNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnOutputLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
GlobalPoolingLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ActivationLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocalResponseNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ConvolutionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DropoutLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
FeedForwardLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPaddingLayer.getOutputType(int layerIndex,
InputType inputType) |
static InputType |
InputTypeUtil.getOutputTypeCnnLayers(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
ConvolutionMode convolutionMode,
int outputDepth,
int layerIdx,
String layerName,
Class<?> layerClass) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
AutoEncoder.getMemoryReport(InputType inputType) |
LayerMemoryReport |
SubsamplingLayer.getMemoryReport(InputType inputType) |
abstract LayerMemoryReport |
Layer.getMemoryReport(InputType inputType)
This is a report of the estimated memory consumption for the given layer
|
LayerMemoryReport |
LSTM.getMemoryReport(InputType inputType) |
LayerMemoryReport |
RBM.getMemoryReport(InputType inputType) |
LayerMemoryReport |
EmbeddingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
BatchNormalization.getMemoryReport(InputType inputType) |
LayerMemoryReport |
BaseOutputLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
GravesBidirectionalLSTM.getMemoryReport(InputType inputType) |
LayerMemoryReport |
GravesLSTM.getMemoryReport(InputType inputType) |
LayerMemoryReport |
GlobalPoolingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ActivationLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
LocalResponseNormalization.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ConvolutionLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
DropoutLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
CenterLossOutputLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
LossLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
ZeroPaddingLayer.getMemoryReport(InputType inputType) |
LayerMemoryReport |
DenseLayer.getMemoryReport(InputType inputType) |
InputType |
SubsamplingLayer.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 |
BaseRecurrentLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
BatchNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
RnnOutputLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
GlobalPoolingLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ActivationLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
LocalResponseNormalization.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ConvolutionLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
DropoutLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Subsampling1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
FeedForwardLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
Convolution1DLayer.getOutputType(int layerIndex,
InputType inputType) |
InputType |
ZeroPaddingLayer.getOutputType(int layerIndex,
InputType inputType) |
static InputType |
InputTypeUtil.getOutputTypeCnnLayers(InputType inputType,
int[] kernelSize,
int[] stride,
int[] padding,
ConvolutionMode convolutionMode,
int outputDepth,
int layerIdx,
String layerName,
Class<?> layerClass) |
InputPreProcessor |
SubsamplingLayer.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 |
BaseRecurrentLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
BatchNormalization.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
RnnOutputLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
GlobalPoolingLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ActivationLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
LocalResponseNormalization.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ConvolutionLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
DropoutLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Subsampling1DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
FeedForwardLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Convolution1DLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
ZeroPaddingLayer.getPreProcessorForInputType(InputType inputType) |
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,
String layerName) |
void |
SubsamplingLayer.setNIn(InputType inputType,
boolean override) |
abstract void |
Layer.setNIn(InputType inputType,
boolean override)
Set the nIn value (number of inputs, or input depth for CNNs) based on the given input type
|
void |
BaseRecurrentLayer.setNIn(InputType inputType,
boolean override) |
void |
BatchNormalization.setNIn(InputType inputType,
boolean override) |
void |
RnnOutputLayer.setNIn(InputType inputType,
boolean override) |
void |
GlobalPoolingLayer.setNIn(InputType inputType,
boolean override) |
void |
ActivationLayer.setNIn(InputType inputType,
boolean override) |
void |
LocalResponseNormalization.setNIn(InputType inputType,
boolean override) |
void |
ConvolutionLayer.setNIn(InputType inputType,
boolean override) |
void |
DropoutLayer.setNIn(InputType inputType,
boolean override) |
void |
Subsampling1DLayer.setNIn(InputType inputType,
boolean override) |
void |
FeedForwardLayer.setNIn(InputType inputType,
boolean override) |
void |
Convolution1DLayer.setNIn(InputType inputType,
boolean override) |
void |
ZeroPaddingLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
FrozenLayer.getOutputType(int layerIndex,
InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
FrozenLayer.getMemoryReport(InputType inputType) |
InputType |
FrozenLayer.getOutputType(int layerIndex,
InputType inputType) |
InputPreProcessor |
FrozenLayer.getPreProcessorForInputType(InputType inputType) |
void |
FrozenLayer.setNIn(InputType inputType,
boolean override) |
| Modifier and Type | Method and Description |
|---|---|
LayerMemoryReport |
VariationalAutoencoder.getMemoryReport(InputType inputType) |
| Constructor and Description |
|---|
Builder(String layerName,
Class<?> layerType,
InputType inputType,
InputType outputType) |
NetworkMemoryReport(Map<String,MemoryReport> layerAndVertexReports,
Class<?> modelClass,
String modelName,
InputType... networkInputTypes) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
UnitVarianceProcessor.getOutputType(InputType inputType) |
InputType |
BinomialSamplingPreProcessor.getOutputType(InputType inputType) |
InputType |
ComposableInputPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ZeroMeanAndUnitVariancePreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ZeroMeanPrePreProcessor.getOutputType(InputType inputType) |
| Modifier and Type | Method and Description |
|---|---|
InputType |
UnitVarianceProcessor.getOutputType(InputType inputType) |
InputType |
BinomialSamplingPreProcessor.getOutputType(InputType inputType) |
InputType |
ComposableInputPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToFeedForwardPreProcessor.getOutputType(InputType inputType) |
InputType |
FeedForwardToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ZeroMeanAndUnitVariancePreProcessor.getOutputType(InputType inputType) |
InputType |
RnnToCnnPreProcessor.getOutputType(InputType inputType) |
InputType |
CnnToRnnPreProcessor.getOutputType(InputType inputType) |
InputType |
ZeroMeanPrePreProcessor.getOutputType(InputType inputType) |
| 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 |
|---|---|
TransferLearning.GraphBuilder |
TransferLearning.GraphBuilder.setInputTypes(InputType... inputTypes)
Sets the input type of corresponding inputs.
|
Copyright © 2017. All rights reserved.