Modifier and Type | Field and Description |
---|---|
protected InputPreProcessor |
BaseNetworkSpace.LayerConf.preProcessor |
Modifier and Type | Field and Description |
---|---|
protected ParameterSpace<Map<Integer,InputPreProcessor>> |
MultiLayerSpace.inputPreProcessors |
protected ParameterSpace<Map<Integer,InputPreProcessor>> |
MultiLayerSpace.Builder.inputPreProcessors |
Modifier and Type | Method and Description |
---|---|
ComputationGraphSpace.Builder |
ComputationGraphSpace.Builder.addLayer(String layerName,
LayerSpace<? extends Layer> layerSpace,
InputPreProcessor preProcessor,
String... layerInputs) |
ComputationGraphSpace.Builder |
ComputationGraphSpace.Builder.layer(String layerName,
LayerSpace<? extends Layer> layerSpace,
InputPreProcessor preProcessor,
String... layerInputs) |
Modifier and Type | Method and Description |
---|---|
MultiLayerSpace.Builder |
MultiLayerSpace.Builder.setInputPreProcessors(Map<Integer,InputPreProcessor> inputPreProcessors) |
MultiLayerSpace.Builder |
MultiLayerSpace.Builder.setInputPreProcessors(ParameterSpace<Map<Integer,InputPreProcessor>> inputPreProcessors) |
Modifier and Type | Field and Description |
---|---|
protected Map<String,InputPreProcessor> |
ComputationGraphConfiguration.GraphBuilder.inputPreProcessors |
protected Map<Integer,InputPreProcessor> |
MultiLayerConfiguration.inputPreProcessors |
protected Map<Integer,InputPreProcessor> |
MultiLayerConfiguration.Builder.inputPreProcessors |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
InputPreProcessor.clone() |
InputPreProcessor |
MultiLayerConfiguration.getInputPreProcess(int curr) |
Modifier and Type | Method and Description |
---|---|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.addLayer(String layerName,
Layer layer,
InputPreProcessor preProcessor,
String... layerInputs)
Add a layer and an
InputPreProcessor , with the specified name and specified inputs. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.appendLayer(String layerName,
Layer layer,
InputPreProcessor preProcessor)
Add a layer and an
InputPreProcessor , with the specified name
and input from the last added layer/vertex. |
MultiLayerConfiguration.Builder |
MultiLayerConfiguration.Builder.inputPreProcessor(Integer layer,
InputPreProcessor processor)
Specify the processors.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.inputPreProcessor(String layer,
InputPreProcessor processor)
Specify the processors for a given layer
These are used at each layer for doing things like normalization and shaping of input.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.layer(String layerName,
Layer layer,
InputPreProcessor preProcessor,
String... layerInputs)
Add a layer and an
InputPreProcessor , with the specified name and specified inputs. |
Modifier and Type | Method and Description |
---|---|
MultiLayerConfiguration.Builder |
MultiLayerConfiguration.Builder.inputPreProcessors(Map<Integer,InputPreProcessor> processors) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
LayerVertex.getPreProcessor() |
Constructor and Description |
---|
LayerVertex(NeuralNetConfiguration layerConf,
InputPreProcessor preProcessor) |
PreprocessorVertex(InputPreProcessor preProcessor) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
Cropping1D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Cropping2D.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
Cropping3D.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
FrozenLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
Yolo2OutputLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
Bidirectional.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
TimeDistributed.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
AbstractSameDiffLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
MaskLayer.getPreProcessorForInputType(InputType inputType) |
InputPreProcessor |
MaskZeroLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
BaseWrapperLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Class and Description |
---|---|
class |
BaseInputPreProcessor |
class |
Cnn3DToFeedForwardPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
class |
CnnToFeedForwardPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
class |
CnnToRnnPreProcessor
A preprocessor to allow CNN and RNN layers to be used together.
|
class |
ComposableInputPreProcessor
Composable input pre processor
|
class |
FeedForwardToCnn3DPreProcessor
A preprocessor to allow 3D CNN and standard feed-forward network layers to be used together.
|
class |
FeedForwardToCnnPreProcessor
A preprocessor to allow CNN and standard feed-forward network layers to be used together.
|
class |
FeedForwardToRnnPreProcessor
A preprocessor to allow RNN and feed-forward network layers to be used together.
|
class |
RnnToCnnPreProcessor
A preprocessor to allow RNN and CNN layers to be used together
For example, time series (video) input -> ConvolutionLayer, or conceivable GravesLSTM -> ConvolutionLayer Functionally equivalent to combining RnnToFeedForwardPreProcessor + FeedForwardToCnnPreProcessor Specifically, this does two things: (a) Reshape 3d activations out of RNN layer, with shape [miniBatchSize, numChannels*inputHeight*inputWidth, timeSeriesLength]) into 4d (CNN) activations (with shape [numExamples*timeSeriesLength, numChannels, inputWidth, inputHeight]) (b) Reshapes 4d epsilons (weights. |
class |
RnnToFeedForwardPreProcessor
A preprocessor to allow RNN and feed-forward network layers to be used together.
|
Constructor and Description |
---|
ComposableInputPreProcessor(InputPreProcessor... inputPreProcessors) |
Constructor and Description |
---|
LayerVertex(ComputationGraph graph,
String name,
int vertexIndex,
Layer layer,
InputPreProcessor layerPreProcessor,
boolean outputVertex,
DataType dataType)
Create a network input vertex:
|
LayerVertex(ComputationGraph graph,
String name,
int vertexIndex,
VertexIndices[] inputVertices,
VertexIndices[] outputVertices,
Layer layer,
InputPreProcessor layerPreProcessor,
boolean outputVertex,
DataType dataType) |
PreprocessorVertex(ComputationGraph graph,
String name,
int vertexIndex,
InputPreProcessor preProcessor,
DataType dataType) |
PreprocessorVertex(ComputationGraph graph,
String name,
int vertexIndex,
VertexIndices[] inputVertices,
VertexIndices[] outputVertices,
InputPreProcessor preProcessor,
DataType dataType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasLayer.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
TFOpLayer.getPreProcessorForInputType(InputType inputType) |
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasConvolution1D.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasFlatten.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
InputPreProcessor |
KerasPermute.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
InputPreProcessor |
KerasReshape.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasGlobalPooling.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasLSTM.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
InputPreProcessor |
KerasSimpleRnn.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Method and Description |
---|---|
InputPreProcessor |
KerasBidirectional.getInputPreprocessor(InputType... inputType)
Gets appropriate DL4J InputPreProcessor for given InputTypes.
|
Modifier and Type | Class and Description |
---|---|
class |
KerasFlattenRnnPreprocessor
Preprocessor to flatten input of RNN type
|
class |
PermutePreprocessor
Preprocessor to permute input data according to specified permutation indices.
|
class |
ReshapePreprocessor
Generic reshape preprocessor.
|
class |
TensorFlowCnnToFeedForwardPreProcessor
Deprecated.
Exists only for backward compatibility of older pretrained models. Should not be used.
Use
CnnToFeedForwardPreProcessor for all new models instead. |
Modifier and Type | Method and Description |
---|---|
TransferLearning.GraphBuilder |
TransferLearning.GraphBuilder.addLayer(String layerName,
Layer layer,
InputPreProcessor preProcessor,
String... layerInputs)
Add a layer with a specified preprocessor
|
TransferLearning.Builder |
TransferLearning.Builder.setInputPreProcessor(int layer,
InputPreProcessor processor)
Specify the preprocessor for the added layers
for cases where they cannot be inferred automatically.
|
Copyright © 2020. All rights reserved.