Package | Description |
---|---|
org.deeplearning4j.nn.conf | |
org.deeplearning4j.nn.conf.module | |
org.deeplearning4j.zoo.model | |
org.deeplearning4j.zoo.model.helper |
Modifier and Type | Method and Description |
---|---|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.addInputs(Collection<String> inputNames)
Specify the inputs to the network, and their associated labels.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.addInputs(String... inputNames)
Specify the inputs to the network, and their associated labels.
|
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.addLayer(String layerName,
Layer layer,
String... layerInputs)
Add a layer, with no
InputPreProcessor , with the specified name and specified inputs. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.addVertex(String vertexName,
GraphVertex vertex,
String... vertexInputs)
Add a
GraphVertex to the network configuration. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.allowDisconnected(boolean allowDisconnected)
Used only during validation after building.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.allowNoOutput(boolean allowNoOutput)
Used only during validation after building.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.appendLayer(String layerName,
Layer layer)
Add a layer, with no
InputPreProcessor , with the specified name
and input from the last added layer/vertex. |
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. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.appendVertex(String vertexName,
GraphVertex vertex)
Add a
GraphVertex to the network configuration, with input from the last added vertex/layer. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.backpropType(BackpropType type)
The type of backprop.
|
ComputationGraphConfiguration.GraphBuilder |
NeuralNetConfiguration.Builder.graphBuilder()
Create a GraphBuilder (for creating a ComputationGraphConfiguration).
|
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(int layerName,
Layer layer,
String... layerInputs)
Add a layer, with no
InputPreProcessor , with the specified name and specified inputs. |
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. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.layer(String layerName,
Layer layer,
String... layerInputs)
Add a layer, with no
InputPreProcessor , with the specified name and specified inputs. |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.removeVertex(String vertexName)
Intended for use with the transfer learning API.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.removeVertex(String vertexName,
boolean removeConnections)
Intended for use with the transfer learning API.
|
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(). |
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.setOutputs(String... outputNames)
Set the network output labels.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.tBPTTBackwardLength(int backwardLength)
When doing truncated BPTT: how many steps of backward should we do?
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.tBPTTForwardLength(int forwardLength)
When doing truncated BPTT: how many steps of forward pass should we do
before doing (truncated) backprop?
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.tBPTTLength(int tbpttLength)
When doing truncated backpropagation through time (tBPTT): how many steps should we do?
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.validateOutputLayerConfig(boolean validate)
Enabled by default.
|
ComputationGraphConfiguration.GraphBuilder |
ComputationGraphConfiguration.GraphBuilder.validateTbpttConfig(boolean validate)
Enabled by default.
|
Modifier and Type | Method and Description |
---|---|
ComputationGraphConfiguration.GraphBuilder |
GraphBuilderModule.updateBuilder(ComputationGraphConfiguration.GraphBuilder graph,
String layerName,
int inputSize,
int[][] config,
String inputLayer)
Add a layer to the collection of layers being generated by this module.
|
Modifier and Type | Method and Description |
---|---|
ComputationGraphConfiguration.GraphBuilder |
GraphBuilderModule.updateBuilder(ComputationGraphConfiguration.GraphBuilder graph,
String layerName,
int inputSize,
int[][] config,
String inputLayer)
Add a layer to the collection of layers being generated by this module.
|
Modifier and Type | Method and Description |
---|---|
ComputationGraphConfiguration.GraphBuilder |
NASNet.graphBuilder() |
ComputationGraphConfiguration.GraphBuilder |
ResNet50.graphBuilder() |
ComputationGraphConfiguration.GraphBuilder |
SqueezeNet.graphBuilder() |
ComputationGraphConfiguration.GraphBuilder |
UNet.graphBuilder() |
ComputationGraphConfiguration.GraphBuilder |
Xception.graphBuilder() |
ComputationGraphConfiguration.GraphBuilder |
InceptionResNetV1.graphBuilder(String input) |
Modifier and Type | Method and Description |
---|---|
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
int filterSize,
int nIn,
int nOut,
int poolSize) |
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
int filterSize,
int nIn,
int nOut,
int poolSize,
int poolStride) |
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
String input,
int filterSize,
int nIn,
int nOut,
int poolSize,
int poolStride) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int pNorm,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int poolSize,
int poolStride,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int pNorm,
int poolSize,
int poolStride,
Activation transferFunction,
String inputLayer)
Appends inception layer configurations a GraphBuilder object, based on the concept of
Inception via the GoogleLeNet paper: https://arxiv.org/abs/1409.4842
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResA(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet A to a computation graph.
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResB(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet B to a computation graph.
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResC(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet C to a computation graph.
|
Modifier and Type | Method and Description |
---|---|
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
int filterSize,
int nIn,
int nOut,
int poolSize) |
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
int filterSize,
int nIn,
int nOut,
int poolSize,
int poolStride) |
static ComputationGraphConfiguration.GraphBuilder |
DarknetHelper.addLayers(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int layerNumber,
String input,
int filterSize,
int nIn,
int nOut,
int poolSize,
int poolStride) |
static String |
NASNetHelper.adjustBlock(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int filters,
String blockId,
String input) |
static String |
NASNetHelper.adjustBlock(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int filters,
String blockId,
String input,
String inputToMatch) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int pNorm,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int poolSize,
int poolStride,
Activation transferFunction,
String inputLayer) |
static ComputationGraphConfiguration.GraphBuilder |
FaceNetHelper.appendGraph(ComputationGraphConfiguration.GraphBuilder graph,
String moduleLayerName,
int inputSize,
int[] kernelSize,
int[] kernelStride,
int[] outputSize,
int[] reduceSize,
SubsamplingLayer.PoolingType poolingType,
int pNorm,
int poolSize,
int poolStride,
Activation transferFunction,
String inputLayer)
Appends inception layer configurations a GraphBuilder object, based on the concept of
Inception via the GoogleLeNet paper: https://arxiv.org/abs/1409.4842
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResA(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet A to a computation graph.
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResB(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet B to a computation graph.
|
static ComputationGraphConfiguration.GraphBuilder |
InceptionResNetHelper.inceptionV1ResC(ComputationGraphConfiguration.GraphBuilder graph,
String blockName,
int scale,
double activationScale,
String input)
Append Inception-ResNet C to a computation graph.
|
static Pair<String,String> |
NASNetHelper.normalA(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int filters,
String blockId,
String inputX,
String inputP) |
static Pair<String,String> |
NASNetHelper.reductionA(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int filters,
String blockId,
String inputX,
String inputP) |
static String |
NASNetHelper.sepConvBlock(ComputationGraphConfiguration.GraphBuilder graphBuilder,
int filters,
int kernelSize,
int stride,
String blockId,
String input) |
Copyright © 2020. All rights reserved.