Uses of Class
org.deeplearning4j.nn.conf.MultiLayerConfiguration.Builder

Packages that use MultiLayerConfiguration.Builder

Package	Description
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.layers.setup

Uses of MultiLayerConfiguration.Builder in org.deeplearning4j.nn.conf

Subclasses of MultiLayerConfiguration.Builder in org.deeplearning4j.nn.conf

Modifier and Type	Class and Description
static class	NeuralNetConfiguration.ListBuilder Fluent interface for building a list of configurations

Methods in org.deeplearning4j.nn.conf that return MultiLayerConfiguration.Builder

Modifier and Type	Method and Description
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.backprop(boolean backprop) Whether to do back prop or not
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.backpropType(BackpropType type) The type of backprop.
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.cnnInputSize(int[] cnnInputSize) Deprecated. use setInputType(InputType) with InputType.convolutional(height,width,depth), for CNN data with shape [minibatchSize,depth,height,width]. For image data that has been flattened into a row vector per example (shape [minibatchSize,depth*height*width]) instead use InputType.convolutionalFlat(height,width,depth)
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.cnnInputSize(int height, int width, int depth) Deprecated. use setInputType(InputType) with InputType.convolutional(height,width,depth), for CNN data with shape [minibatchSize,depth,height,width]. For image data that has been flattened into a row vector per example (shape [minibatchSize,depth*height*width]) instead use InputType.convolutionalFlat(height,width,depth)
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.confs(List<NeuralNetConfiguration> confs)
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.inputPreProcessor(Integer layer, InputPreProcessor processor) Specify the processors.
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.inputPreProcessors(Map<Integer,InputPreProcessor> processors)
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.pretrain(boolean pretrain) Whether to do pre train or not
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.setInputType(InputType inputType)
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.tBPTTBackwardLength(int backwardLength) When doing truncated BPTT: how many steps of backward should we do? Only applicable when doing backpropType(BackpropType.TruncatedBPTT) This is the k2 parameter on pg23 of http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf
MultiLayerConfiguration.Builder	MultiLayerConfiguration.Builder.tBPTTForwardLength(int forwardLength) When doing truncated BPTT: how many steps of forward pass should we do before doing (truncated) backprop? Only applicable when doing backpropType(BackpropType.TruncatedBPTT) Typically tBPTTForwardLength parameter is same as the tBPTTBackwardLength parameter, but may be larger than it in some circumstances (but never smaller) Ideally your training data time series length should be divisible by this This is the k1 parameter on pg23 of http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf

Uses of MultiLayerConfiguration.Builder in org.deeplearning4j.nn.conf.layers.setup

Fields in org.deeplearning4j.nn.conf.layers.setup declared as MultiLayerConfiguration.Builder

Modifier and Type	Field and Description
protected MultiLayerConfiguration.Builder	ConvolutionLayerSetup.conf Deprecated.

Methods in org.deeplearning4j.nn.conf.layers.setup with parameters of type MultiLayerConfiguration.Builder

Modifier and Type	Method and Description
Layer	ConvolutionLayerSetup.getLayer(int i, MultiLayerConfiguration.Builder builder) Deprecated.

Constructors in org.deeplearning4j.nn.conf.layers.setup with parameters of type MultiLayerConfiguration.Builder

Constructor and Description

ConvolutionLayerSetup(MultiLayerConfiguration.Builder builder, int height, int width, int channels) Deprecated. Use setInputType(InputType) to set nIns and add preprocessors as required. This can be done using builder.setInputType(InputType.convolutional(height, width, channels)) For image data that has been flattened into a row vector per example (shape [minibatchSize,depth*height*width]) instead use InputType.convolutionalFlat(height,width,depth).