Uses of Class
org.deeplearning4j.nn.multilayer.MultiLayerNetwork

Packages that use MultiLayerNetwork

Package	Description
org.deeplearning4j.earlystopping.saver
org.deeplearning4j.earlystopping.scorecalc.base
org.deeplearning4j.earlystopping.trainer
org.deeplearning4j.eval
org.deeplearning4j.gradientcheck
org.deeplearning4j.nn.multilayer
org.deeplearning4j.nn.transferlearning
org.deeplearning4j.nn.updater
org.deeplearning4j.optimize.listeners.checkpoint
org.deeplearning4j.util

Uses of MultiLayerNetwork in org.deeplearning4j.earlystopping.saver

Methods in org.deeplearning4j.earlystopping.saver that return MultiLayerNetwork

Modifier and Type	Method and Description
MultiLayerNetwork	LocalFileModelSaver.getBestModel()
MultiLayerNetwork	LocalFileModelSaver.getLatestModel()

Methods in org.deeplearning4j.earlystopping.saver with parameters of type MultiLayerNetwork

Modifier and Type	Method and Description
void	LocalFileModelSaver.saveBestModel(MultiLayerNetwork net, double score)
void	LocalFileModelSaver.saveLatestModel(MultiLayerNetwork net, double score)

Uses of MultiLayerNetwork in org.deeplearning4j.earlystopping.scorecalc.base

Methods in org.deeplearning4j.earlystopping.scorecalc.base with parameters of type MultiLayerNetwork

Modifier and Type	Method and Description
protected INDArray[]	BaseMLNScoreCalculator.output(MultiLayerNetwork network, INDArray[] input, INDArray[] fMask, INDArray[] lMask)
protected INDArray	BaseMLNScoreCalculator.output(MultiLayerNetwork network, INDArray input, INDArray fMask, INDArray lMask)
protected double	BaseMLNScoreCalculator.scoreMinibatch(MultiLayerNetwork network, INDArray[] features, INDArray[] labels, INDArray[] fMask, INDArray[] lMask, INDArray[] output)

Uses of MultiLayerNetwork in org.deeplearning4j.earlystopping.trainer

Constructors in org.deeplearning4j.earlystopping.trainer with parameters of type MultiLayerNetwork

Constructor and Description
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> esConfig, MultiLayerNetwork net, DataSetIterator train)
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> esConfig, MultiLayerNetwork net, DataSetIterator train, EarlyStoppingListener<MultiLayerNetwork> listener)

Constructor parameters in org.deeplearning4j.earlystopping.trainer with type arguments of type MultiLayerNetwork

Constructor and Description
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> earlyStoppingConfiguration, MultiLayerConfiguration configuration, DataSetIterator train)
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> esConfig, MultiLayerNetwork net, DataSetIterator train)
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> esConfig, MultiLayerNetwork net, DataSetIterator train, EarlyStoppingListener<MultiLayerNetwork> listener)
EarlyStoppingTrainer(EarlyStoppingConfiguration<MultiLayerNetwork> esConfig, MultiLayerNetwork net, DataSetIterator train, EarlyStoppingListener<MultiLayerNetwork> listener)

Uses of MultiLayerNetwork in org.deeplearning4j.eval

Methods in org.deeplearning4j.eval with parameters of type MultiLayerNetwork

Modifier and Type	Method and Description
void	Evaluation.eval(INDArray trueLabels, INDArray input, MultiLayerNetwork network) Evaluate the output using the given true labels, the input to the multi layer network and the multi layer network to use for evaluation

Uses of MultiLayerNetwork in org.deeplearning4j.gradientcheck

Methods in org.deeplearning4j.gradientcheck with parameters of type MultiLayerNetwork

Modifier and Type	Method and Description
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels) Check backprop gradients for a MultiLayerNetwork.
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask)
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam)
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam, Set<String> excludeParams)
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam, Set<String> excludeParams, Consumer<MultiLayerNetwork> callEachIter)
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam, Set<String> excludeParams, Integer rngSeedResetEachIter)

Method parameters in org.deeplearning4j.gradientcheck with type arguments of type MultiLayerNetwork

Modifier and Type	Method and Description
static boolean	GradientCheckUtil.checkGradients(MultiLayerNetwork mln, double epsilon, double maxRelError, double minAbsoluteError, boolean print, boolean exitOnFirstError, INDArray input, INDArray labels, INDArray inputMask, INDArray labelMask, boolean subset, int maxPerParam, Set<String> excludeParams, Consumer<MultiLayerNetwork> callEachIter)

Uses of MultiLayerNetwork in org.deeplearning4j.nn.multilayer

Methods in org.deeplearning4j.nn.multilayer that return MultiLayerNetwork

Modifier and Type	Method and Description
MultiLayerNetwork	MultiLayerNetwork.clone() Clones the multilayernetwork
static MultiLayerNetwork	MultiLayerNetwork.load(File f, boolean loadUpdater) Restore a MultiLayerNetwork to a file, saved using save(File) or ModelSerializer

Uses of MultiLayerNetwork in org.deeplearning4j.nn.transferlearning

Methods in org.deeplearning4j.nn.transferlearning that return MultiLayerNetwork

Modifier and Type	Method and Description
MultiLayerNetwork	TransferLearning.Builder.build() Returns a model with the fine tune configuration and specified architecture changes.
MultiLayerNetwork	TransferLearningHelper.unfrozenMLN() Returns the unfrozen layers of the MultiLayerNetwork as a multilayernetwork Note that with each call to featurizedFit the parameters to the original MLN are also updated

Constructors in org.deeplearning4j.nn.transferlearning with parameters of type MultiLayerNetwork

Constructor and Description
Builder(MultiLayerNetwork origModel) Multilayer Network to tweak for transfer learning
TransferLearningHelper(MultiLayerNetwork orig) Expects a MLN where some layers are frozen
TransferLearningHelper(MultiLayerNetwork orig, int frozenTill) Will modify the given MLN (in place!) to freeze layers (hold params constant during training) specified and below

Uses of MultiLayerNetwork in org.deeplearning4j.nn.updater

Constructors in org.deeplearning4j.nn.updater with parameters of type MultiLayerNetwork

Constructor and Description
MultiLayerUpdater(MultiLayerNetwork network)
MultiLayerUpdater(MultiLayerNetwork network, INDArray updaterState)

Uses of MultiLayerNetwork in org.deeplearning4j.optimize.listeners.checkpoint

Methods in org.deeplearning4j.optimize.listeners.checkpoint that return MultiLayerNetwork

Modifier and Type	Method and Description
MultiLayerNetwork	CheckpointListener.loadCheckpointMLN(Checkpoint checkpoint) Load a MultiLayerNetwork for the given checkpoint
MultiLayerNetwork	CheckpointListener.loadCheckpointMLN(int checkpointNum) Load a MultiLayerNetwork for the given checkpoint number

Uses of MultiLayerNetwork in org.deeplearning4j.util

Methods in org.deeplearning4j.util that return MultiLayerNetwork

Modifier and Type	Method and Description
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(File file) Load a multi layer network from a file
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(File file, boolean loadUpdater) Load a multi layer network from a file
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(InputStream is) Restore a multi layer network from an input stream * Note: the input stream is read fully and closed by this method.
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(InputStream is, boolean loadUpdater) Load a MultiLayerNetwork from InputStream from an input stream Note: the input stream is read fully and closed by this method.
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(String path) Load a MultilayerNetwork model from a file
static MultiLayerNetwork	ModelSerializer.restoreMultiLayerNetwork(String path, boolean loadUpdater) Load a MultilayerNetwork model from a file

Methods in org.deeplearning4j.util that return types with arguments of type MultiLayerNetwork

Modifier and Type	Method and Description
static Pair<MultiLayerNetwork,Normalizer>	ModelSerializer.restoreMultiLayerNetworkAndNormalizer(File file, boolean loadUpdater) Restore a MultiLayerNetwork and Normalizer (if present - null if not) from a File
static Pair<MultiLayerNetwork,Normalizer>	ModelSerializer.restoreMultiLayerNetworkAndNormalizer(InputStream is, boolean loadUpdater) Restore a MultiLayerNetwork and Normalizer (if present - null if not) from the InputStream.

Methods in org.deeplearning4j.util with parameters of type MultiLayerNetwork

Modifier and Type	Method and Description
static Double	NetworkUtils.getLearningRate(MultiLayerNetwork net, int layerNumber) Get the current learning rate, for the specified layer, fromthe network.
static void	NetworkUtils.setLearningRate(MultiLayerNetwork net, double newLr) Set the learning rate for all layers in the network to the specified value.
static void	NetworkUtils.setLearningRate(MultiLayerNetwork net, int layerNumber, double newLr) Set the learning rate for a single layer in the network to the specified value.
static void	NetworkUtils.setLearningRate(MultiLayerNetwork net, int layerNumber, ISchedule lrSchedule) Set the learning rate schedule for a single layer in the network to the specified value. Note also that NetworkUtils.setLearningRate(MultiLayerNetwork, ISchedule) should also be used in preference, when all layers need to be set to a new LR schedule. This schedule will replace any/all existing schedules, and also any fixed learning rate values. Note also that the iteration/epoch counts will not be reset.
static void	NetworkUtils.setLearningRate(MultiLayerNetwork net, ISchedule newLrSchedule) Set the learning rate schedule for all layers in the network to the specified schedule.
static ComputationGraph	NetworkUtils.toComputationGraph(MultiLayerNetwork net) Convert a MultiLayerNetwork to a ComputationGraph