Uses of Class
deepnetts.net.NeuralNetwork

Packages that use NeuralNetwork

Package	Description
deepnetts.automl	Support for automatically building deep learning models using hyper-parameter search.
deepnetts.eval	Evaluation procedures for machine learning models, used to estimate how good models are performing when given new data that (that was not used for training).
deepnetts.net	Neural network architectures with their corresponding builders.
deepnetts.net.loss	Commonly used loss functions, which are used to calculate error during the training as a difference between predicted and target output.
deepnetts.net.train	Training algorithms and related utilities.
deepnetts.util	Various utility classes including Tensor, image operations, multithreading, exceptions etc.

Uses of NeuralNetwork in deepnetts.automl

Classes in deepnetts.automl with type parameters of type NeuralNetwork

Modifier and Type	Interface and Description
interface	NetworkFactory<T extends NeuralNetwork> Base interface for all network factories.

Methods in deepnetts.automl that return NeuralNetwork

Modifier and Type	Method and Description
NeuralNetwork	HyperParameterSearch.getNetwork()

Methods in deepnetts.automl that return types with arguments of type NeuralNetwork

Modifier and Type	Method and Description
javax.visrec.ml.eval.Evaluator<NeuralNetwork,javax.visrec.ml.data.DataSet<? extends MLDataItem>>	HyperParameterSearch.getEvaluator()

Method parameters in deepnetts.automl with type arguments of type NeuralNetwork

Modifier and Type	Method and Description
HyperParameterSearch	HyperParameterSearch.evaluator(javax.visrec.ml.eval.Evaluator<NeuralNetwork,javax.visrec.ml.data.DataSet<? extends MLDataItem>> evaluator)

Uses of NeuralNetwork in deepnetts.eval

Methods in deepnetts.eval with parameters of type NeuralNetwork

Modifier and Type	Method and Description
ClassificationMetrics	ClassifierEvaluator.evaluate(NeuralNetwork neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) Performs classifier evaluation and returns classification performance metrics.
javax.visrec.ml.eval.EvaluationMetrics	RegresionEvaluator.evaluate(NeuralNetwork neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)
static ClassificationMetrics	Evaluators.evaluateClassifier(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet)
static RegressionMetrics	Evaluators.evaluateRegressor(NeuralNetwork<?> neuralNet, javax.visrec.ml.data.DataSet<? extends MLDataItem> testSet) Evaluates specified neural network with test set, as a regression model and returns basic regression evauation metrics.

Uses of NeuralNetwork in deepnetts.net

Subclasses of NeuralNetwork in deepnetts.net

Modifier and Type	Class and Description
class	ConvolutionalNetwork Convolutional neural network is an extension of feed forward network, which can include 2D and 3D adaptive preprocessing layers (Convolutional and MaxPooling layer), which is specialized to learn to recognize features in images.
class	FeedForwardNetwork Feed forward neural network architecture, also known as Multi Layer Perceptron.

Uses of NeuralNetwork in deepnetts.net.loss

Methods in deepnetts.net.loss with parameters of type NeuralNetwork

Modifier and Type	Method and Description
default float	LossFunction.valueFor(NeuralNetwork nnet, javax.visrec.ml.data.DataSet<? extends MLDataItem> dataSet) Calculates and returns loss function value for the given neural network and data set.

Constructors in deepnetts.net.loss with parameters of type NeuralNetwork

Constructor and Description
BinaryCrossEntropyLoss(NeuralNetwork neuralNet)
CrossEntropyLoss(NeuralNetwork neuralNet)
MeanSquaredErrorLoss(NeuralNetwork neuralNet) Creates a new mean squared error loss for the given neural network.

Uses of NeuralNetwork in deepnetts.net.train

Methods in deepnetts.net.train that return NeuralNetwork

Modifier and Type	Method and Description
NeuralNetwork	KFoldCrossValidation.getBestNetwork()
NeuralNetwork<?>	BackpropagationTrainer.getNeuralNetwork() Returns a neural network trained by this trainer.

Methods in deepnetts.net.train with parameters of type NeuralNetwork

Modifier and Type	Method and Description
KFoldCrossValidation.Builder	KFoldCrossValidation.Builder.model(NeuralNetwork neuralNet)

Method parameters in deepnetts.net.train with type arguments of type NeuralNetwork

Modifier and Type	Method and Description
KFoldCrossValidation.Builder	KFoldCrossValidation.Builder.evaluator(javax.visrec.ml.eval.Evaluator<NeuralNetwork,javax.visrec.ml.data.DataSet<? extends MLDataItem>> evaluator)

Constructors in deepnetts.net.train with parameters of type NeuralNetwork

Constructor and Description
BackpropagationTrainer(NeuralNetwork neuralNet) Creates an instance of BackpropagationTrainer for the given neural network to train.

Uses of NeuralNetwork in deepnetts.util

Methods in deepnetts.util that return NeuralNetwork

Modifier and Type	Method and Description
static NeuralNetwork	FileIO.createFromFile(File file)
static NeuralNetwork	FileIO.createFromJson(File file)
static NeuralNetwork	FileIO.createFromJson(org.json.JSONObject jsonObj)
static NeuralNetwork	FileIO.createFromJson(String jsonStr)

Methods in deepnetts.util with parameters of type NeuralNetwork

Modifier and Type	Method and Description
static void	TensorflowUtils.importWeights(NeuralNetwork network, String weightsFileName)
static String	FileIO.toJson(NeuralNetwork<?> nnet) Returns JSON representation of specified neural network object.
static void	FileIO.writeToFile(NeuralNetwork neuralNet, String fileName) Serializes specified neural network to file with specified file.
static void	FileIO.writeToFileAsJson(NeuralNetwork neuralNet, String fileName)