Class/Object

org.deeplearning4j.scalnet.models

NeuralNet

Related Docs: object NeuralNet | package models

Permalink

class NeuralNet extends Model

Simple DL4J-style sequential neural net architecture with one input node and one output node for each node in computational graph.

Wraps DL4J MultiLayerNetwork. Enforces DL4J model construction pattern: adds pre-processing layers automatically but requires user to specify output layer explicitly.

Linear Supertypes
Model, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. NeuralNet
  2. Model
  3. AnyRef
  4. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new NeuralNet(inputType: Option[InputType] = None, rngSeed: Long = 0)

    Permalink

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  4. def add(layer: Node): Unit

    Permalink
  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  6. def buildModelConfig(optimizer: Optimizer, seed: Long): Builder

    Permalink

    Build model configuration from optimizer and seed.

    Build model configuration from optimizer and seed.

    optimizer

    optimization algorithm to use in model

    seed

    seed to use

    returns

    NeuralNetConfiguration.Builder

    Definition Classes
    Model
  7. def buildOutput(lossFunction: LossFunction): Unit

    Permalink

    Make last layer of architecture an output layer using the provided loss function.

    Make last layer of architecture an output layer using the provided loss function.

    lossFunction

    loss function to use

    Definition Classes
    Model
  8. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  9. def compile(lossFunction: LossFunction, optimizer: Optimizer = defaultOptimizer): Unit

    Permalink

    Compile neural net architecture.

    Compile neural net architecture. Call immediately before training.

    lossFunction

    loss function to use

    optimizer

    optimization algorithm to use

    Definition Classes
    NeuralNetModel
  10. val defaultEpochs: Int

    Permalink
    Attributes
    protected
    Definition Classes
    Model
  11. val defaultOptimizer: SGD

    Permalink
    Attributes
    protected
    Definition Classes
    Model
  12. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  13. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  14. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  15. def fit(iter: DataSetIterator, nbEpoch: Int = defaultEpochs, listeners: List[IterationListener]): Unit

    Permalink

    Fit neural net to data.

    Fit neural net to data.

    iter

    iterator over data set

    nbEpoch

    number of epochs to train

    listeners

    callbacks for monitoring training

    Definition Classes
    NeuralNetModel
  16. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  17. def getLayers: List[Node]

    Permalink
    Definition Classes
    Model
  18. def getNetwork: MultiLayerNetwork

    Permalink
    Definition Classes
    Model
  19. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  20. val inputType: Option[InputType]

    Permalink
  21. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  22. var layers: List[Node]

    Permalink
    Attributes
    protected
    Definition Classes
    Model
  23. var model: MultiLayerNetwork

    Permalink
    Attributes
    protected
    Definition Classes
    Model
  24. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  25. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  26. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  27. def predict(x: DataSet): INDArray

    Permalink

    Use neural net to make prediction on input x.

    Use neural net to make prediction on input x.

    x

    input represented as DataSet

    Definition Classes
    Model
  28. def predict(x: INDArray): INDArray

    Permalink

    Use neural net to make prediction on input x

    Use neural net to make prediction on input x

    x

    input represented as INDArray

    Definition Classes
    Model
  29. val rngSeed: Long

    Permalink
  30. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  31. def toJson: String

    Permalink
    Definition Classes
    Model
  32. def toString(): String

    Permalink
    Definition Classes
    Model → AnyRef → Any
  33. def toYaml: String

    Permalink
    Definition Classes
    Model
  34. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  35. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  36. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Model

Inherited from AnyRef

Inherited from Any

Ungrouped