Class

com.github.nearbydelta.deepspark.network

GeneralNetwork

Related Doc: package network

Permalink

class GeneralNetwork[In, Out] extends Network[In, Out]

Network with general input

In

Input type

Out

Output type

Linear Supertypes
Network[In, Out], KryoSerializable, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. GeneralNetwork
  2. Network
  3. KryoSerializable
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Visibility
  1. Public
  2. All

Instance Constructors

  1. new GeneralNetwork(inputLayer: InputLayer[In, _])

    Permalink

    inputLayer

    Input layer

  2. new GeneralNetwork()

    Permalink
    Annotations
    @deprecated
    Deprecated

    This is for kryo deserialization. Please use this(inputlayer)

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 NOut: Int

    Permalink

    Size of output

    Size of output

    returns

    Output size

    Definition Classes
    GeneralNetworkNetwork
  5. final def add(layer: Layer[DataVec, DataVec]): GeneralNetwork.this.type

    Permalink

    Add new top layer.

    Add new top layer.

    layer

    Layer to be added on top of current stack.

    returns

    self

    Definition Classes
    Network
  6. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  7. def backward(error: ParSeq[DataVec]): ArrayBuffer[() ⇒ Unit]

    Permalink

    Execute error backpropagation

    Execute error backpropagation

    Definition Classes
    GeneralNetworkNetwork
  8. final def backwardSeq(err: ParSeq[DataVec]): (ParSeq[DataVec], ArrayBuffer[() ⇒ Unit])

    Permalink

    Backpropagate errors

    Backpropagate errors

    err

    Top-level error to be propagated backward.

    returns

    lowest-level error sequence.

    Attributes
    protected
    Definition Classes
    Network
  9. def broadcast(sc: SparkContext): Unit

    Permalink

    Broadcast resources of input layer.

    Broadcast resources of input layer.

    sc

    Spark Context

    Definition Classes
    GeneralNetworkNetwork
  10. var builder: WeightBuilder

    Permalink

    Weight builder for this network.

    Weight builder for this network. *

    Attributes
    protected
    Definition Classes
    Network
  11. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  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 forward(in: RDD[(Long, In)]): RDD[(Long, DataVec)]

    Permalink

    Apply this network.

    Apply this network.

    in

    RDD of (ID, Value).

    returns

    RDD of (ID, Output vector).

    Definition Classes
    GeneralNetworkNetwork
  16. def forward(in: ParSeq[In]): ParSeq[DataVec]

    Permalink

    Apply this network.

    Apply this network.

    in

    Parallel Sequence of input

    returns

    Sequence of Output vector.

    Definition Classes
    GeneralNetworkNetwork
  17. def forward(in: In): DataVec

    Permalink

    Apply this network.

    Apply this network.

    in

    input

    returns

    Output vector.

    Definition Classes
    GeneralNetworkNetwork
  18. final def forwardRDD(in: RDD[(Long, DataVec)], layers: Seq[Layer[DataVec, DataVec]] = layerSeq): RDD[(Long, DataVec)]

    Permalink

    Apply by layers.

    Apply by layers.

    in

    RDD of (ID, Vector)

    layers

    Sequence of layers to be applied. Default value is layer sequence.

    returns

    RDD of final output (ID, Output Vector)

    Attributes
    protected
    Definition Classes
    Network
    Annotations
    @tailrec()
  19. final def forwardSeq(in: ParSeq[DataVec]): ParSeq[DataVec]

    Permalink

    Apply by layers.

    Apply by layers.

    in

    Parallel sequence of Vector

    returns

    Parallel sequence of final output

    Attributes
    protected
    Definition Classes
    Network
  20. final def forwardSingle(in: DataVec, layers: Seq[Layer[DataVec, DataVec]] = layerSeq): DataVec

    Permalink

    Apply by layers.

    Apply by layers.

    in

    Vector

    layers

    Sequence of layers to be applied. Default value is layer sequence.

    returns

    Final output Output Vector

    Attributes
    protected
    Definition Classes
    Network
    Annotations
    @tailrec()
  21. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  22. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  23. def initiateBy(builder: WeightBuilder): GeneralNetwork.this.type

    Permalink

    Initiate this network by given builder

    Initiate this network by given builder

    builder

    Weight builder

    returns

    self

    Definition Classes
    GeneralNetworkNetwork
  24. var inputLayer: InputLayer[In, _]

    Permalink

    Input layer

  25. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  26. val layerSeq: ListBuffer[Layer[DataVec, DataVec]]

    Permalink

    Seqeunce of hidden/output layer to be applied.

    Seqeunce of hidden/output layer to be applied. *

    Attributes
    protected
    Definition Classes
    Network
  27. def layers: Seq[Layer[DataVec, DataVec]]

    Permalink

    Sequence of hidden/output layers

    Sequence of hidden/output layers

    returns

    Sequence of hidden/output layer

    Definition Classes
    Network
  28. def loss: Double

    Permalink

    Weight loss of layers

    Weight loss of layers

    returns

    Weight loss

    Definition Classes
    GeneralNetworkNetwork
  29. final def ne(arg0: AnyRef): Boolean

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

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

    Permalink
    Definition Classes
    AnyRef
  32. def predictSoft(in: In): DataVec

    Permalink

    Apply this network.

    Apply this network.

    in

    input

    returns

    Output vector.

    Definition Classes
    Network
  33. def predictSoft(in: RDD[In])(implicit arg0: ClassTag[DataVec]): RDD[DataVec]

    Permalink

    Apply this network.

    Apply this network.

    in

    RDD of Value.

    returns

    RDD of Output vector.

    Definition Classes
    Network
  34. def read(kryo: Kryo, input: Input): Unit

    Permalink
    Definition Classes
    GeneralNetworkNetwork → KryoSerializable
  35. def saveTo(file: String): Unit

    Permalink

    Save this network.

    Save this network.

    file

    Save path of this network.

    Definition Classes
    Network
  36. def setUpdatable(bool: Boolean): Network[In, Out]

    Permalink

    Set this network can be used in backpropagation.

    Set this network can be used in backpropagation.

    bool

    True if this should prepare backpropagation

    returns

    self

    Definition Classes
    GeneralNetworkNetwork
  37. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  38. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  39. def unbroadcast(): Unit

    Permalink

    Unpersist resources of input layer.

    Unpersist resources of input layer.

    Definition Classes
    GeneralNetworkNetwork
  40. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  43. def write(kryo: Kryo, output: Output): Unit

    Permalink
    Definition Classes
    GeneralNetworkNetwork → KryoSerializable

Inherited from Network[In, Out]

Inherited from KryoSerializable

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped