com.intel.analytics.bigdl.nn

RecurrentDecoder

class RecurrentDecoder[T] extends Recurrent[T]

RecurrentDecoder module is a container of rnn cells that used to make a prediction of the next timestep based on the prediction we made from the previous timestep. Input for RecurrentDecoder is dynamically composed during training. input at t(i) is output at t(i-1), input at t(0) is user input, and user input has to be batch x stepShape(shape of the input at a single time step).

Different types of rnn cells can be added using add() function.

Linear Supertypes
Recurrent[T], DynamicContainer[Tensor[T], Tensor[T], T], Container[Tensor[T], Tensor[T], T], AbstractModule[Tensor[T], Tensor[T], T], InferShape, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. RecurrentDecoder
  2. Recurrent
  3. DynamicContainer
  4. Container
  5. AbstractModule
  6. InferShape
  7. Serializable
  8. Serializable
  9. AnyRef
  10. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new RecurrentDecoder(seqLength: Int)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    seqLength

    sequence length of the output

Value Members

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

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

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

    Definition Classes
    AnyRef
  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  6. var _input: Table

    Attributes
    protected
    Definition Classes
    Recurrent
  7. def accGradParameters(input: Tensor[T], gradOutput: Tensor[T]): Unit

    Computing the gradient of the module with respect to its own parameters.

    Computing the gradient of the module with respect to its own parameters. Many modules do not perform this step as they do not have any parameters. The state variable name for the parameters is module dependent. The module is expected to accumulate the gradients with respect to the parameters in some variable.

    input
    gradOutput

    Definition Classes
    RecurrentDecoderRecurrentAbstractModule
  8. def add(module: AbstractModule[_ <: Activity, _ <: Activity, T]): RecurrentDecoder.this.type

    modules: -- preTopology |- topology (cell)

    modules: -- preTopology |- topology (cell)

    The topology (or cell) will be cloned for N times w.r.t the time dimension. The preTopology will be execute only once before the recurrence.

    module

    module to be add

    returns

    this container

    Definition Classes
    RecurrentDecoderRecurrentDynamicContainer
  9. def apply(name: String): Option[AbstractModule[Activity, Activity, T]]

    Find a module with given name.

    Find a module with given name. If there is no module with given name, it will return None. If there are multiple modules with the given name, an exception will be thrown.

    name
    returns

    Definition Classes
    ContainerAbstractModule
  10. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  11. def backward(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

    Performs a back-propagation step through the module, with respect to the given input.

    Performs a back-propagation step through the module, with respect to the given input. In general this method makes the assumption forward(input) has been called before, with the same input. This is necessary for optimization reasons. If you do not respect this rule, backward() will compute incorrect gradients.

    input

    input data

    gradOutput

    gradient of next layer

    returns

    gradient corresponding to input data

    Definition Classes
    RecurrentDecoderRecurrentAbstractModule
  12. var backwardTime: Long

    Attributes
    protected
    Definition Classes
    AbstractModule
  13. val batchDim: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  14. var batchNormParams: BatchNormParams[T]

    Definition Classes
    Recurrent
  15. var batchSize: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  16. def canEqual(other: Any): Boolean

    Definition Classes
    RecurrentDecoderRecurrentContainerAbstractModule
  17. val cells: ArrayBuffer[Cell[T]]

    Attributes
    protected
    Definition Classes
    Recurrent
  18. final def checkEngineType(): RecurrentDecoder.this.type

    get execution engine type

    get execution engine type

    Definition Classes
    ContainerAbstractModule
  19. def clearState(): RecurrentDecoder.this.type

    Clear cached activities to save storage space or network bandwidth.

    Clear cached activities to save storage space or network bandwidth. Note that we use Tensor.set to keep some information like tensor share

    The subclass should override this method if it allocate some extra resource, and call the super.clearState in the override method

    returns

    Definition Classes
    RecurrentContainerAbstractModule
  20. final def clone(deepCopy: Boolean): AbstractModule[Tensor[T], Tensor[T], T]

    Clone the module, deep or shallow copy

    Clone the module, deep or shallow copy

    deepCopy
    returns

    Definition Classes
    AbstractModule
  21. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  22. def cloneCells(): Unit

    Attributes
    protected
    Definition Classes
    Recurrent
  23. final def cloneModule(): RecurrentDecoder.this.type

    Clone the model

    Clone the model

    returns

    Definition Classes
    AbstractModule
  24. val currentGradOutput: Table

    Attributes
    protected
    Definition Classes
    Recurrent
  25. var currentInput: Table

    Attributes
    protected
    Definition Classes
    Recurrent
  26. final def eq(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  27. def equals(other: Any): Boolean

    Definition Classes
    RecurrentDecoderRecurrentContainerAbstractModule → AnyRef → Any
  28. final def evaluate(): RecurrentDecoder.this.type

    Set the module to evaluate mode

    Set the module to evaluate mode

    returns

    Definition Classes
    ContainerAbstractModule
  29. final def evaluate(dataSet: LocalDataSet[MiniBatch[T]], vMethods: Array[_ <: ValidationMethod[T]]): Array[(ValidationResult, ValidationMethod[T])]

    use ValidationMethod to evaluate module on the given local dataset

    use ValidationMethod to evaluate module on the given local dataset

    dataSet
    vMethods
    returns

    Definition Classes
    AbstractModule
  30. final def evaluate(dataset: RDD[MiniBatch[T]], vMethods: Array[_ <: ValidationMethod[T]]): Array[(ValidationResult, ValidationMethod[T])]

    use ValidationMethod to evaluate module on the given rdd dataset

    use ValidationMethod to evaluate module on the given rdd dataset

    dataset
    vMethods
    returns

    Definition Classes
    AbstractModule
  31. final def evaluate(dataset: RDD[Sample[T]], vMethods: Array[_ <: ValidationMethod[T]], batchSize: Option[Int] = None): Array[(ValidationResult, ValidationMethod[T])]

    use ValidationMethod to evaluate module on the given rdd dataset

    use ValidationMethod to evaluate module on the given rdd dataset

    dataset

    dataset for test

    vMethods

    validation methods

    batchSize

    total batchsize of all partitions, optional param and default 4 * partitionNum of dataset

    returns

    Definition Classes
    AbstractModule
  32. final def evaluateImage(imageFrame: ImageFrame, vMethods: Array[_ <: ValidationMethod[T]], batchSize: Option[Int] = None): Array[(ValidationResult, ValidationMethod[T])]

    use ValidationMethod to evaluate module on the given ImageFrame

    use ValidationMethod to evaluate module on the given ImageFrame

    imageFrame

    ImageFrame for valudation

    vMethods

    validation methods

    batchSize

    total batch size of all partitions

    returns

    Definition Classes
    AbstractModule
  33. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  34. def findDropouts(cell: Cell[T]): Array[Dropout[T]]

    Definition Classes
    Recurrent
  35. def findModules(moduleType: String): ArrayBuffer[AbstractModule[_, _, T]]

    Definition Classes
    Container
  36. final def forward(input: Tensor[T]): Tensor[T]

    Takes an input object, and computes the corresponding output of the module.

    Takes an input object, and computes the corresponding output of the module. After a forward, the output state variable should have been updated to the new value.

    input

    input data

    returns

    output data

    Definition Classes
    AbstractModule
  37. var forwardTime: Long

    Attributes
    protected
    Definition Classes
    AbstractModule
  38. def freeze(names: String*): RecurrentDecoder.this.type

    freeze the module, i.

    freeze the module, i.e. their parameters(weight/bias, if exists) are not changed in training process if names is not empty, set an array of layers that match the given names to be "freezed",

    names

    an array of layer names

    returns

    current graph model

    Definition Classes
    ContainerAbstractModule
  39. def getCell(): Cell[T]

    Definition Classes
    Recurrent
  40. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  41. def getExtraParameter(): Array[Tensor[T]]

    Get extra parameter in this module.

    Get extra parameter in this module. Extra parameter means the trainable parameters beside weight and bias. Such as runningMean and runningVar in BatchNormalization.

    The subclass should override this method if it has some parameters besides weight and bias.

    returns

    an array of tensor

    Definition Classes
    ContainerAbstractModule
  42. def getHiddenState(): Activity

    Definition Classes
    Recurrent
  43. final def getInputShape(): Shape

    Return the inputShape for the current Layer and the first dim is batch.

    Return the inputShape for the current Layer and the first dim is batch.

    Definition Classes
    InferShape
  44. final def getName(): String

    Get the module name, default name is className@namePostfix

    Get the module name, default name is className@namePostfix

    returns

    Definition Classes
    AbstractModule
  45. final def getNumericType(): TensorDataType

    Get numeric type of module parameters

    Get numeric type of module parameters

    returns

    Definition Classes
    AbstractModule
  46. final def getOutputShape(): Shape

    Return the outputShape for the current Layer and the first dim is batch.

    Return the outputShape for the current Layer and the first dim is batch.

    Definition Classes
    InferShape
  47. def getParametersTable(): Table

    This function returns a table contains ModuleName, the parameter names and parameter value in this module.

    This function returns a table contains ModuleName, the parameter names and parameter value in this module.

    The result table is a structure of Table(ModuleName -> Table(ParameterName -> ParameterValue)), and the type is Table[String, Table[String, Tensor[T]]].

    For example, get the weight of a module named conv1: table[Table]("conv1")[Tensor[T]]("weight").

    The names of the parameters follow such convention:

    1. If there's one parameter, the parameter is named as "weight", the gradient is named as "gradWeight"

    2. If there're two parameters, the first parameter is named as "weight", the first gradient is named as "gradWeight"; the second parameter is named as "bias", the seconcd gradient is named as "gradBias"

    3. If there're more parameters, the weight is named as "weight" with a seq number as suffix, the gradient is named as "gradient" with a seq number as suffix

    Custom modules should override this function the default impl if the convention doesn't meet the requirement.

    returns

    Table

    Definition Classes
    RecurrentDecoderContainerAbstractModule
  48. final def getPrintName(): String

    Attributes
    protected
    Definition Classes
    AbstractModule
  49. final def getScaleB(): Double

    Get the scale of gradientBias

    Get the scale of gradientBias

    Definition Classes
    AbstractModule
  50. final def getScaleW(): Double

    Get the scale of gradientWeight

    Get the scale of gradientWeight

    Definition Classes
    AbstractModule
  51. def getTimes(): Array[(AbstractModule[_ <: Activity, _ <: Activity, T], Long, Long)]

    Get the forward/backward cost time for the module or its submodules

    Get the forward/backward cost time for the module or its submodules

    returns

    Definition Classes
    RecurrentContainerAbstractModule
  52. final def getTimesGroupByModuleType(): Array[(String, Long, Long)]

    Get the forward/backward cost time for the module or its submodules and group by module type.

    Get the forward/backward cost time for the module or its submodules and group by module type.

    returns

    (module type name, forward time, backward time)

    Definition Classes
    AbstractModule
  53. final def getWeightsBias(): Array[Tensor[T]]

    Get weight and bias for the module

    Get weight and bias for the module

    returns

    array of weights and bias

    Definition Classes
    AbstractModule
  54. var gradHidden: Activity

    Attributes
    protected
    Definition Classes
    Recurrent
  55. var gradInput: Tensor[T]

    The cached gradient of activities.

    The cached gradient of activities. So we don't compute it again when need it

    Definition Classes
    AbstractModule
  56. val gradInput2Cell: Tensor[T]

    Attributes
    protected
    Definition Classes
    Recurrent
  57. final def hasName: Boolean

    Whether user set a name to the module before

    Whether user set a name to the module before

    returns

    Definition Classes
    AbstractModule
  58. def hashCode(): Int

    Definition Classes
    RecurrentDecoderRecurrentContainerAbstractModule → AnyRef → Any
  59. val hidDim: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  60. var hidden: Activity

    Attributes
    protected
    Definition Classes
    Recurrent
  61. var hiddenShape: Array[Int]

    Attributes
    protected
    Definition Classes
    Recurrent
  62. def initHidden(sizes: Array[Int]): Unit

    Clone N models; N depends on the time dimension of the input

    Clone N models; N depends on the time dimension of the input

    Attributes
    protected
    Definition Classes
    Recurrent
  63. var initHiddenState: Activity

    Attributes
    protected
    Definition Classes
    Recurrent
  64. var input2Cell: Tensor[T]

    Attributes
    protected
    Definition Classes
    Recurrent
  65. val inputDim: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  66. def inputs(first: (ModuleNode[T], Int), nodesWithIndex: (ModuleNode[T], Int)*): ModuleNode[T]

    Build graph: some other modules point to current module

    Build graph: some other modules point to current module

    first

    distinguish from another inputs when input parameter list is empty

    nodesWithIndex

    upstream module nodes and the output tensor index. The start index is 1.

    returns

    node containing current module

    Definition Classes
    AbstractModule
  67. def inputs(nodes: Array[ModuleNode[T]]): ModuleNode[T]

    Build graph: some other modules point to current module

    Build graph: some other modules point to current module

    nodes

    upstream module nodes in an array

    returns

    node containing current module

    Definition Classes
    AbstractModule
  68. def inputs(nodes: ModuleNode[T]*): ModuleNode[T]

    Build graph: some other modules point to current module

    Build graph: some other modules point to current module

    nodes

    upstream module nodes

    returns

    node containing current module

    Definition Classes
    AbstractModule
  69. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  70. final def isTraining(): Boolean

    Check if the model is in training mode

    Check if the model is in training mode

    returns

    Definition Classes
    AbstractModule
  71. var line: String

    Attributes
    protected
    Definition Classes
    AbstractModule
  72. final def loadModelWeights(srcModel: Module[Float], matchAll: Boolean = true): RecurrentDecoder.this.type

    copy weights from another model, mapping by layer name

    copy weights from another model, mapping by layer name

    srcModel

    model to copy from

    matchAll

    whether to match all layers' weights and bias,

    returns

    current module

    Definition Classes
    AbstractModule
  73. final def loadWeights(weightPath: String, matchAll: Boolean = true): RecurrentDecoder.this.type

    load pretrained weights and bias to current module

    load pretrained weights and bias to current module

    weightPath

    file to store weights and bias

    matchAll

    whether to match all layers' weights and bias, if not, only load existing pretrained weights and bias

    returns

    current module

    Definition Classes
    AbstractModule
  74. var maskZero: Boolean

    Definition Classes
    Recurrent
  75. val modules: ArrayBuffer[AbstractModule[Activity, Activity, T]]

    Definition Classes
    Container
  76. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  77. final def notify(): Unit

    Definition Classes
    AnyRef
  78. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  79. var output: Tensor[T]

    The cached output.

    The cached output. So we don't compute it again when need it

    Definition Classes
    AbstractModule
  80. def parameters(): (Array[Tensor[T]], Array[Tensor[T]])

    This function returns two arrays.

    This function returns two arrays. One for the weights and the other the gradients Custom modules should override this function if they have parameters

    returns

    (Array of weights, Array of grad)

    Definition Classes
    RecurrentDecoderContainerAbstractModule
  81. var preTopology: AbstractModule[Activity, Activity, T]

    Attributes
    protected
    Definition Classes
    Recurrent
  82. final def predict(dataset: RDD[Sample[T]], batchSize: Int = 1, shareBuffer: Boolean = false): RDD[Activity]

    module predict, return the probability distribution

    module predict, return the probability distribution

    dataset

    dataset for prediction

    batchSize

    total batchSize for all partitions. if -1, default is 4 * partitionNumber of datatset

    shareBuffer

    whether to share same memory for each batch predict results

    Definition Classes
    AbstractModule
  83. final def predictClass(dataset: RDD[Sample[T]], batchSize: Int = 1): RDD[Int]

    module predict, return the predict label

    module predict, return the predict label

    dataset

    dataset for prediction

    batchSize

    total batchSize for all partitions. if -1, default is 4 * partitionNumber of dataset

    Definition Classes
    AbstractModule
  84. final def predictImage(imageFrame: ImageFrame, outputLayer: String = null, shareBuffer: Boolean = false, batchPerPartition: Int = 4, predictKey: String = ImageFeature.predict, featurePaddingParam: Option[PaddingParam[T]] = None): ImageFrame

    model predict images, return imageFrame with predicted tensor, if you want to call predictImage multiple times, it is recommended to use Predictor for DistributedImageFrame or LocalPredictor for LocalImageFrame

    model predict images, return imageFrame with predicted tensor, if you want to call predictImage multiple times, it is recommended to use Predictor for DistributedImageFrame or LocalPredictor for LocalImageFrame

    imageFrame

    imageFrame that contains images

    outputLayer

    if outputLayer is not null, the output of layer that matches outputLayer will be used as predicted output

    shareBuffer

    whether to share same memory for each batch predict results

    batchPerPartition

    batch size per partition, default is 4

    predictKey

    key to store predicted result

    featurePaddingParam

    featurePaddingParam if the inputs have variant size

    returns

    Definition Classes
    AbstractModule
  85. def processInputs(first: (ModuleNode[T], Int), nodesWithIndex: (ModuleNode[T], Int)*): ModuleNode[T]

    Attributes
    protected
    Definition Classes
    AbstractModule
  86. def processInputs(nodes: Seq[ModuleNode[T]]): ModuleNode[T]

    Attributes
    protected
    Definition Classes
    AbstractModule
  87. final def quantize(): Module[T]

    Quantize this module, which reduces the precision of the parameter.

    Quantize this module, which reduces the precision of the parameter. Get a higher speed with a little accuracy cost.

    returns

    Definition Classes
    AbstractModule
  88. def release(): Unit

    if the model contains native resources such as aligned memory, we should release it by manual.

    if the model contains native resources such as aligned memory, we should release it by manual. JVM GC can't release them reliably.

    Definition Classes
    ContainerAbstractModule
  89. def reset(): Unit

    Reset module parameters, which is re-initialize the parameter with given initMethod

    Reset module parameters, which is re-initialize the parameter with given initMethod

    Definition Classes
    RecurrentContainerAbstractModule
  90. def resetTimes(): Unit

    Reset the forward/backward record time for the module or its submodules

    Reset the forward/backward record time for the module or its submodules

    returns

    Definition Classes
    RecurrentContainerAbstractModule
  91. final def saveCaffe(prototxtPath: String, modelPath: String, useV2: Boolean = true, overwrite: Boolean = false): RecurrentDecoder.this.type

    Save this module to path in caffe readable format

    Save this module to path in caffe readable format

    prototxtPath
    modelPath
    useV2
    overwrite
    returns

    Definition Classes
    AbstractModule
  92. final def saveDefinition(path: String, overWrite: Boolean = false): RecurrentDecoder.this.type

    Save this module definition to path.

    Save this module definition to path.

    path

    path to save module, local file system, HDFS and Amazon S3 is supported. HDFS path should be like "hdfs://[host]:[port]/xxx" Amazon S3 path should be like "s3a://bucket/xxx"

    overWrite

    if overwrite

    returns

    self

    Definition Classes
    AbstractModule
  93. final def saveModule(path: String, weightPath: String = null, overWrite: Boolean = false): RecurrentDecoder.this.type

    Save this module to path with protobuf format

    Save this module to path with protobuf format

    path

    path to save module, local file system, HDFS and Amazon S3 is supported. HDFS path should be like "hdfs://[host]:[port]/xxx" Amazon S3 path should be like "s3a://bucket/xxx"

    weightPath

    where to store weight

    overWrite

    if overwrite

    returns

    self

    Definition Classes
    AbstractModule
  94. final def saveTF(inputs: Seq[(String, Seq[Int])], path: String, byteOrder: ByteOrder = ByteOrder.LITTLE_ENDIAN, dataFormat: TensorflowDataFormat = TensorflowDataFormat.NHWC): RecurrentDecoder.this.type

    Save this module to path in tensorflow readable format

    Save this module to path in tensorflow readable format

    inputs
    path
    byteOrder
    dataFormat
    returns

    Definition Classes
    AbstractModule
  95. final def saveTorch(path: String, overWrite: Boolean = false): RecurrentDecoder.this.type

    Save this module to path in torch7 readable format

    Save this module to path in torch7 readable format

    path
    overWrite
    returns

    Definition Classes
    AbstractModule
  96. final def saveWeights(path: String, overWrite: Boolean): Unit

    save weights and bias to file

    save weights and bias to file

    path

    file to save

    overWrite

    whether to overwrite or not

    Definition Classes
    AbstractModule
  97. var scaleB: Double

    Attributes
    protected
    Definition Classes
    AbstractModule
  98. var scaleW: Double

    The scale of gradient weight and gradient bias before gradParameters being accumulated.

    The scale of gradient weight and gradient bias before gradParameters being accumulated.

    Attributes
    protected
    Definition Classes
    AbstractModule
  99. val seqLength: Int

    sequence length of the output

  100. final def setExtraParameter(extraParam: Array[Tensor[T]]): RecurrentDecoder.this.type

    Set extra parameter to this module.

    Set extra parameter to this module. Extra parameter means the trainable parameters beside weight and bias. Such as runningMean and runningVar in BatchNormalization.

    returns

    this

    Definition Classes
    AbstractModule
  101. def setHiddenState(hiddenState: Activity): Unit

    Definition Classes
    Recurrent
  102. final def setLine(line: String): RecurrentDecoder.this.type

    Set the line separator when print the module

    Set the line separator when print the module

    line
    returns

    Definition Classes
    AbstractModule
  103. final def setName(name: String): RecurrentDecoder.this.type

    Set the module name

    Set the module name

    name
    returns

    Definition Classes
    AbstractModule
  104. def setScaleB(b: Double): RecurrentDecoder.this.type

    Set the scale of gradientBias

    Set the scale of gradientBias

    b

    the value of the scale of gradientBias

    returns

    this

    Definition Classes
    ContainerAbstractModule
  105. def setScaleW(w: Double): RecurrentDecoder.this.type

    Set the scale of gradientWeight

    Set the scale of gradientWeight

    w

    the value of the scale of gradientWeight

    returns

    this

    Definition Classes
    ContainerAbstractModule
  106. final def setWeightsBias(newWeights: Array[Tensor[T]]): RecurrentDecoder.this.type

    Set weight and bias for the module

    Set weight and bias for the module

    newWeights

    array of weights and bias

    returns

    Definition Classes
    AbstractModule
  107. def share(cells: ArrayBuffer[Cell[T]]): Unit

    Sharing weights, bias, gradWeights across all the cells in time dim

    Sharing weights, bias, gradWeights across all the cells in time dim

    cells

    Definition Classes
    Recurrent
  108. val stepGradBuffer: Tensor[T]

    Attributes
    protected
    Definition Classes
    Recurrent
  109. val stepInput2CellBuf: Tensor[T]

    Attributes
    protected
    Definition Classes
    Recurrent
  110. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  111. val timeDim: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  112. var times: Int

    Attributes
    protected
    Definition Classes
    Recurrent
  113. def toGraph(startNodes: ModuleNode[T]*): Graph[T]

    Generate graph module with start nodes

    Generate graph module with start nodes

    startNodes
    returns

    Definition Classes
    AbstractModule
  114. def toString(): String

    Definition Classes
    RecurrentAbstractModule → AnyRef → Any
  115. var topology: Cell[T]

    Attributes
    protected
    Definition Classes
    Recurrent
  116. var train: Boolean

    Module status.

    Module status. It is useful for modules like dropout/batch normalization

    Attributes
    protected
    Definition Classes
    AbstractModule
  117. final def training(): RecurrentDecoder.this.type

    Set the module to training mode

    Set the module to training mode

    returns

    Definition Classes
    ContainerAbstractModule
  118. def unFreeze(names: String*): RecurrentDecoder.this.type

    "unfreeze" module, i.

    "unfreeze" module, i.e. make the module parameters(weight/bias, if exists) to be trained(updated) in training process if names is not empty, unfreeze layers that match given names

    names

    array of module names to unFreeze

    Definition Classes
    ContainerAbstractModule
  119. def updateGradInput(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

    Computing the gradient of the module with respect to its own input.

    Computing the gradient of the module with respect to its own input. This is returned in gradInput. Also, the gradInput state variable is updated accordingly.

    input
    gradOutput
    returns

    Definition Classes
    RecurrentDecoderRecurrentAbstractModule
  120. def updateOutput(input: Tensor[T]): Tensor[T]

    Computes the output using the current parameter set of the class and input.

    Computes the output using the current parameter set of the class and input. This function returns the result which is stored in the output field.

    input
    returns

    Definition Classes
    RecurrentDecoderRecurrentAbstractModule
  121. final def wait(): Unit

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  124. def zeroGradParameters(): Unit

    If the module has parameters, this will zero the accumulation of the gradients with respect to these parameters.

    If the module has parameters, this will zero the accumulation of the gradients with respect to these parameters. Otherwise, it does nothing.

    Definition Classes
    AbstractModule

Deprecated Value Members

  1. final def save(path: String, overWrite: Boolean = false): RecurrentDecoder.this.type

    Save this module to path.

    Save this module to path.

    path

    path to save module, local file system, HDFS and Amazon S3 is supported. HDFS path should be like "hdfs://[host]:[port]/xxx" Amazon S3 path should be like "s3a://bucket/xxx"

    overWrite

    if overwrite

    returns

    self

    Definition Classes
    AbstractModule
    Annotations
    @deprecated
    Deprecated

    (Since version 0.3.0) please use recommended saveModule(path, overWrite)

Inherited from Recurrent[T]

Inherited from DynamicContainer[Tensor[T], Tensor[T], T]

Inherited from Container[Tensor[T], Tensor[T], T]

Inherited from AbstractModule[Tensor[T], Tensor[T], T]

Inherited from InferShape

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped