com.intel.analytics.bigdl.nn

ConvLSTMPeephole3D

class ConvLSTMPeephole3D[T] extends Cell[T]

Convolution Long Short Term Memory architecture with peephole. Ref. A.: https://arxiv.org/abs/1506.04214 (blueprint for this module) B. https://github.com/viorik/ConvLSTM

Linear Supertypes
Cell[T], AbstractModule[Table, Table, T], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. ConvLSTMPeephole3D
  2. Cell
  3. AbstractModule
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ConvLSTMPeephole3D(inputSize: Int, outputSize: Int, kernelI: Int, kernelC: Int, stride: Int = 1, padding: Int = -1, wRegularizer: Regularizer[T] = null, uRegularizer: Regularizer[T] = null, bRegularizer: Regularizer[T] = null, cRegularizer: Regularizer[T] = null, withPeephole: Boolean = true)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    inputSize

    number of input planes in the image given into forward()

    outputSize

    number of output planes the convolution layer will produce

    kernelI

    Convolutional filter size to convolve input

    kernelC

    Convolutional filter size to convolve cell

    stride

    The step of the convolution

    padding

    The step of the convolution, default is -1, behaves same with SAME padding in tensorflow. Default stride,padding ensure last 3 dim of output shape is the same with input

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. def accGradParameters(input: Table, gradOutput: Table): 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
    CellAbstractModule
  7. def addTimes(other: Cell[T]): Unit

    Definition Classes
    Cell
  8. 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
    AbstractModule
  9. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  10. var bRegularizer: Regularizer[T]

  11. def backward(input: Table, gradOutput: Table): Table

    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
    CellAbstractModule
  12. var backwardTime: Long

    Attributes
    protected
    Definition Classes
    AbstractModule
  13. var backwardTimes: Array[Long]

    Definition Classes
    Cell
  14. def buildCell(): Sequential[T]

  15. def buildForgetGate(): Sequential[T]

  16. def buildGate(name: String = null): Sequential[T]

  17. def buildHidden(): Sequential[T]

  18. def buildInputGate(): Sequential[T]

  19. def buildModel(): Sequential[T]

  20. def buildOutputGate(): Sequential[T]

  21. var cRegularizer: Regularizer[T]

  22. def canEqual(other: Any): Boolean

    Definition Classes
    ConvLSTMPeephole3DAbstractModule
  23. var cell: AbstractModule[Activity, Activity, T]

    Any recurrent kernels should have a cell member variable which represents the module in the kernel.

    Any recurrent kernels should have a cell member variable which represents the module in the kernel.

    The cell receive an input with a format of T(input, preHiddens), and the output should be a format of T(output, hiddens). The hiddens represents the kernel's output hiddens at the current time step, which will be transferred to next time step. For instance, a simple RnnCell, hiddens is h, for LSTM, hiddens is T(h, c), and for both of them, the output variable represents h. Similarly the preHiddens is the kernel's output hiddens at the previous time step.

    Definition Classes
    ConvLSTMPeephole3DCell
  24. var cellLayer: Sequential[T]

  25. def checkEngineType(): ConvLSTMPeephole3D.this.type

    get execution engine type

    get execution engine type

    Definition Classes
    AbstractModule
  26. def clearState(): ConvLSTMPeephole3D.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
    AbstractModule
  27. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  28. def cloneModule(): AbstractModule[Table, Table, T]

    Definition Classes
    AbstractModule
  29. final def eq(arg0: AnyRef): Boolean

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

    Definition Classes
    ConvLSTMPeephole3DAbstractModule → AnyRef → Any
  31. def evaluate(dataSet: LocalDataSet[MiniBatch[T]], vMethods: Array[ValidationMethod[T]]): Array[(ValidationResult, ValidationMethod[T])]

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

    use ValidationMethod to evaluate module

    use ValidationMethod to evaluate module

    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
  33. def evaluate(): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  34. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  35. var forgetGate: Sequential[T]

  36. final def forward(input: Table): Table

    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. var forwardTimes: Array[Long]

    Definition Classes
    Cell
  39. def freeze(names: String*): ConvLSTMPeephole3D.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
    AbstractModule
  40. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  41. def getClassTagNumerics(): (Array[ClassTag[_]], Array[TensorNumeric[_]])

    Definition Classes
    AbstractModule
  42. 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
    AbstractModule
  43. 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
  44. def getNamePostfix: String

    Definition Classes
    AbstractModule
  45. def getNumericType(): TensorDataType

    returns

    Float or Double

    Definition Classes
    AbstractModule
  46. def getParameters(): (Tensor[T], Tensor[T])

    This method compact all parameters and gradients of the model into two tensors.

    This method compact all parameters and gradients of the model into two tensors. So it's easier to use optim method

    returns

    Definition Classes
    AbstractModule
  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").

    Custom modules should override this function if they have parameters.

    returns

    Table

    Definition Classes
    CellAbstractModule
  48. def getPrintName(): String

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

    Get the scale of gradientBias

    Get the scale of gradientBias

    Definition Classes
    AbstractModule
  50. 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)]

    Definition Classes
    CellAbstractModule
  52. 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
  53. var gradInput: Table

    The cached gradient of activities.

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

    Definition Classes
    AbstractModule
  54. def hasName: Boolean

    Definition Classes
    AbstractModule
  55. def hashCode(): Int

    Definition Classes
    ConvLSTMPeephole3DAbstractModule → AnyRef → Any
  56. def hidResize(hidden: Activity, batchSize: Int, stepShape: Array[Int]): Activity

    resize the hidden parameters wrt the batch size, hiddens shapes.

    resize the hidden parameters wrt the batch size, hiddens shapes.

    e.g. RnnCell contains 1 hidden parameter (H), thus it will return Tensor(size) LSTM contains 2 hidden parameters (C and H) and will return T(Tensor(), Tensor())\ and recursively intialize all the tensors in the Table.

    hidden
    batchSize

    batchSize

    stepShape

    For rnn/lstm/gru, it's embedding size. For convlstm/ convlstm3D, it's a list of outputPlane, length, width, height

    returns

    Definition Classes
    Cell
  57. var hiddenLayer: Sequential[T]

  58. def hiddenSizeOfPreTopo: Int

    Definition Classes
    Cell
  59. val hiddensShape: Array[Int]

    Definition Classes
    Cell
  60. var inputGate: Sequential[T]

  61. val inputSize: Int

    number of input planes in the image given into forward()

  62. 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
  63. 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
  64. 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
  65. final def isInstanceOf[T0]: Boolean

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

    Definition Classes
    AbstractModule
  67. val kernelC: Int

    Convolutional filter size to convolve cell

  68. val kernelI: Int

    Convolutional filter size to convolve input

  69. var line: String

    Attributes
    protected
    Definition Classes
    AbstractModule
  70. def loadModelWeights(srcModel: Module[Float], matchAll: Boolean = true): ConvLSTMPeephole3D.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
  71. def loadWeights(weightPath: String, matchAll: Boolean = true): ConvLSTMPeephole3D.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
  72. final def ne(arg0: AnyRef): Boolean

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

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

    Definition Classes
    AnyRef
  75. var output: Table

    The cached output.

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

    Definition Classes
    AbstractModule
  76. var outputGate: Sequential[T]

  77. val outputSize: Int

    number of output planes the convolution layer will produce

  78. val padding: Int

    The step of the convolution, default is -1, behaves same with SAME padding in tensorflow.

    The step of the convolution, default is -1, behaves same with SAME padding in tensorflow. Default stride,padding ensure last 3 dim of output shape is the same with input

  79. 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
    CellAbstractModule
  80. var preTopology: TensorModule[T]

    The preTopology defines operations to pre-process the input when it is not dependent on the time dimension.

    The preTopology defines operations to pre-process the input when it is not dependent on the time dimension. For example, the i2h in SimpleRNN Cell can be calculated before the recurrence since all the input slices are independent.

    This is particular useful to boost the performance of the recurrent layer.

    Please define your own preTopology according to your Cell structure. Please refer to SimpleRNN or LSTM for reference.

    returns

    Definition Classes
    ConvLSTMPeephole3DCell
  81. 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
  82. 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
  83. def predictImage(imageFrame: ImageFrame, outputLayer: String = null, shareBuffer: Boolean = false, batchPerPartition: Int = 4, predictKey: String = ImageFeature.predict): ImageFrame

    model predict images, return imageFrame with predicted tensor

    model predict images, return imageFrame with predicted tensor

    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

    returns

    Definition Classes
    AbstractModule
  84. def quantize(): Module[T]

    Definition Classes
    AbstractModule
  85. def regluarized(isRegularized: Boolean): Unit

    Use this method to set the whether the recurrent cell is regularized

    Use this method to set the whether the recurrent cell is regularized

    isRegularized

    whether to be regularized or not

    Definition Classes
    Cell
  86. var regularizers: Array[Regularizer[T]]

    Definition Classes
    Cell
  87. def reset(): Unit

    Definition Classes
    ConvLSTMPeephole3DCellAbstractModule
  88. def resetTimes(): Unit

    Definition Classes
    CellAbstractModule
  89. def saveCaffe(prototxtPath: String, modelPath: String, useV2: Boolean = true, overwrite: Boolean = false): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  90. def saveDefinition(path: String, overWrite: Boolean = false): ConvLSTMPeephole3D.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
  91. def saveModule(path: String, weightPath: String = null, overWrite: Boolean = false): ConvLSTMPeephole3D.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
  92. def saveTF(inputs: Seq[(String, Seq[Int])], path: String, byteOrder: ByteOrder = ByteOrder.LITTLE_ENDIAN, dataFormat: TensorflowDataFormat = TensorflowDataFormat.NHWC): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  93. def saveTorch(path: String, overWrite: Boolean = false): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  94. 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
  95. var scaleB: Double

    Attributes
    protected
    Definition Classes
    AbstractModule
  96. 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
  97. def setExtraParameter(extraParam: Array[Tensor[T]]): ConvLSTMPeephole3D.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
  98. def setLine(line: String): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  99. def setName(name: String): ConvLSTMPeephole3D.this.type

    Set the module name

    Set the module name

    name
    returns

    Definition Classes
    AbstractModule
  100. def setNamePostfix(namePostfix: String): Unit

    Definition Classes
    AbstractModule
  101. def setScaleB(b: Double): ConvLSTMPeephole3D.this.type

    Set the scale of gradientBias

    Set the scale of gradientBias

    b

    the value of the scale of gradientBias

    returns

    this

    Definition Classes
    AbstractModule
  102. def setScaleW(w: Double): ConvLSTMPeephole3D.this.type

    Set the scale of gradientWeight

    Set the scale of gradientWeight

    w

    the value of the scale of gradientWeight

    returns

    this

    Definition Classes
    AbstractModule
  103. def setWeightsBias(newWeights: Array[Tensor[T]]): ConvLSTMPeephole3D.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
  104. val stride: Int

    The step of the convolution

  105. var subModules: Array[AbstractModule[_ <: Activity, _ <: Activity, T]]

    Definition Classes
    Cell
  106. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  107. var times: Array[(AbstractModule[_ <: Activity, _ <: Activity, T], Long, Long)]

    Definition Classes
    Cell
  108. def toGraph(startNodes: ModuleNode[T]*): Graph[T]

    Generate graph module with start nodes

    Generate graph module with start nodes

    startNodes
    returns

    Definition Classes
    AbstractModule
  109. def toString(): String

    Definition Classes
    ConvLSTMPeephole3DAbstractModule → AnyRef → Any
  110. var train: Boolean

    Module status.

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

    Attributes
    protected
    Definition Classes
    AbstractModule
  111. def training(): ConvLSTMPeephole3D.this.type

    Definition Classes
    AbstractModule
  112. var uRegularizer: Regularizer[T]

  113. def unFreeze(names: String*): ConvLSTMPeephole3D.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
    AbstractModule
  114. def updateGradInput(input: Table, gradOutput: Table): Table

    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
    CellAbstractModule
  115. def updateOutput(input: Table): Table

    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
    CellAbstractModule
  116. def updateParameters(learningRate: T): Unit

    Definition Classes
    CellAbstractModule
  117. var wRegularizer: Regularizer[T]

  118. final def wait(): Unit

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  121. val withPeephole: Boolean

  122. 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
    CellAbstractModule

Deprecated Value Members

  1. def save(path: String, overWrite: Boolean = false): ConvLSTMPeephole3D.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

    please use recommended saveModule(path, overWrite)

Inherited from Cell[T]

Inherited from AbstractModule[Table, Table, T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped