com.intel.analytics.zoo.pipeline.api.keras.layers

AtrousConvolution1D

class AtrousConvolution1D[T] extends bigdl.nn.keras.AtrousConvolution1D[T] with Net

Applies an atrous convolution operator for filtering neighborhoods of 1-D inputs. A.k.a dilated convolution or convolution with holes. Bias will be included in this layer. Border mode currently supported for this layer is 'valid'. You can also use AtrousConv1D as an alias of this layer. The input of this layer should be 3D.

When using this layer as the first layer in a model, you need to provide the argument inputShape (a Single Shape, does not include the batch dimension).

T

The numeric type of parameter(e.g. weight, bias). Only support float/double now.

Linear Supertypes
Net, bigdl.nn.keras.AtrousConvolution1D[T], KerasLayer[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. AtrousConvolution1D
  2. Net
  3. AtrousConvolution1D
  4. KerasLayer
  5. Container
  6. AbstractModule
  7. InferShape
  8. Serializable
  9. Serializable
  10. AnyRef
  11. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new AtrousConvolution1D(nbFilter: Int, filterLength: Int, init: InitializationMethod = com.intel.analytics.bigdl.nn.Xavier, activation: KerasLayer[Tensor[T], Tensor[T], T] = null, subsampleLength: Int = 1, atrousRate: Int = 1, wRegularizer: Regularizer[T] = null, bRegularizer: Regularizer[T] = null, inputShape: Shape = null)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    nbFilter

    Number of convolution kernels to use.

    filterLength

    The extension (spatial or temporal) of each filter.

    init

    Initialization method for the weights of the layer. Default is Xavier. You can also pass in corresponding string representations such as 'glorot_uniform' or 'normal', etc. for simple init methods in the factory method.

    activation

    Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.

    subsampleLength

    Factor by which to subsample output. Integer. Default is 1.

    atrousRate

    Factor for kernel dilation. Also called filter_dilation elsewhere. Integer. Default is 1.

    wRegularizer

    An instance of Regularizer, (eg. L1 or L2 regularization), applied to the input weights matrices. Default is null.

    bRegularizer

    An instance of Regularizer, applied to the bias. Default is null.

    inputShape

    A Single Shape, does not include the batch dimension.

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: Tensor[T], gradOutput: Tensor[T]): Unit

    Definition Classes
    KerasLayer → AbstractModule
  7. val activation: KerasLayer[Tensor[T], Tensor[T], T]

    Activation function to use.

    Activation function to use. Default is null. You can also pass in corresponding string representations such as 'relu' or 'sigmoid', etc. for simple activations in the factory method.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  8. def apply(name: String): Option[AbstractModule[Activity, Activity, T]]

    Definition Classes
    Container → AbstractModule
  9. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  10. val atrousRate: Int

    Factor for kernel dilation.

    Factor for kernel dilation. Also called filter_dilation elsewhere. Integer. Default is 1.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  11. def backward(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

    Definition Classes
    AbstractModule
  12. var backwardTime: Long

    Attributes
    protected
    Definition Classes
    AbstractModule
  13. def build(calcInputShape: Shape): Shape

    Definition Classes
    KerasLayer → InferShape
  14. def canEqual(other: Any): Boolean

    Definition Classes
    Container → AbstractModule
  15. final def checkEngineType(): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  16. def clearState(): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  17. final def clone(deepCopy: Boolean): AbstractModule[Tensor[T], Tensor[T], T]

    Definition Classes
    AbstractModule
  18. def clone(): AnyRef

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

    Definition Classes
    AbstractModule
  20. def computeOutputShape(inputShape: Shape): Shape

    Definition Classes
    AtrousConvolution1D → KerasLayer → InferShape
  21. def doBuild(inputShape: Shape): AbstractModule[Tensor[T], Tensor[T], T]

    Definition Classes
    AtrousConvolution1D → KerasLayer
  22. final def eq(arg0: AnyRef): Boolean

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

    Definition Classes
    Container → AbstractModule → AnyRef → Any
  24. final def evaluate(): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  25. final def evaluate(dataSet: LocalDataSet[MiniBatch[T]], vMethods: Array[_ <: ValidationMethod[T]]): Array[(ValidationResult, ValidationMethod[T])]

    Definition Classes
    AbstractModule
  26. final def evaluate(dataset: RDD[Sample[T]], vMethods: Array[_ <: ValidationMethod[T]], batchSize: Option[Int]): Array[(ValidationResult, ValidationMethod[T])]

    Definition Classes
    AbstractModule
  27. final def evaluateImage(imageFrame: ImageFrame, vMethods: Array[_ <: ValidationMethod[T]], batchSize: Option[Int]): Array[(ValidationResult, ValidationMethod[T])]

    Definition Classes
    AbstractModule
  28. val filterLength: Int

    The extension (spatial or temporal) of each filter.

    The extension (spatial or temporal) of each filter.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  29. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  30. def findModules(moduleType: String): ArrayBuffer[AbstractModule[_, _, T]]

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

    Definition Classes
    AbstractModule
  32. var forwardTime: Long

    Attributes
    protected
    Definition Classes
    AbstractModule
  33. def freeze(names: String*): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  34. def from[T](vars: Variable[T]*)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Build graph: some other modules point to current module

    Build graph: some other modules point to current module

    vars

    upstream variables

    returns

    Variable containing current module

    Definition Classes
    Net
  35. final def getClass(): Class[_]

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

    Definition Classes
    Container → AbstractModule
  37. final def getInputShape(): Shape

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

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

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

    Definition Classes
    InferShape
  41. def getParametersTable(): Table

    Definition Classes
    Container → AbstractModule
  42. final def getPrintName(): String

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

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

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

    Definition Classes
    Container → AbstractModule
  46. final def getTimesGroupByModuleType(): Array[(String, Long, Long)]

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

    Definition Classes
    AbstractModule
  48. var gradInput: Tensor[T]

    Definition Classes
    AbstractModule
  49. final def hasName: Boolean

    Definition Classes
    AbstractModule
  50. def hashCode(): Int

    Definition Classes
    Container → AbstractModule → AnyRef → Any
  51. val init: InitializationMethod

    Initialization method for the weights of the layer.

    Initialization method for the weights of the layer. Default is Xavier. You can also pass in corresponding string representations such as 'glorot_uniform' or 'normal', etc. for simple init methods in the factory method.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  52. val inputShape: Shape

    A Single Shape, does not include the batch dimension.

    A Single Shape, does not include the batch dimension.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  53. def inputs(first: (ModuleNode[T], Int), nodesWithIndex: (ModuleNode[T], Int)*): ModuleNode[T]

    Definition Classes
    KerasLayer → AbstractModule
  54. def inputs(nodes: Array[ModuleNode[T]]): ModuleNode[T]

    Definition Classes
    KerasLayer → AbstractModule
  55. def inputs(nodes: ModuleNode[T]*): ModuleNode[T]

    Definition Classes
    KerasLayer → AbstractModule
  56. def isBuilt(): Boolean

    Definition Classes
    KerasLayer → InferShape
  57. def isFrozen[T]()(implicit arg0: ClassTag[T]): Boolean

    Definition Classes
    Net
  58. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  59. def isKerasStyle(): Boolean

    Definition Classes
    KerasLayer → InferShape
  60. final def isTraining(): Boolean

    Definition Classes
    AbstractModule
  61. def labor: AbstractModule[Tensor[T], Tensor[T], T]

    Definition Classes
    KerasLayer
  62. def labor_=(value: AbstractModule[Tensor[T], Tensor[T], T]): Unit

    Definition Classes
    KerasLayer
  63. var line: String

    Attributes
    protected
    Definition Classes
    AbstractModule
  64. final def loadModelWeights(srcModel: Module[Float], matchAll: Boolean): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  65. final def loadWeights(weightPath: String, matchAll: Boolean): AtrousConvolution1D.this.type

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

    Definition Classes
    Container
  67. val nbFilter: Int

    Number of convolution kernels to use.

    Number of convolution kernels to use.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  68. final def ne(arg0: AnyRef): Boolean

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

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

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

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

    Definition Classes
    Container → AbstractModule
  73. final def predict(dataset: RDD[Sample[T]], batchSize: Int, shareBuffer: Boolean): RDD[Activity]

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

    Definition Classes
    AbstractModule
  75. final def predictImage(imageFrame: ImageFrame, outputLayer: String, shareBuffer: Boolean, batchPerPartition: Int, predictKey: String, featurePaddingParam: Option[PaddingParam[T]]): ImageFrame

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

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

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

    Definition Classes
    AbstractModule
  79. def release(): Unit

    Definition Classes
    Container → AbstractModule
  80. def reset(): Unit

    Definition Classes
    Container → AbstractModule
  81. def resetTimes(): Unit

    Definition Classes
    Container → AbstractModule
  82. final def saveCaffe(prototxtPath: String, modelPath: String, useV2: Boolean, overwrite: Boolean): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  83. final def saveDefinition(path: String, overWrite: Boolean): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  84. final def saveModule(path: String, weightPath: String, overWrite: Boolean): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  85. final def saveTF(inputs: Seq[(String, Seq[Int])], path: String, byteOrder: ByteOrder, dataFormat: TensorflowDataFormat): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  86. final def saveTorch(path: String, overWrite: Boolean): AtrousConvolution1D.this.type

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

    Definition Classes
    AbstractModule
  88. var scaleB: Double

    Attributes
    protected
    Definition Classes
    AbstractModule
  89. var scaleW: Double

    Attributes
    protected
    Definition Classes
    AbstractModule
  90. final def setExtraParameter(extraParam: Array[Tensor[T]]): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  91. final def setLine(line: String): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  92. final def setName(name: String): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  93. def setScaleB(b: Double): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  94. def setScaleW(w: Double): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  95. final def setWeightsBias(newWeights: Array[Tensor[T]]): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
  96. val subsampleLength: Int

    Factor by which to subsample output.

    Factor by which to subsample output. Integer. Default is 1.

    Definition Classes
    AtrousConvolution1D → AtrousConvolution1D
  97. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  98. def toGraph(startNodes: ModuleNode[T]*): Graph[T]

    Definition Classes
    AbstractModule
  99. def toString(): String

    Definition Classes
    AbstractModule → AnyRef → Any
  100. var train: Boolean

    Attributes
    protected
    Definition Classes
    AbstractModule
  101. final def training(): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  102. def unFreeze(names: String*): AtrousConvolution1D.this.type

    Definition Classes
    Container → AbstractModule
  103. def updateGradInput(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

    Definition Classes
    KerasLayer → AbstractModule
  104. def updateOutput(input: Tensor[T]): Tensor[T]

    Definition Classes
    KerasLayer → AbstractModule
  105. final def wait(): Unit

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

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

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

    Definition Classes
    AbstractModule

Deprecated Value Members

  1. final def save(path: String, overWrite: Boolean): AtrousConvolution1D.this.type

    Definition Classes
    AbstractModule
    Annotations
    @deprecated
    Deprecated

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

Inherited from Net

Inherited from bigdl.nn.keras.AtrousConvolution1D[T]

Inherited from KerasLayer[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