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

Dropout

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

Applies Dropout to the input by randomly setting a fraction 'p' of input units to 0 at each update during training time in order to prevent overfitting.

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

T

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

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

Instance Constructors

  1. new Dropout(p: Double, inputShape: Shape = null)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    p

    Fraction of the input units to drop. Double between 0 and 1.

    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. def apply(name: String): Option[AbstractModule[Activity, Activity, T]]

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

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

    Definition Classes
    AbstractModule
  10. var backwardTime: Long

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

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

    Definition Classes
    Container → AbstractModule
  13. final def checkEngineType(): Dropout.this.type

    Definition Classes
    Container → AbstractModule
  14. def clearState(): Dropout.this.type

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

    Definition Classes
    AbstractModule
  16. def clone(): AnyRef

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

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

    Definition Classes
    IdentityOutputShape → InferShape
  19. def doBuild(inputShape: Shape): AbstractModule[Tensor[T], Tensor[T], T]

    Definition Classes
    Dropout → KerasLayer
  20. final def eq(arg0: AnyRef): Boolean

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

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

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

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

    Definition Classes
    AbstractModule
  25. def finalize(): Unit

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

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

    Definition Classes
    AbstractModule
  28. var forwardTime: Long

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

    Definition Classes
    Container → AbstractModule
  30. 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
  31. final def getClass(): Class[_]

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

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

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

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

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

    Definition Classes
    InferShape
  37. def getParametersTable(): Table

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

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

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

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

    Definition Classes
    Container → AbstractModule
  42. final def getWeightsBias(): Array[Tensor[T]]

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

    Definition Classes
    AbstractModule
  44. final def hasName: Boolean

    Definition Classes
    AbstractModule
  45. def hashCode(): Int

    Definition Classes
    Container → AbstractModule → AnyRef → Any
  46. val inputShape: Shape

    A Single Shape, does not include the batch dimension.

    A Single Shape, does not include the batch dimension.

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

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

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

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

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

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

    Definition Classes
    Any
  53. def isKerasStyle(): Boolean

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

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

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

    Definition Classes
    KerasLayer
  57. var line: String

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

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

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

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

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

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

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

    Definition Classes
    AbstractModule
  65. val p: Double

    Fraction of the input units to drop.

    Fraction of the input units to drop. Double between 0 and 1.

    Definition Classes
    Dropout → Dropout
  66. def parameters(): (Array[Tensor[T]], Array[Tensor[T]])

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

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

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

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

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

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

    Definition Classes
    AbstractModule
  73. def reset(): Unit

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

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

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

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

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

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

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

    Definition Classes
    AbstractModule
  81. var scaleB: Double

    Attributes
    protected
    Definition Classes
    AbstractModule
  82. var scaleW: Double

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

    Definition Classes
    AbstractModule
  84. final def setLine(line: String): Dropout.this.type

    Definition Classes
    AbstractModule
  85. final def setName(name: String): Dropout.this.type

    Definition Classes
    AbstractModule
  86. def setScaleB(b: Double): Dropout.this.type

    Definition Classes
    Container → AbstractModule
  87. def setScaleW(w: Double): Dropout.this.type

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

    Definition Classes
    AbstractModule
  89. final def synchronized[T0](arg0: ⇒ T0): T0

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

    Definition Classes
    AbstractModule
  91. def toString(): String

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

    Attributes
    protected
    Definition Classes
    AbstractModule
  93. final def training(): Dropout.this.type

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

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

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

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

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

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

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

    Definition Classes
    AbstractModule

Deprecated Value Members

  1. final def save(path: String, overWrite: Boolean): Dropout.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.Dropout[T]

Inherited from IdentityOutputShape

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