Class/Object

com.intel.analytics.zoo.pipeline.api.keras2.layers

Dense

Related Docs: object Dense | package layers

Permalink

class Dense[T] extends keras.layers.Dense[T] with Net

A densely-connected NN layer. The most common input is 2D.

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
keras.layers.Dense[T], Net, bigdl.nn.keras.Dense[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. Dense
  2. Dense
  3. Net
  4. Dense
  5. KerasLayer
  6. Container
  7. AbstractModule
  8. InferShape
  9. Serializable
  10. Serializable
  11. AnyRef
  12. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Dense(units: Int, kernelInitializer: InitializationMethod = Xavier, biasInitializer: InitializationMethod = Zeros, activation: KerasLayer[Tensor[T], Tensor[T], T] = null, kernelRegularizer: Regularizer[T] = null, biasRegularizer: Regularizer[T] = null, useBias: Boolean = true, inputShape: Shape = null)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    Permalink

    units

    The size of output dimension.

    kernelInitializer

    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.

    kernelRegularizer

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

    biasRegularizer

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

    useBias

    Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.

    inputShape

    A Single Shape, does not include the batch dimension.

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 accGradParameters(input: Tensor[T], gradOutput: Tensor[T]): Unit

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

    Permalink

    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
    DenseDense → Dense
  6. def apply(name: String): Option[AbstractModule[Activity, Activity, T]]

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

    Permalink
    Definition Classes
    Any
  8. var bRegularizer: Regularizer[T]

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

    Permalink
    Definition Classes
    AbstractModule
  10. var backwardTime: Long

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  11. val bias: Boolean

    Permalink

    Whether to include a bias (i.e.

    Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.

    Definition Classes
    Dense → Dense
  12. val biasInitializer: InitializationMethod

    Permalink
  13. val biasRegularizer: Regularizer[T]

    Permalink

    An instance of Regularizer, applied to the bias.

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

  14. def build(calcInputShape: Shape): Shape

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

    Permalink
    Definition Classes
    Container → AbstractModule
  16. final def checkEngineType(): Dense.this.type

    Permalink
    Definition Classes
    Container → AbstractModule
  17. def clearState(): Dense.this.type

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

    Permalink
    Definition Classes
    AbstractModule
  19. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  20. final def cloneModule(): Dense.this.type

    Permalink
    Definition Classes
    AbstractModule
  21. def computeOutputShape(inputShape: Shape): Shape

    Permalink
    Definition Classes
    Dense → KerasLayer → InferShape
  22. def doBuild(inputShape: Shape): AbstractModule[Tensor[T], Tensor[T], T]

    Permalink
    Definition Classes
    Dense → Dense → KerasLayer
  23. final def eq(arg0: AnyRef): Boolean

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

    Permalink
    Definition Classes
    Container → AbstractModule → AnyRef → Any
  25. final def evaluate(): Dense.this.type

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

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

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

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

    Permalink
    Definition Classes
    AbstractModule
  30. def finalize(): Unit

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

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

    Permalink
    Definition Classes
    AbstractModule
  33. var forwardTime: Long

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  34. def freeze(names: String*): Dense.this.type

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

    Permalink

    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
  36. final def getClass(): Class[_]

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

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

    Permalink
    Definition Classes
    InferShape
  39. final def getName(): String

    Permalink
    Definition Classes
    AbstractModule
  40. final def getNumericType(): TensorDataType

    Permalink
    Definition Classes
    AbstractModule
  41. final def getOutputShape(): Shape

    Permalink
    Definition Classes
    InferShape
  42. def getParametersTable(): Table

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

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

    Permalink
    Definition Classes
    AbstractModule
  45. final def getScaleW(): Double

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

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

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

    Permalink
    Definition Classes
    AbstractModule
  49. var gradInput: Tensor[T]

    Permalink
    Definition Classes
    AbstractModule
  50. final def hasName: Boolean

    Permalink
    Definition Classes
    AbstractModule
  51. def hashCode(): Int

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

    Permalink

    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
    Dense → Dense
  53. val inputShape: Shape

    Permalink

    A Single Shape, does not include the batch dimension.

    A Single Shape, does not include the batch dimension.

    Definition Classes
    DenseDense → Dense
  54. def inputs(first: (ModuleNode[T], Int), nodesWithIndex: (ModuleNode[T], Int)*): ModuleNode[T]

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

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

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

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

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

    Permalink
    Definition Classes
    Any
  60. def isKerasStyle(): Boolean

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

    Permalink
    Definition Classes
    AbstractModule
  62. val kernelInitializer: InitializationMethod

    Permalink

    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.

  63. val kernelRegularizer: Regularizer[T]

    Permalink

    An instance of Regularizer, (eg.

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

  64. def labor: AbstractModule[Tensor[T], Tensor[T], T]

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

    Permalink
    Definition Classes
    KerasLayer
  66. var line: String

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

    Permalink
    Definition Classes
    AbstractModule
  68. final def loadWeights(weightPath: String, matchAll: Boolean): Dense.this.type

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

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

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

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

    Permalink
    Definition Classes
    AnyRef
  73. var output: Tensor[T]

    Permalink
    Definition Classes
    AbstractModule
  74. val outputDim: Int

    Permalink

    The size of output dimension.

    The size of output dimension.

    Definition Classes
    Dense → Dense
  75. def parameters(): (Array[Tensor[T]], Array[Tensor[T]])

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

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

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

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

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

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

    Permalink
    Definition Classes
    AbstractModule
  82. def release(): Unit

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

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

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

    Permalink
    Definition Classes
    AbstractModule
  86. final def saveDefinition(path: String, overWrite: Boolean): Dense.this.type

    Permalink
    Definition Classes
    AbstractModule
  87. final def saveModule(path: String, weightPath: String, overWrite: Boolean): Dense.this.type

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

    Permalink
    Definition Classes
    AbstractModule
  89. final def saveTorch(path: String, overWrite: Boolean): Dense.this.type

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

    Permalink
    Definition Classes
    AbstractModule
  91. var scaleB: Double

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  92. var scaleW: Double

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

    Permalink
    Definition Classes
    AbstractModule
  94. final def setLine(line: String): Dense.this.type

    Permalink
    Definition Classes
    AbstractModule
  95. final def setName(name: String): Dense.this.type

    Permalink
    Definition Classes
    AbstractModule
  96. def setScaleB(b: Double): Dense.this.type

    Permalink
    Definition Classes
    Container → AbstractModule
  97. def setScaleW(w: Double): Dense.this.type

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

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

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

    Permalink
    Definition Classes
    AbstractModule
  101. def toString(): String

    Permalink
    Definition Classes
    AbstractModule → AnyRef → Any
  102. var train: Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  103. final def training(): Dense.this.type

    Permalink
    Definition Classes
    Container → AbstractModule
  104. def unFreeze(names: String*): Dense.this.type

    Permalink
    Definition Classes
    Container → AbstractModule
  105. val units: Int

    Permalink

    The size of output dimension.

  106. def updateGradInput(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

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

    Permalink
    Definition Classes
    KerasLayer → AbstractModule
  108. val useBias: Boolean

    Permalink

    Whether to include a bias (i.e.

    Whether to include a bias (i.e. make the layer affine rather than linear). Default is true.

  109. var wRegularizer: Regularizer[T]

    Permalink
    Definition Classes
    Dense
  110. final def wait(): Unit

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

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

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

    Permalink
    Definition Classes
    AbstractModule

Deprecated Value Members

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

    Permalink
    Definition Classes
    AbstractModule
    Annotations
    @deprecated
    Deprecated

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

Inherited from keras.layers.Dense[T]

Inherited from Net

Inherited from bigdl.nn.keras.Dense[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