Class/Object

com.intel.analytics.bigdl.nn

LocallyConnected2D

Related Docs: object LocallyConnected2D | package nn

Permalink

class LocallyConnected2D[T] extends TensorModule[T] with Initializable

The LocallyConnected2D layer works similarly to the SpatialConvolution layer, except that weights are unshared, that is, a different set of filters is applied at each different patch of the input.

T

The numeric type in the criterion, usually which are Float or Double

Linear Supertypes
Initializable, TensorModule[T], AbstractModule[Tensor[T], Tensor[T], T], InferShape, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. LocallyConnected2D
  2. Initializable
  3. TensorModule
  4. AbstractModule
  5. InferShape
  6. Serializable
  7. Serializable
  8. AnyRef
  9. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new LocallyConnected2D(nInputPlane: Int, inputWidth: Int, inputHeight: Int, nOutputPlane: Int, kernelW: Int, kernelH: Int, strideW: Int = 1, strideH: Int = 1, padW: Int = 0, padH: Int = 0, propagateBack: Boolean = true, wRegularizer: Regularizer[T] = null, bRegularizer: Regularizer[T] = null, initWeight: Tensor[T] = null, initBias: Tensor[T] = null, initGradWeight: Tensor[T] = null, initGradBias: Tensor[T] = null, withBias: Boolean = true, format: DataFormat = DataFormat.NCHW)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    Permalink

    nInputPlane

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

    inputWidth

    The input width

    inputHeight

    The input height

    nOutputPlane

    The number of output planes the convolution layer will produce.

    kernelW

    The kernel width of the convolution

    kernelH

    The kernel height of the convolution

    strideW

    The step of the convolution in the width dimension

    strideH

    The step of the convolution in the height dimension

    padW

    The additional zeros added per width to the input planes

    padH

    The additional zeros added per height to the input planes

    propagateBack

    propagate gradient back

    wRegularizer

    weight regularizer

    bRegularizer

    bias regularizer

    initWeight

    initial weight

    initBias

    initial bias

    initGradWeight

    initial gradient weight

    initGradBias

    initial gradient bias

    withBias

    if has bias

    format

    data format NCHW, NHWC

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. val _1x1: Boolean

    Permalink
    Attributes
    protected
  5. def accGradParameters(input: Tensor[T], gradOutput: Tensor[T]): Unit

    Permalink

    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.

    Definition Classes
    LocallyConnected2DAbstractModule
  6. def accGradParametersFrame(gradOutput: Tensor[T], gradWeight: Tensor[T], gradBias: Tensor[T], fInput: Tensor[T], scaleW: T, scaleB: T)(implicit ev: TensorNumeric[T]): Unit

    Permalink
    Attributes
    protected
  7. def apply(name: String): Option[AbstractModule[Activity, Activity, T]]

    Permalink

    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.

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

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

    Permalink

    bias regularizer

  10. def backward(input: Tensor[T], gradOutput: Tensor[T]): Tensor[T]

    Permalink

    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
    AbstractModule
  11. var backwardTime: Long

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  12. val bias: Tensor[T]

    Permalink
  13. var biasInitMethod: InitializationMethod

    Permalink
    Attributes
    protected
    Definition Classes
    Initializable
  14. def calcGradParametersFrame(gradOutput: Tensor[T], gradWeight: Tensor[T], gradBias: Tensor[T], fInput: Tensor[T], scaleW: T, scaleB: T)(implicit ev: TensorNumeric[T]): Unit

    Permalink
    Attributes
    protected
  15. def clearState(): LocallyConnected2D.this.type

    Permalink

    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

    Definition Classes
    LocallyConnected2DAbstractModule
  16. final def clone(deepCopy: Boolean): AbstractModule[Tensor[T], Tensor[T], T]

    Permalink

    Clone the module, deep or shallow copy

    Clone the module, deep or shallow copy

    Definition Classes
    AbstractModule
  17. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  18. final def cloneModule(): LocallyConnected2D.this.type

    Permalink

    Clone the model

    Clone the model

    Definition Classes
    AbstractModule
  19. var col2imTime: Long

    Permalink
    Attributes
    protected
  20. def computeOutputShape(inputShape: Shape): Shape

    Permalink

    We suppose the first dim is batch

    We suppose the first dim is batch

    Definition Classes
    LocallyConnected2DInferShape
  21. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  22. def equals(obj: Any): Boolean

    Permalink
    Definition Classes
    LocallyConnected2DAbstractModule → AnyRef → Any
  23. final def evaluate(dataSet: LocalDataSet[MiniBatch[T]], vMethods: Array[_ <: ValidationMethod[T]]): Array[(ValidationResult, ValidationMethod[T])]

    Permalink

    use ValidationMethod to evaluate module on the given local dataset

    use ValidationMethod to evaluate module on the given local dataset

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

    Permalink

    use ValidationMethod to evaluate module on the given rdd dataset

    use ValidationMethod to evaluate module on the given rdd dataset

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

    Permalink

    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

    Definition Classes
    AbstractModule
  26. def evaluate(): LocallyConnected2D.this.type

    Permalink

    Set the module to evaluate mode

    Set the module to evaluate mode

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

    Permalink

    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

    Definition Classes
    AbstractModule
  28. var fGradInput: Tensor[T]

    Permalink
  29. var fInput: Tensor[T]

    Permalink
  30. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  31. val format: DataFormat

    Permalink

    data format NCHW, NHWC

  32. final def forward(input: Tensor[T]): Tensor[T]

    Permalink

    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
  33. var forwardTime: Long

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  34. def freeze(names: String*): LocallyConnected2D.this.type

    Permalink

    freeze the module, i.e.

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

    Permalink
    Definition Classes
    AnyRef → Any
  36. def getCol2ImgTime(): Double

    Permalink
  37. def getExtraParameter(): Array[Tensor[T]]

    Permalink

    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
  38. def getIm2ColTime(): Double

    Permalink
  39. final def getInputShape(): Shape

    Permalink

    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
  40. final def getName(): String

    Permalink

    Get the module name, default name is className@namePostfix

    Get the module name, default name is className@namePostfix

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

    Permalink

    Get numeric type of module parameters

    Get numeric type of module parameters

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

    Permalink

    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
  43. def getPadding(inputHeight: Int, inputWidth: Int): (Int, Int, Int, Int)

    Permalink
    Attributes
    protected
  44. def getParametersTable(): Table

    Permalink

    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
    AbstractModule
  45. final def getPrintName(): String

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

    Permalink

    Get the scale of gradientBias

    Get the scale of gradientBias

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

    Permalink

    Get the scale of gradientWeight

    Get the scale of gradientWeight

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

    Permalink

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

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

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

    Permalink

    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
  50. final def getWeightsBias(): Array[Tensor[T]]

    Permalink

    Get weight and bias for the module

    Get weight and bias for the module

    returns

    array of weights and bias

    Definition Classes
    AbstractModule
  51. val gradBias: Tensor[T]

    Permalink
  52. var gradBiasWindow: Tensor[T]

    Permalink
    Attributes
    protected
  53. var gradInput: Tensor[T]

    Permalink

    The cached gradient of activities.

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

    Definition Classes
    AbstractModule
  54. val gradWeight: Tensor[T]

    Permalink
  55. var gradWeightMM: Tensor[T]

    Permalink
    Attributes
    protected
  56. var gradWeightMMInBatch: Tensor[T]

    Permalink
    Attributes
    protected
  57. val gradientBiasMT: Tensor[T]

    Permalink
    Attributes
    protected
  58. final def hasName: Boolean

    Permalink

    Whether user set a name to the module before

    Whether user set a name to the module before

    Definition Classes
    AbstractModule
  59. def hashCode(): Int

    Permalink
    Definition Classes
    LocallyConnected2DAbstractModule → AnyRef → Any
  60. var im2colTime: Long

    Permalink
    Attributes
    protected
  61. val initBias: Tensor[T]

    Permalink

    initial bias

  62. val initGradBias: Tensor[T]

    Permalink

    initial gradient bias

  63. val initGradWeight: Tensor[T]

    Permalink

    initial gradient weight

  64. val initWeight: Tensor[T]

    Permalink

    initial weight

  65. val inputHeight: Int

    Permalink

    The input height

  66. val inputWidth: Int

    Permalink

    The input width

  67. def inputs(first: (ModuleNode[T], Int), nodesWithIndex: (ModuleNode[T], Int)*): ModuleNode[T]

    Permalink

    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
  68. def inputs(nodes: Array[ModuleNode[T]]): ModuleNode[T]

    Permalink

    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
  69. def inputs(nodes: ModuleNode[T]*): ModuleNode[T]

    Permalink

    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
  70. var inputsFormats: Seq[Int]

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  71. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  72. final def isTraining(): Boolean

    Permalink

    Check if the model is in training mode

    Check if the model is in training mode

    Definition Classes
    AbstractModule
  73. val kernelH: Int

    Permalink

    The kernel height of the convolution

  74. val kernelW: Int

    Permalink

    The kernel width of the convolution

  75. var line: String

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  76. final def loadModelWeights(srcModel: Module[Float], matchAll: Boolean = true): LocallyConnected2D.this.type

    Permalink

    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
  77. final def loadWeights(weightPath: String, matchAll: Boolean = true): LocallyConnected2D.this.type

    Permalink

    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
  78. val nInputPlane: Int

    Permalink

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

  79. val nOutputPlane: Int

    Permalink

    The number of output planes the convolution layer will produce.

  80. final def ne(arg0: AnyRef): Boolean

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

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

    Permalink
    Definition Classes
    AnyRef
  83. val ones: Tensor[T]

    Permalink
    Attributes
    protected
  84. val onesBatch: Tensor[T]

    Permalink
    Attributes
    protected
  85. val onesBias: Tensor[T]

    Permalink
    Attributes
    protected
  86. var output: Tensor[T]

    Permalink

    The cached output.

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

    Definition Classes
    AbstractModule
  87. val outputHeight: Int

    Permalink
  88. val outputWidth: Int

    Permalink
  89. var outputsFormats: Seq[Int]

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  90. val padBottom: Int

    Permalink
  91. val padH: Int

    Permalink

    The additional zeros added per height to the input planes

  92. val padLeft: Int

    Permalink
  93. val padRight: Int

    Permalink
  94. val padTop: Int

    Permalink
  95. val padW: Int

    Permalink

    The additional zeros added per width to the input planes

  96. def parameters(): (Array[Tensor[T]], Array[Tensor[T]])

    Permalink

    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
    LocallyConnected2DAbstractModule
  97. final def predict(dataset: RDD[Sample[T]], batchSize: Int = 1, shareBuffer: Boolean = false): RDD[Activity]

    Permalink

    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
  98. final def predictClass(dataset: RDD[Sample[T]], batchSize: Int = 1): RDD[Int]

    Permalink

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

    Permalink

    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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    AbstractModule
  102. val propagateBack: Boolean

    Permalink

    propagate gradient back

  103. final def quantize(): Module[T]

    Permalink

    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.

    Definition Classes
    AbstractModule
  104. def release(): Unit

    Permalink

    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
    AbstractModule
  105. def reset(): Unit

    Permalink

    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
    LocallyConnected2DInitializableAbstractModule
  106. def resetTimes(): Unit

    Permalink

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

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

    Definition Classes
    AbstractModule
  107. var results: Array[Future[Unit]]

    Permalink
    Attributes
    protected
  108. final def saveCaffe(prototxtPath: String, modelPath: String, useV2: Boolean = true, overwrite: Boolean = false): LocallyConnected2D.this.type

    Permalink

    Save this module to path in caffe readable format

    Save this module to path in caffe readable format

    Definition Classes
    AbstractModule
  109. final def saveDefinition(path: String, overWrite: Boolean = false): LocallyConnected2D.this.type

    Permalink

    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
  110. final def saveModule(path: String, weightPath: String = null, overWrite: Boolean = false): LocallyConnected2D.this.type

    Permalink

    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
  111. final def saveTF(inputs: Seq[(String, Seq[Int])], path: String, byteOrder: ByteOrder = ByteOrder.LITTLE_ENDIAN, dataFormat: TensorflowDataFormat = TensorflowDataFormat.NHWC): LocallyConnected2D.this.type

    Permalink

    Save this module to path in tensorflow readable format

    Save this module to path in tensorflow readable format

    Definition Classes
    AbstractModule
  112. final def saveTorch(path: String, overWrite: Boolean = false): LocallyConnected2D.this.type

    Permalink

    Save this module to path in torch7 readable format

    Save this module to path in torch7 readable format

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

    Permalink

    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
  114. var scaleB: Double

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

    Permalink

    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
  116. def setExtraParameter(extraParam: Array[Tensor[T]]): LocallyConnected2D.this.type

    Permalink

    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
  117. def setInitMethod(initMethod: Array[InitializationMethod]): LocallyConnected2D.this.type

    Permalink
    Definition Classes
    Initializable
  118. def setInitMethod(weightInitMethod: InitializationMethod = null, biasInitMethod: InitializationMethod = null): LocallyConnected2D.this.type

    Permalink
    Definition Classes
    Initializable
  119. def setInputFormats(formats: Seq[Int]): LocallyConnected2D.this.type

    Permalink

    set input formats for graph

    set input formats for graph

    Definition Classes
    AbstractModule
  120. final def setLine(line: String): LocallyConnected2D.this.type

    Permalink

    Set the line separator when print the module

    Set the line separator when print the module

    Definition Classes
    AbstractModule
  121. final def setName(name: String): LocallyConnected2D.this.type

    Permalink

    Set the module name

    Set the module name

    Definition Classes
    AbstractModule
  122. def setOutputFormats(formats: Seq[Int]): LocallyConnected2D.this.type

    Permalink

    set output formats for graph

    set output formats for graph

    Definition Classes
    AbstractModule
  123. def setScaleB(b: Double): LocallyConnected2D.this.type

    Permalink

    Set the scale of gradientBias

    Set the scale of gradientBias

    b

    the value of the scale of gradientBias

    returns

    this

    Definition Classes
    AbstractModule
  124. def setScaleW(w: Double): LocallyConnected2D.this.type

    Permalink

    Set the scale of gradientWeight

    Set the scale of gradientWeight

    w

    the value of the scale of gradientWeight

    returns

    this

    Definition Classes
    AbstractModule
  125. final def setWeightsBias(newWeights: Array[Tensor[T]]): LocallyConnected2D.this.type

    Permalink

    Set weight and bias for the module

    Set weight and bias for the module

    newWeights

    array of weights and bias

    Definition Classes
    AbstractModule
  126. val sizes: Array[Int]

    Permalink
  127. val strideH: Int

    Permalink

    The step of the convolution in the height dimension

  128. val strideW: Int

    Permalink

    The step of the convolution in the width dimension

  129. final def synchronized[T0](arg0: ⇒ T0): T0

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

    Permalink

    Generate graph module with start nodes

    Generate graph module with start nodes

    Definition Classes
    AbstractModule
  131. def toString(): String

    Permalink
    Definition Classes
    LocallyConnected2DAbstractModule → AnyRef → Any
  132. var train: Boolean

    Permalink

    Module status.

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

    Attributes
    protected
    Definition Classes
    AbstractModule
  133. def training(): LocallyConnected2D.this.type

    Permalink

    Set the module to training mode

    Set the module to training mode

    Definition Classes
    AbstractModule
  134. def unFreeze(names: String*): LocallyConnected2D.this.type

    Permalink

    "unfreeze" module, i.e.

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

    Permalink

    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.

    Definition Classes
    LocallyConnected2DAbstractModule
  136. def updateGradInputFrame(gradInput: Tensor[T], gradOutput: Tensor[T], weight: Tensor[T], fgradInput: Tensor[T], kW: Int, kH: Int, dW: Int, dH: Int, padLeft: Int, padTop: Int, padRight: Int, padBottom: Int)(implicit ev: TensorNumeric[T]): Unit

    Permalink
    Attributes
    protected
  137. def updateOutput(input: Tensor[T]): Tensor[T]

    Permalink

    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.

    Definition Classes
    LocallyConnected2DAbstractModule
  138. def updateOutputFrame(input: Tensor[T], output: Tensor[T], weight: Tensor[T], bias: Tensor[T], fInput: Tensor[T], kW: Int, kH: Int, dW: Int, dH: Int, padLeft: Int, padTop: Int, padRight: Int, padBottom: Int, nInputPlane: Int, inputWidth: Int, inputHeight: Int, nOutputPlane: Int, outputWidth: Int, outputHeight: Int)(implicit ev: TensorNumeric[T]): Unit

    Permalink
    Attributes
    protected
  139. var wRegularizer: Regularizer[T]

    Permalink

    weight regularizer

  140. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  143. val weight: Tensor[T]

    Permalink
  144. var weightInitMethod: InitializationMethod

    Permalink
    Attributes
    protected
    Definition Classes
    Initializable
  145. val withBias: Boolean

    Permalink

    if has bias

  146. def zeroGradParameters(): Unit

    Permalink

    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. def save(path: String, overWrite: Boolean = false): LocallyConnected2D.this.type

    Permalink

    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 Initializable

Inherited from TensorModule[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