Object

com.intel.analytics.zoo.models.image.objectdetection.common

ModuleUtil

Related Doc: package common

Permalink

object ModuleUtil

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. ModuleUtil
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

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 addConvRelu[T](prevNodes: ModuleNode[T], p: (Int, Int, Int, Int, Int), name: String, prefix: String = "conv", nGroup: Int = 1, propogateBack: Boolean = true)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): ModuleNode[T]

    Permalink

    Create Convolution layer followed by Relu activation

    Create Convolution layer followed by Relu activation

    prevNodes

    previous node for convolution layer node

    p

    convolution size info. Should be (input plane number, output plane number, kernel size, stride size, pad size). We'are assuming kernel width = kernel height, stride width = stride height, pad width = pad height

    name

    layer name

    prefix

    prefix for the layer name

    nGroup

    kernel group number

    propogateBack

    whether to propagate gradient back

    returns

    Relu node

  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  6. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  7. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  8. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  9. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  10. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  11. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  12. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  13. def loadModelWeights(srcModel: Module[Float], targetModel: Module[Float], matchAll: Boolean = true): ModuleUtil.this.type

    Permalink

    Load model weights and bias from source model to target model

    Load model weights and bias from source model to target model

    srcModel

    source model

    targetModel

    target model

    matchAll

    whether to match all layers' weights and bias, if not, only load existing source weights and bias

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

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

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

    Permalink
    Definition Classes
    AnyRef
  17. def selectResults[T](start: Int, dim: Int, nInputDims: Int, numComponents: Int, name: String)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Module[T]

    Permalink

    select results (confs || locs || priorboxes), use JoinTable to concat them into one tensor

    select results (confs || locs || priorboxes), use JoinTable to concat them into one tensor

    start

    start index of the result

    dim

    dimension to join

    nInputDims

    specify the number of dimensions for the input

    name

    result layer name

  18. val shareFinput: Tensor[Float]

    Permalink
  19. def shareMemory(model: Module[Float], isShareOutput: Boolean = false): Unit

    Permalink

    share the storage of SpatialConvolution fInput note that this sharing only works for Inference only

    share the storage of SpatialConvolution fInput note that this sharing only works for Inference only

    model

    model to share

  20. def stopGradient[T](model: Graph[T])(implicit arg0: ClassTag[T]): Unit

    Permalink

    Stop the input gradient of layers whose name ended with priorbox in a model, their input gradient are not computed.

    Stop the input gradient of layers whose name ended with priorbox in a model, their input gradient are not computed.

    model

    the graph model

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

    Permalink
    Definition Classes
    AnyRef
  22. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  23. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from AnyRef

Inherited from Any

Ungrouped