org.apache.mxnet.javaapi

DeconvolutionParam

Related Doc: package javaapi

class DeconvolutionParam extends AnyRef

This Param Object is specifically used for Deconvolution

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. DeconvolutionParam
  2. AnyRef
  3. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new DeconvolutionParam(data: NDArray, weight: NDArray, bias: NDArray, kernel: Shape, num_filter: Integer)

    data

    Input tensor to the deconvolution operation.

    weight

    Weights representing the kernel.

    bias

    Bias added to the result after the deconvolution operation.

    kernel

    Deconvolution kernel size: (w,), (h, w) or (d, h, w). This is same as the kernel size used for the corresponding convolution

    num_filter

    Number of output filters.

Value Members

  1. final def !=(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any
  2. final def ##(): Int

    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any
  4. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  5. def clone(): AnyRef

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

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

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

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  9. def getAdj(): Shape

  10. def getBias(): NDArray

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

    Definition Classes
    AnyRef → Any
  12. def getCudnn_off(): Boolean

  13. def getCudnn_tune(): String

  14. def getData(): NDArray

  15. def getDilate(): Shape

  16. def getKernel(): Shape

  17. def getLayout(): String

  18. def getNo_bias(): Boolean

  19. def getNum_filter(): Integer

  20. def getNum_group(): Integer

  21. def getOut(): mxnet.NDArray

  22. def getPad(): Shape

  23. def getStride(): Shape

  24. def getTarget_shape(): Shape

  25. def getWeight(): NDArray

  26. def getWorkspace(): Long

  27. def hashCode(): Int

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

    Definition Classes
    Any
  29. final def ne(arg0: AnyRef): Boolean

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

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

    Definition Classes
    AnyRef
  32. def setAdj(adj: Shape): DeconvolutionParam

    adj

    Adjustment for output shape: (w,), (h, w) or (d, h, w). If target_shape is set, adj will be ignored and computed accordingly.

  33. def setCudnn_off(cudnn_off: Boolean): DeconvolutionParam

    cudnn_off

    Turn off cudnn for this layer.

  34. def setCudnn_tune(cudnn_tune: String): DeconvolutionParam

    cudnn_tune

    Whether to pick convolution algorithm by running performance test.

  35. def setDilate(dilate: Shape): DeconvolutionParam

    dilate

    Dilation factor for each dimension of the input: (w,), (h, w) or (d, h, w). Defaults to 1 for each dimension.

  36. def setLayout(layout: String): DeconvolutionParam

    layout

    Set layout for input, output and weight. Empty for default layout, NCW for 1d, NCHW for 2d and NCDHW for 3d.NHWC and NDHWC are only supported on GPU.

  37. def setNo_bias(no_bias: Boolean): DeconvolutionParam

    no_bias

    Whether to disable bias parameter.

  38. def setNum_group(num_group: Integer): DeconvolutionParam

    num_group

    Number of groups partition.

  39. def setOut(out: NDArray): DeconvolutionParam

  40. def setPad(pad: Shape): DeconvolutionParam

    pad

    The amount of implicit zero padding added during convolution for each dimension of the input: (w,), (h, w) or (d, h, w). (kernel-1)/2 is usually a good choice. If target_shape is set, pad will be ignored and a padding that will generate the target shape will be used. Defaults to no padding.

  41. def setStride(stride: Shape): DeconvolutionParam

    stride

    The stride used for the corresponding convolution: (w,), (h, w) or (d, h, w). Defaults to 1 for each dimension.

  42. def setTarget_shape(target_shape: Shape): DeconvolutionParam

    target_shape

    Shape of the output tensor: (w,), (h, w) or (d, h, w).

  43. def setWorkspace(workspace: Long): DeconvolutionParam

    workspace

    Maximum temporary workspace allowed (MB) in deconvolution.This parameter has two usages. When CUDNN is not used, it determines the effective batch size of the deconvolution kernel. When CUDNN is used, it controls the maximum temporary storage used for tuning the best CUDNN kernel when limited_workspace strategy is used.

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

    Definition Classes
    AnyRef
  45. def toString(): String

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

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from AnyRef

Inherited from Any

Ungrouped