Packages

sealed trait Variable extends AnyRef

A value of a tensor valued function, a vertex in the computational graph.

A Variable may be constant, i.e. depends on no other Variables. Constant variables may or may not need their partial derivatives computed.

Linear Supertypes
AnyRef, Any
Known Subclasses
Constant, ConstantWithGrad, ConstantWithoutGrad, VariableNonConstant
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Variable
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Abstract Value Members

  1. abstract def op: Option[Op]

    The parent operation of this value in the computational graph.

    The parent operation of this value in the computational graph. Empty for constants.

  2. abstract def partialDerivative: Option[STen]

    The partial derivative, or a placeholder tensor for the partial derivative.

    The partial derivative, or a placeholder tensor for the partial derivative.

    Returns empty iff this Variable needs no gradient computation. Otherwise a placeholder tensor is allocated upfront when the Variable is allocated.

  3. abstract def value: STen

    The actual tensor value of this Variable.

Concrete Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##: Int
    Definition Classes
    AnyRef → Any
  3. def *[S](other: Double)(implicit arg0: Sc[S]): Variable
  4. def *[S](other: Variable)(implicit arg0: Sc[S]): Variable
  5. def +[S](other: Double)(implicit arg0: Sc[S]): Variable
  6. def +[S](other: Variable)(implicit arg0: Sc[S]): Variable
  7. def -[S](other: Variable)(implicit arg0: Sc[S]): Variable
  8. def /[S](other: Variable)(implicit arg0: Sc[S]): Variable
  9. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  10. def argmax[S](dim: Long, keepDim: Boolean)(implicit arg0: Sc[S]): Variable
  11. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def assign[S](other: Variable)(implicit arg0: Sc[S]): Variable
  13. def atan[S](implicit arg0: Sc[S]): Variable
  14. def backprop(): Unit

    Runs the backpropagation algorithm starting from this value

    Runs the backpropagation algorithm starting from this value

    Only meaningful if this is scalar i.e. the number of elements in the value tensor is 1.

  15. def binaryCrossEntropyWithLogitsLoss[S](target: STen, posWeights: Option[STen] = None, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
  16. def bmm[S](other: Variable)(implicit arg0: Sc[S]): Variable
  17. def cast[S](precision: FloatingPointPrecision)(implicit arg0: Sc[S]): Variable
  18. def cat[S](other: Variable, dim: Long)(implicit arg0: Sc[S]): Variable
  19. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @native()
  20. def colSum[S](implicit arg0: Sc[S]): Variable
  21. def cos[S](implicit arg0: Sc[S]): Variable
  22. def cross[S](other: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
  23. def crossEntropy[S](other: Variable)(implicit arg0: Sc[S]): Variable
  24. def detached: Constant

    Returns an other Variable wrapping the same value tensor, without any parent and with needsGrad=false.

  25. def diag[S](diagonal: Long)(implicit arg0: Sc[S]): Variable
  26. def dropout[S](prob: Double, train: Boolean)(implicit arg0: Sc[S]): Variable
  27. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  28. def equals(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef → Any
  29. def euclideanDistance[S](b: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
  30. def exp[S](implicit arg0: Sc[S]): Variable
  31. def expandAs[S](other: STen)(implicit arg0: Sc[S]): Variable
  32. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable])
  33. def flatten[S](startDim: Int, endDim: Int)(implicit arg0: Sc[S]): Variable
  34. def flatten[S](startDim: Int)(implicit arg0: Sc[S]): Variable
  35. def flatten[S](implicit arg0: Sc[S]): Variable
  36. def flattenLastDimensions[S](dims: Int)(implicit arg0: Sc[S]): Variable
  37. def gelu[S](implicit arg0: Sc[S]): Variable
  38. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  39. def graphMemoryAllocationReport: GraphMemoryAllocationReport
  40. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  41. val id: UUID

    Returns unique, stable and random UUID.

  42. def indexAdd[S](index: Variable, dim: Int, maxIndex: Long)(implicit arg0: Sc[S]): Variable
  43. def indexSelect[S](dim: Long, index: Variable)(implicit arg0: Sc[S]): Variable
  44. def inv[S](implicit arg0: Sc[S]): Variable
  45. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  46. def l1Loss[S](target: STen, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
  47. def leakyRelu[S](negativeSlope: Double)(implicit arg0: Sc[S]): Variable
  48. def log[S](implicit arg0: Sc[S]): Variable
  49. def log1p[S](implicit arg0: Sc[S]): Variable
  50. def logSoftMax[S](dim: Int)(implicit arg0: Sc[S]): Variable
  51. def logdet[S](implicit arg0: Sc[S]): Variable
  52. def makeBooleanMask[S](q: Long)(implicit arg0: Sc[S]): Variable
  53. def maskFill[S](mask: Variable, fill: Double)(implicit arg0: Sc[S]): Variable
  54. def maskSelect[S](mask: Variable)(implicit arg0: Sc[S]): Variable
  55. def mean[S](dim: List[Int], keepDim: Boolean)(implicit arg0: Sc[S]): Variable
  56. def mean[S](dim: List[Int])(implicit arg0: Sc[S]): Variable
  57. def mm[S](other: Variable)(implicit arg0: Sc[S]): Variable
  58. def mseLoss[S](target: STen, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
  59. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  60. def needsGrad: Boolean

    Returns true if lamp.autograd.Variable.partialDerivative is defined.

  61. def nllLoss[S](target: STen, weights: STen, reduction: Reduction = Mean, ignore: Long = -100L)(implicit arg0: Sc[S]): Variable
  62. def normalize[S](dim: List[Int])(implicit arg0: Sc[S]): Variable
  63. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  64. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  65. def oneHot[S](numClasses: Int)(implicit arg0: Sc[S]): Variable
  66. def options[S](implicit arg0: Sc[S]): STenOptions

    Returns the tensor options of its value.

  67. def pow[S](exponent: Variable)(implicit arg0: Sc[S]): Variable
  68. def pow[S](const: Double)(implicit arg0: Sc[S]): Variable
  69. def relu[S](implicit arg0: Sc[S]): Variable
  70. def repeatInterleave[S](repeats: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
  71. def reshape[S](shape: List[Long])(implicit arg0: Sc[S]): Variable
  72. def rowSum[S](implicit arg0: Sc[S]): Variable
  73. def scatterAdd[S](index: Variable, dim: Int, maxIndex: Long)(implicit arg0: Sc[S]): Variable
  74. def select[S](dim: Long, index: Long)(implicit arg0: Sc[S]): Variable
  75. def shape: List[Long]

    Returns the shape of its value.

  76. def sigmoid[S](implicit arg0: Sc[S]): Variable
  77. def sin[S](implicit arg0: Sc[S]): Variable
  78. val sizes: List[Long]

    Returns the shape of its value.

  79. def softplus[S](beta: Double, threshold: Double)(implicit arg0: Sc[S]): Variable
  80. def squaredFrobenius[S](implicit arg0: Sc[S]): Variable
  81. def sum[S](dim: List[Int], keepDim: Boolean)(implicit arg0: Sc[S]): Variable
  82. def sum[S](implicit arg0: Sc[S]): Variable
  83. def swish1[S](implicit arg0: Sc[S]): Variable
  84. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  85. def t[S](implicit arg0: Sc[S]): Variable

    Returns a new variable with the first two dimensions transposed.

  86. def tan[S](implicit arg0: Sc[S]): Variable
  87. def tanh[S](implicit arg0: Sc[S]): Variable
  88. def toDense[S](implicit arg0: Sc[S]): Variable
  89. def toLongMat: Mat[Long]
  90. def toMat: Mat[Double]
  91. def toString(): String
    Definition Classes
    Variable → AnyRef → Any
  92. def transpose[S](dim1: Int, dim2: Int)(implicit arg0: Sc[S]): Variable

    Returns a new variable with the respective dimensions transposed.

  93. def variance[S](dim: List[Int])(implicit arg0: Sc[S]): Variable
  94. def view[S](shape: List[Long])(implicit arg0: Sc[S]): Variable
  95. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  96. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  97. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  98. lazy val wengert: Seq[Variable]

    Returns the Wengert list

  99. def withGrad[S](implicit arg0: Sc[S]): ConstantWithGrad

    Returns an other Variable wrapping the same value tensor, without any parent and with needsGrad=true.

  100. def zeroGrad(): Unit

    In place zeros out the partial derivative

  101. def zipBackward(fn: (STen, STen) => Unit): (Variable, (STen, STen) => Unit)

    Returns a pair of this instance and the supplied function

Inherited from AnyRef

Inherited from Any

Ungrouped