lamp-core
API
Generated with
lamp-core/lamp/lamp.autograd/VariableNonConstant

VariableNonConstant

lamp.autograd.VariableNonConstant
See theVariableNonConstant companion object
case class VariableNonConstant(op1: Op, value: STen, pd: STen) extends Variable

A variable whose parent is not empty, neither its partial derivative

Attributes

Companion
object
Graph
Supertypes
trait Serializable
trait Product
trait Equals
trait Variable
class Object
trait Matchable
class Any
Show all

Members list

Value members

Inherited methods

def *[S : Sc](other: Double): Variable

Attributes

Inherited from:
Variable
def *[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def +[S : Sc](other: Double): Variable

Attributes

Inherited from:
Variable
def +[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def -[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def /[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def argmax[S : Sc](dim: Long, keepDim: Boolean): Variable

Attributes

Inherited from:
Variable
def assign[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def atan[S : Sc]: Variable

Attributes

Inherited from:
Variable
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.

Attributes

Inherited from:
Variable
def binaryCrossEntropyWithLogitsLoss[S : Sc](target: STen, posWeights: Option[STen], reduction: Reduction): Variable

Attributes

Inherited from:
Variable
def bmm[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def cast[S : Sc](precision: FloatingPointPrecision): Variable

Attributes

Inherited from:
Variable
def cat[S : Sc](other: Variable, dim: Long): Variable

Attributes

Inherited from:
Variable
def choleskyLower[S : Sc]: Variable

Attributes

Inherited from:
Variable
def choleskySolve[S : Sc](factor: Variable, upper: Boolean): Variable

Attributes

Inherited from:
Variable
def clamp[S : Sc](min: Variable, max: Variable): Variable

Attributes

Inherited from:
Variable
def colSum[S : Sc]: Variable

Attributes

Inherited from:
Variable
def cos[S : Sc]: Variable

Attributes

Inherited from:
Variable
def cross[S : Sc](other: Variable, dim: Int): Variable

Attributes

Inherited from:
Variable
def crossEntropy[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def debug[S : Sc](fun: (STen, Boolean, Boolean) => Unit): Variable

Attributes

Inherited from:
Variable
def detached: Constant

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

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

Attributes

Inherited from:
Variable
def diag[S : Sc](diagonal: Long): Variable

Attributes

Inherited from:
Variable
def dropout[S : Sc](prob: Double, train: Boolean): Variable

Attributes

Inherited from:
Variable
def euclideanDistance[S : Sc](b: Variable, dim: Int): Variable

Attributes

Inherited from:
Variable
def exp[S : Sc]: Variable

Attributes

Inherited from:
Variable
def expand[S : Sc](shape: List[Long]): Variable

Attributes

Inherited from:
Variable
def expandAs[S : Sc](other: STen): Variable

Attributes

Inherited from:
Variable
def flatten[S : Sc](startDim: Int, endDim: Int): Variable

Attributes

Inherited from:
Variable
def flatten[S : Sc](startDim: Int): Variable

Attributes

Inherited from:
Variable
def flatten[S : Sc]: Variable

Attributes

Inherited from:
Variable
def flattenLastDimensions[S : Sc](dims: Int): Variable

Attributes

Inherited from:
Variable
def gelu[S : Sc]: Variable

Attributes

Inherited from:
Variable
def hardSwish[S : Sc]: Variable

Attributes

Inherited from:
Variable
def indexAdd[S : Sc](index: Variable, dim: Int, maxIndex: Long): Variable

Attributes

Inherited from:
Variable
def indexAddFromSource[S : Sc](index: Variable, dim: Int, source: Variable): Variable

Attributes

Inherited from:
Variable
def indexFill[S : Sc](index: Variable, dim: Int, fillValue: Double): Variable

Attributes

Inherited from:
Variable
def indexSelect[S : Sc](dim: Long, index: Variable): Variable

Attributes

Inherited from:
Variable
def inv[S : Sc]: Variable

Attributes

Inherited from:
Variable
def leakyRelu[S : Sc](negativeSlope: Double): Variable

Attributes

Inherited from:
Variable
def log[S : Sc]: Variable

Attributes

Inherited from:
Variable
def log1p[S : Sc]: Variable

Attributes

Inherited from:
Variable
def logSoftMax[S : Sc](dim: Int): Variable

Attributes

Inherited from:
Variable
def logdet[S : Sc]: Variable

Attributes

Inherited from:
Variable
def makeBooleanMask[S : Sc](q: Long): Variable

Attributes

Inherited from:
Variable
def maskFill[S : Sc](mask: Variable, fill: Double): Variable

Attributes

Inherited from:
Variable
def maskSelect[S : Sc](mask: Variable): Variable

Attributes

Inherited from:
Variable
def maximum[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def mean[S : Sc](dim: List[Int], keepDim: Boolean): Variable

Attributes

Inherited from:
Variable
def mean[S : Sc](dim: List[Int]): Variable

Attributes

Inherited from:
Variable
def minimum[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def mm[S : Sc](other: Variable): Variable

Attributes

Inherited from:
Variable
def mseLoss[S : Sc](target: STen, reduction: Reduction): Variable

Attributes

Inherited from:
Variable
def needsGrad: Boolean

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

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

Attributes

Inherited from:
Variable
def nllLoss[S : Sc](target: STen, weights: STen, reduction: Reduction, ignore: Long): Variable

Attributes

Inherited from:
Variable
def norm2[S : Sc](dim: List[Int], keepDim: Boolean): Variable

Attributes

Inherited from:
Variable
def norm2[S : Sc](dim: List[Int]): Variable

Attributes

Inherited from:
Variable
def normalize[S : Sc](dim: List[Int], eps: Double): Variable

Attributes

Inherited from:
Variable
def oneHot[S : Sc](numClasses: Int): Variable

Attributes

Inherited from:
Variable
def options[S : Sc]: STenOptions

Returns the tensor options of its value.

Returns the tensor options of its value.

Attributes

Inherited from:
Variable
def pinv[S : Sc](rcond: Double): Variable

Attributes

Inherited from:
Variable
def pow[S : Sc](exponent: Variable): Variable

Attributes

Inherited from:
Variable
def pow[S : Sc](const: Double): Variable

Attributes

Inherited from:
Variable
def productElementNames: Iterator[String]

Attributes

Inherited from:
Product
def productIterator: Iterator[Any]

Attributes

Inherited from:
Product
def relu[S : Sc]: Variable

Attributes

Inherited from:
Variable
def repeatInterleave[S : Sc](repeats: Variable, dim: Int): Variable

Attributes

Inherited from:
Variable
def reshape[S : Sc](shape: List[Long]): Variable

Attributes

Inherited from:
Variable
def rowSum[S : Sc]: Variable

Attributes

Inherited from:
Variable
def scatterAdd[S : Sc](index: Variable, dim: Int, maxIndex: Long): Variable

Attributes

Inherited from:
Variable
def select[S : Sc](dim: Long, index: Long): Variable

Attributes

Inherited from:
Variable
def shape: List[Long]

Returns the shape of its value.

Returns the shape of its value.

Attributes

Inherited from:
Variable
def sigmoid[S : Sc]: Variable

Attributes

Inherited from:
Variable
def sin[S : Sc]: Variable

Attributes

Inherited from:
Variable
def slice[S : Sc](dim: Long, start: Long, end: Long, step: Long): Variable

Attributes

Inherited from:
Variable
def smoothL1Loss[S : Sc](target: STen, reduction: Reduction, beta: Double): Variable

Attributes

Inherited from:
Variable
def softplus[S : Sc](beta: Double, threshold: Double): Variable

Attributes

Inherited from:
Variable
def squaredFrobenius[S : Sc]: Variable

Attributes

Inherited from:
Variable
def sum[S : Sc](dim: List[Int], keepDim: Boolean): Variable

Attributes

Inherited from:
Variable
def sum[S : Sc]: Variable

Attributes

Inherited from:
Variable
def swish1[S : Sc]: Variable

Attributes

Inherited from:
Variable
def t[S : Sc]: Variable

Returns a new variable with the first two dimensions transposed.

Returns a new variable with the first two dimensions transposed.

Attributes

Inherited from:
Variable
def tan[S : Sc]: Variable

Attributes

Inherited from:
Variable
def tanh[S : Sc]: Variable

Attributes

Inherited from:
Variable
def toDense[S : Sc]: Variable

Attributes

Inherited from:
Variable
def toDoubleArray: Array[Double]

Attributes

Inherited from:
Variable
def toLongArray: Array[Long]

Attributes

Inherited from:
Variable
override def toString: String

Returns a string representation of the object.

Returns a string representation of the object.

The default representation is platform dependent.

Attributes

Returns

a string representation of the object.

Definition Classes
Variable -> Any
Inherited from:
Variable
def transpose[S : Sc](dim1: Int, dim2: Int): Variable

Returns a new variable with the respective dimensions transposed.

Returns a new variable with the respective dimensions transposed.

Attributes

Inherited from:
Variable
def variance[S : Sc](dim: List[Int]): Variable

Attributes

Inherited from:
Variable
def view[S : Sc](shape: List[Long]): Variable

Attributes

Inherited from:
Variable
def withGrad[S : Sc]: ConstantWithGrad

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

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

Attributes

Inherited from:
Variable
def zeroGrad(): Unit

In place zeros out the partial derivative

In place zeros out the partial derivative

Attributes

Inherited from:
Variable

Concrete fields

val op: Option[Op]

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

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

Attributes

val 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.

Attributes

Inherited fields

val id: UUID

Returns unique, stable and random UUID.

Returns unique, stable and random UUID.

Attributes

Inherited from:
Variable
val sizes: List[Long]

Returns the shape of its value.

Returns the shape of its value.

Attributes

Inherited from:
Variable
lazy val wengert: Seq[Variable]

Returns the Wengert list

Returns the Wengert list

Attributes

Inherited from:
Variable
Generated with