sealed trait Constant extends Variable
A variable whose parent is empty
Linear Supertypes
Known Subclasses
Ordering
- Alphabetic
- By Inheritance
Inherited
- Constant
- Variable
- AnyRef
- Any
- Hide All
- Show All
Visibility
- Public
- Protected
Abstract Value Members
- 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.
- Definition Classes
- Variable
- abstract def value: STen
The actual tensor value of this Variable.
The actual tensor value of this Variable.
- Definition Classes
- Variable
Concrete Value Members
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##: Int
- Definition Classes
- AnyRef → Any
- def *[S](other: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def *[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def +[S](other: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def +[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def -[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def /[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- def argmax[S](dim: Long, keepDim: Boolean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def assign[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def atan[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- 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.
- Definition Classes
- Variable
- def binaryCrossEntropyWithLogitsLoss[S](target: STen, posWeights: Option[STen] = None, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def bmm[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def cast[S](precision: FloatingPointPrecision)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def cat[S](other: Variable, dim: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def cholesky[S](upper: Boolean = false)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def choleskySolve[S](factor: Variable, upper: Boolean = false)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @native()
- def colSum[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def cos[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def cross[S](other: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def crossEntropy[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- 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.- Definition Classes
- Variable
- def diag[S](diagonal: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def dropout[S](prob: Double, train: Boolean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- def euclideanDistance[S](b: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def exp[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def expandAs[S](other: STen)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable])
- def flatten[S](startDim: Int, endDim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def flatten[S](startDim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def flatten[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def flattenLastDimensions[S](dims: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def gelu[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def graphMemoryAllocationReport: GraphMemoryAllocationReport
- Definition Classes
- Variable
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- val id: UUID
Returns unique, stable and random UUID.
Returns unique, stable and random UUID.
- Definition Classes
- Variable
- def indexAdd[S](index: Variable, dim: Int, maxIndex: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def indexSelect[S](dim: Long, index: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def inv[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- def l1Loss[S](target: STen, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def leakyRelu[S](negativeSlope: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def log[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def log1p[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def logSoftMax[S](dim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def logdet[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def makeBooleanMask[S](q: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def maskFill[S](mask: Variable, fill: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def maskSelect[S](mask: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def mean[S](dim: List[Int], keepDim: Boolean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def mean[S](dim: List[Int])(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def mm[S](other: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def mseLoss[S](target: STen, reduction: Reduction = Mean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def needsGrad: Boolean
Returns true if lamp.autograd.Variable.partialDerivative is defined.
Returns true if lamp.autograd.Variable.partialDerivative is defined.
- Definition Classes
- Variable
- def nllLoss[S](target: STen, weights: STen, reduction: Reduction = Mean, ignore: Long = -100L)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def normalize[S](dim: List[Int], eps: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- def oneHot[S](numClasses: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def op: None
The parent operation of this value in the computational graph.
- def options[S](implicit arg0: Sc[S]): STenOptions
Returns the tensor options of its value.
Returns the tensor options of its value.
- Definition Classes
- Variable
- def pinv[S](rcond: Double = 1e-5)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def pow[S](exponent: Variable)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def pow[S](const: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def relu[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def repeatInterleave[S](repeats: Variable, dim: Int)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def reshape[S](shape: List[Long])(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def rowSum[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def scatterAdd[S](index: Variable, dim: Int, maxIndex: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def select[S](dim: Long, index: Long)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def shape: List[Long]
Returns the shape of its value.
Returns the shape of its value.
- Definition Classes
- Variable
- def sigmoid[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def sin[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- val sizes: List[Long]
Returns the shape of its value.
Returns the shape of its value.
- Definition Classes
- Variable
- def softplus[S](beta: Double, threshold: Double)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def squaredFrobenius[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def sum[S](dim: List[Int], keepDim: Boolean)(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def sum[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def swish1[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def t[S](implicit arg0: Sc[S]): Variable
Returns a new variable with the first two dimensions transposed.
Returns a new variable with the first two dimensions transposed.
- Definition Classes
- Variable
- def tan[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def tanh[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def toDense[S](implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def toLongMat: Mat[Long]
- Definition Classes
- Variable
- def toMat: Mat[Double]
- Definition Classes
- Variable
- def toString(): String
- Definition Classes
- Variable → AnyRef → Any
- def transpose[S](dim1: Int, dim2: Int)(implicit arg0: Sc[S]): Variable
Returns a new variable with the respective dimensions transposed.
Returns a new variable with the respective dimensions transposed.
- Definition Classes
- Variable
- def variance[S](dim: List[Int])(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- def view[S](shape: List[Long])(implicit arg0: Sc[S]): Variable
- Definition Classes
- Variable
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- lazy val wengert: Seq[Variable]
Returns the Wengert list
Returns the Wengert list
- Definition Classes
- Variable
- def withGrad[S](implicit arg0: Sc[S]): 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.- Definition Classes
- Variable
- def zeroGrad(): Unit
In place zeros out the partial derivative
In place zeros out the partial derivative
- Definition Classes
- Variable
- def zipBackward(fn: (STen, STen) => Unit): (Variable, (STen, STen) => Unit)
Returns a pair of this instance and the supplied function
Returns a pair of this instance and the supplied function
- Definition Classes
- Variable