AutoGrad

Value Members

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

   Definition Classes

   AnyRef

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

   Definition Classes

   Any

3. final def ##(): Int

   Definition Classes

   AnyRef → Any

4. final def ==(arg0: AnyRef): Boolean

   Definition Classes

   AnyRef

5. final def ==(arg0: Any): Boolean

   Definition Classes

   Any

6. val EPSILON: Double

7. def abs[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

   Element-wise absolute value.

   Element-wise absolute value.

   x

   A variable.

   returns

   A variable.

8. final def asInstanceOf[T0]: T0

   Definition Classes

   Any

9. def batchDot[T](x: Variable[T], y: Variable[T], axes: List[Int], normalize: Boolean = false)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

   Operator that computes a dot product between samples in two tensors.

   Operator that computes a dot product between samples in two tensors.

   x

   A variable.

   y

   A variable.

   axes

   Axes along which to perform multiplication.

   normalize

   Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples.

10. def clip[T](x: Variable[T], min: Double, max: Double)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise value clipping.

    Element-wise value clipping.

    x

    A variable.

    min

    Double.

    max

    Double.

    returns

    A variable.

11. def clone(): AnyRef

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

12. def contiguous[T](input: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Turn the output and grad to be contiguous for the input Variable

13. def epsilon[T]()(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Double

    Define the value of epsilon.

    Define the value of epsilon.

    returns

    A value of type Double.

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

    Definition Classes

    AnyRef

15. def equals(arg0: Any): Boolean

    Definition Classes

    AnyRef → Any

16. def exp[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise exponential.

    Element-wise exponential.

    x

    A variable.

    returns

    A variable.

17. def expandDims[T](x: Variable[T], axis: Int)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Adds a 1-sized dimension at index "axis".

    Adds a 1-sized dimension at index "axis".

    axis

    Position where to add a new axis. You should start from 1 as dim 0 is for batch.

18. def finalize(): Unit

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

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

    Definition Classes

    AnyRef → Any

20. def hashCode(): Int

    Definition Classes

    AnyRef → Any

21. final def isInstanceOf[T0]: Boolean

    Definition Classes

    Any

22. def l2Normalize[T](x: Variable[T], axis: Int)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Normalizes a tensor wrt the L2 norm alongside the specified axis.

    Normalizes a tensor wrt the L2 norm alongside the specified axis.

    x

    A variable.

    axis

    Axis along which to perform multiplication.

23. def log[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise log.

    Element-wise log.

    x

    A variable.

    returns

    A variable.

24. def maximum[T](x: Variable[T], y: Double)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise maximum of two variables

    Element-wise maximum of two variables

    x

    A variable.

    y

    Double

    returns

    A variable.

25. def maximum[T](x: Variable[T], y: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise maximum of two variables

    Element-wise maximum of two variables

    x

    A variable.

    y

    A variable.

    returns

    A variable.

26. def mean[T](x: Variable[T], axis: Int = 0, keepDims: Boolean = false)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Mean of a tensor, alongside the specified axis.

    Mean of a tensor, alongside the specified axis.

    axis

    axis to compute the mean. 0-based indexed.

    keepDims

    A boolean, whether to keep the dimensions or not. If keepdims is False, the rank of the tensor is reduced by 1. If keep_dims is True, the reduced dimensions are retained with length 1.

    returns

    A tensor with the mean of elements of x.

27. def mm[T](x: Variable[T], y: Variable[T], axes: List[Int])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Module to perform matrix multiplication on two mini-batch inputs, producing a mini-batch.

    Module to perform matrix multiplication on two mini-batch inputs, producing a mini-batch.

    x

    A variable.

    y

    A variable.

    axes

    Axes along which to perform multiplication.

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

    Definition Classes

    AnyRef

29. final def notify(): Unit

    Definition Classes

    AnyRef

30. final def notifyAll(): Unit

    Definition Classes

    AnyRef

31. def pow[T](x: Variable[T], a: Double)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise exponentiation.

    Element-wise exponentiation.

    x

    A variable.

    a

    Double.

    returns

    A variable.

32. def softplus[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Softplus of a variable.

    Softplus of a variable.

    x

    A variable.

    returns

    A variable.

33. def softsign[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Softsign of a variable.

    Softsign of a variable.

    x

    A variable.

    returns

    A variable.

34. def sqrt[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise square root.

    Element-wise square root.

    x

    A variable.

    returns

    A variable.

35. def square[T](x: Variable[T])(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Element-wise square.

    Element-wise square.

    x

    A variable.

    returns

    A variable.

36. def stack[T](inputs: List[Variable[T]], axis: Int = 1)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Stacks a list of rank R tensors into a rank R+1 tensor.

    Stacks a list of rank R tensors into a rank R+1 tensor.

    axis

    axis along which to perform stacking.

37. def sum[T](x: Variable[T], axis: Int = 0, keepdims: Boolean = false)(implicit arg0: ClassTag[T], ev: TensorNumeric[T]): Variable[T]

    Sum of the values in a variable, alongside the specified axis.

    Sum of the values in a variable, alongside the specified axis.

    x

    A variable.

    axis

    axis to compute the mean. 0-based indexed.

    keepdims

    A boolean, whether to keep the dimensions or not. If keepDims is False, the rank of the variable is reduced by 1. If keepDims is True, the reduced dimensions are retained with length 1.

    returns

    A variable with the mean of elements of x.

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

    Definition Classes

    AnyRef

39. def toString(): String

    Definition Classes

    AnyRef → Any

40. final def wait(): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

41. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

42. final def wait(arg0: Long): Unit

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )