Class Pow<T extends TType>

java.lang.Object
org.tensorflow.op.RawOp
org.tensorflow.op.math.Pow<T>
All Implemented Interfaces:
Shaped, Op, Operand<T>

@Operator(group="math") public final class Pow<T extends TType> extends RawOp implements Operand<T>
Computes the power of one value to another. Given a tensor x and a tensor y, this operation computes \(x^y\) for corresponding elements in x and y. For example:
# tensor 'x' is [[2, 2]], [3, 3]]
# tensor 'y' is [[8, 16], [2, 3]]
tf.pow(x, y) ==> [[256, 65536], [9, 27]]
  • Field Details

  • Constructor Details

  • Method Details

    • create

      @Endpoint(describeByClass=true) public static <T extends TType> Pow<T> create(Scope scope, Operand<T> x, Operand<T> y)
      Factory method to create a class wrapping a new Pow operation.
      Type Parameters:
      T - data type for Pow output and operands
      Parameters:
      scope - current scope
      x - The x value
      y - The y value
      Returns:
      a new instance of Pow
    • z

      public Output<T> z()
      Gets z.
      Returns:
      z.
    • asOutput

      public Output<T> asOutput()
      Description copied from interface: Operand
      Returns the symbolic handle of the tensor.

      Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

      Specified by:
      asOutput in interface Operand<T extends TType>
      See Also: