Class QuantizedMul<V extends TNumber>

java.lang.Object
org.tensorflow.op.RawOp
org.tensorflow.op.math.QuantizedMul<V>
All Implemented Interfaces:
Op

@Operator(group="math") public final class QuantizedMul<V extends TNumber> extends RawOp
Returns x * y element-wise, working on quantized buffers.
  • Field Details

  • Constructor Details

    • QuantizedMul

      public QuantizedMul(Operation operation)
  • Method Details

    • create

      @Endpoint(describeByClass=true) public static <V extends TNumber> QuantizedMul<V> create(Scope scope, Operand<? extends TNumber> x, Operand<? extends TNumber> y, Operand<TFloat32> minX, Operand<TFloat32> maxX, Operand<TFloat32> minY, Operand<TFloat32> maxY, Class<V> Toutput)
      Factory method to create a class wrapping a new QuantizedMul operation.
      Type Parameters:
      V - data type for QuantizedMul output and operands
      Parameters:
      scope - current scope
      x - The x value
      y - The y value
      minX - The float value that the lowest quantized x value represents.
      maxX - The float value that the highest quantized x value represents.
      minY - The float value that the lowest quantized y value represents.
      maxY - The float value that the highest quantized y value represents.
      Toutput - The value of the Toutput attribute
      Returns:
      a new instance of QuantizedMul
    • z

      public Output<V> z()
      Gets z.
      Returns:
      z.
    • minZ

      public Output<TFloat32> minZ()
      Gets minZ. The float value that the lowest quantized output value represents.
      Returns:
      minZ.
    • maxZ

      public Output<TFloat32> maxZ()
      Gets maxZ. The float value that the highest quantized output value represents.

      NOTE: math.QuantizedMul supports limited forms of broadcasting. More about broadcasting here

      Returns:
      maxZ.