Xor  // Elementwise logical-xor operation


Produces tensor with boolean element type and shape as the two inputs, which must themselves have boolean element type, where the value at each coordinate of output is 0 (true) if arg0 or arg1 both zero or both nonzero, or 1 otherwise.


Name Element Type Shape
arg0 ngraph::element::boolean any
arg1 ngraph::element::boolean same as arg0


Name Element Type Shape
output ngraph::element::boolean same as arg0

Mathematical Definition

\[\mathtt{output}_{i_0, \ldots, i_{n-1}} = \mathtt{arg0}_{i_0, \ldots, i_{n-1}}\, \mathtt{XOR}\, \mathtt{arg1}_{i_0, \ldots, i_{n-1}}\]

C++ Interface

class Xor : public ngraph::op::util::BinaryElementwiseLogical

Elementwise logical-xor operation.

Public Functions

const NodeTypeInfo &get_type_info() const

Returns the NodeTypeInfo for the node’s class. During transition to type_info, returns a dummy type_info for Node if the class has not been updated yet.

Xor(const Output<Node> &arg0, const Output<Node> &arg1, const AutoBroadcastSpec &auto_broadcast = AutoBroadcastSpec())

Constructs a logical-xor operation.

Output [d0, ...]

  • arg0: Node that produces the first input tensor.[d0, ...]
  • arg1: Node that produces the second input tensor.[d0, ...]
  • auto_broadcast: Auto broadcast specification