tf.bitwise.bitwise_xor

TensorFlow 2 version

Elementwise computes the bitwise XOR of x and y.

tf.bitwise.bitwise_xor(
    x, y, name=None
)

The result will have those bits set, that are different in x and y. The computation is performed on the underlying representations of x and y.

For example:

import tensorflow as tf
from tensorflow.python.ops import bitwise_ops
dtype_list = [tf.int8, tf.int16, tf.int32, tf.int64,
              tf.uint8, tf.uint16, tf.uint32, tf.uint64]

for dtype in dtype_list:
  lhs = tf.constant([0, 5, 3, 14], dtype=dtype)
  rhs = tf.constant([5, 0, 7, 11], dtype=dtype)
  exp = tf.constant([5, 5, 4, 5],  dtype=tf.float32)

  res = bitwise_ops.bitwise_xor(lhs, rhs)
  tf.assert_equal(tf.cast(res, tf.float32), exp) # TRUE