(e.g. tf.complex64 or tf.complex128) as tf.cast() make imaginary part 0 while tf.bitcast()
gives module error.
For example,

Example 1:

>>> a = [1., 2., 3.]
>>> equality_bitcast = tf.bitcast(a, tf.complex128)
Traceback (most recent call last):
...
InvalidArgumentError: Cannot bitcast from 1 to 18 [Op:Bitcast]
>>> equality_cast = tf.cast(a, tf.complex128)
>>> print(equality_cast)

		{"Byte", Const, 5},
		{"Chan", Type, 5},
		{"ChanDir", Type, 5},
		{"CheckExpr", Func, 13},
		{"Checker", Type, 5},
		{"Checker.Info", Field, 5},
		{"Comparable", Func, 5},
		{"Complex128", Const, 5},
		{"Complex64", Const, 5},
		{"Config", Type, 5},
		{"Config.Context", Field, 18},
		{"Config.DisableUnusedImportCheck", Field, 5},
		{"Config.Error", Field, 5},

        `tf.float64` (for which there was no GPU implementation). In this
        current release, GPU support for other floating-point types
        (`tf.float16`, `tf.float64`, `tf.complex64`, and `tf.complex128`) has
        been added for this op. If you were relying on the determinism of the
        `tf.float64` CPU implementation being automatically selected because of