(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)

        `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

	{ir.OBITNOT, types.TINT64}:  ssa.OpCom64,
	{ir.OBITNOT, types.TUINT64}: ssa.OpCom64,

	{ir.OIMAG, types.TCOMPLEX64}:  ssa.OpComplexImag,
	{ir.OIMAG, types.TCOMPLEX128}: ssa.OpComplexImag,
	{ir.OREAL, types.TCOMPLEX64}:  ssa.OpComplexReal,
	{ir.OREAL, types.TCOMPLEX128}: ssa.OpComplexReal,

	{ir.OMUL, types.TINT8}:    ssa.OpMul8,
	{ir.OMUL, types.TUINT8}:   ssa.OpMul8,
	{ir.OMUL, types.TINT16}:   ssa.OpMul16,