TensorFlow 1 version View source on GitHub

Returns the real part of a complex (or real) tensor.

Given a tensor input, this operation returns a tensor of type float that is the real part of each element in input considered as a complex number.

For example:

x = tf.constant([-2.25 + 4.75j, 3.25 + 5.75j])
tf.math.real(x)  # [-2.25, 3.25]

If input is already real, it is returned unchanged.

input A Tensor. Must have numeric type.
name A name for the operation (optional).

A Tensor of type float32 or float64.