tf.math.expm1

TensorFlow 1 version

Computes exp(x) - 1 element-wise.

tf.math.expm1(
    x, name=None
)

i.e. exp(x) - 1 or e^(x) - 1, where x is the input tensor. e denotes Euler's number and is approximately equal to 2.718281.

x = tf.constant(2.0)
tf.math.expm1(x) ==> 6.389056

x = tf.constant([2.0, 8.0])
tf.math.expm1(x) ==> array([6.389056, 2979.958], dtype=float32)

x = tf.constant(1 + 1j)
tf.math.expm1(x) ==> (0.46869393991588515+2.2873552871788423j)