tf.math.exp

Computes exponential of x element-wise. y=ex.

Main aliases

tf.exp

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.exp, tf.compat.v1.math.exp

This function computes the exponential of the input tensor element-wise. i.e. math.exp(x) or ex, where x is the input tensor. e denotes Euler's number and is approximately equal to 2.718281. Output is positive for any real input.

x = tf.constant(2.0)
tf.math.exp(x)
<tf.Tensor: shape=(), dtype=float32, numpy=7.389056>
x = tf.constant([2.0, 8.0])
tf.math.exp(x)
<tf.Tensor: shape=(2,), dtype=float32,
numpy=array([   7.389056, 2980.958   ], dtype=float32)>

For complex numbers, the exponential value is calculated as

ex+iy=exeiy=ex(cos(y)+isin(y))

For 1+1j the value would be computed as:

e1(cos(1)+isin(1))=2.7182817×(0.5403023+0.84147096j)

x = tf.constant(1 + 1j)
tf.math.exp(x)
<tf.Tensor: shape=(), dtype=complex128,
numpy=(1.4686939399158851+2.2873552871788423j)>

x A tf.Tensor. Must be one of the following types: bfloat16, half, float32, float64, complex64, complex128.
name A name for the operation (optional).

A tf.Tensor. Has the same type as x.

numpy compatibility

Equivalent to np.exp