jax.numpy.tanh

jax.numpy.tanh(x, /)

Calculate element-wise hyperbolic tangent of input.

JAX implementation of numpy.tanh.

The hyperbolic tangent is defined by:

\[tanh(x) = \frac{sinh(x)}{cosh(x)} = \frac{e^x - e^{-x}}{e^x + e^{-x}}\]

Parameters:

x (ArrayLike) – input array or scalar.

Returns:

An array containing the hyperbolic tangent of each element of x, promoting to inexact dtype.

Return type:

Array

Note

jnp.tanh is equivalent to computing -1j * jnp.tan(1j * x).

See also

• jax.numpy.sinh(): Computes the element-wise hyperbolic sine of the input.

• jax.numpy.cosh(): Computes the element-wise hyperbolic cosine of the input.

• jax.numpy.arctanh(): Computes the element-wise inverse of hyperbolic tangent of the input.

Examples

>>> x = jnp.array([[-1, 0, 1],
...                [3, -2, 5]])
>>> with jnp.printoptions(precision=3, suppress=True):
...   jnp.tanh(x)
Array([[-0.762,  0.   ,  0.762],
       [ 0.995, -0.964,  1.   ]], dtype=float32)
>>> with jnp.printoptions(precision=3, suppress=True):
...   -1j * jnp.tan(1j * x)
Array([[-0.762+0.j,  0.   -0.j,  0.762-0.j],
       [ 0.995-0.j, -0.964+0.j,  1.   -0.j]],      dtype=complex64, weak_type=True)

For complex-valued input:

>>> with jnp.printoptions(precision=3, suppress=True):
...   jnp.tanh(2-5j)
Array(1.031+0.021j, dtype=complex64, weak_type=True)
>>> with jnp.printoptions(precision=3, suppress=True):
...   -1j * jnp.tan(1j * (2-5j))
Array(1.031+0.021j, dtype=complex64, weak_type=True)