silu

Contents

silu#

class saiunit.math.silu(x, unit_to_scale=None)#

SiLU (aka swish) activation function.

Computes the element-wise function:

\[\mathrm{silu}(x) = x \cdot \mathrm{sigmoid}(x) = \frac{x}{1 + e^{-x}}\]

swish() and silu() are both aliases for the same function.

Parameters:

  • x (Quantity | Array | ndarray | bool | number | bool | int | float | complex) – Input array. Must be unitless if a Quantity.

  • unit_to_scale (Unit | None) – Unit used to convert x to a dimensionless number before applying the activation.

Returns:

out – An array with the same shape as x.

Return type:

Array

Examples

>>> import jax.numpy as jnp
>>> import saiunit.math as sumath
>>> sumath.silu(jnp.array([-2., 0., 2.]))
Array([-0.23840584,  0.        ,  1.7615942 ], dtype=float32)
Contents