gelu#

ivy.gelu(x, /, *, approximate=False, out=None)[source]#

Apply the Gaussian error linear unit (GELU) activation function.

Parameters:

  • x (Union[Array, NativeArray]) – Input array.

  • approximate (bool) – Whether to approximate, default is True. (default: False)

  • out (Optional[Array]) – optional output array, for writing the result to. It must have a shape that the (default: None) inputs broadcast to.

Return type:

Array

Returns:

ret – The input array with gelu applied element-wise.

Examples

With ivy.Array input:

>>> x = ivy.array([-1.2, -0.6, 1.5])
>>> y = ivy.gelu(x)
>>> y
ivy.array([-0.138, -0.165, 1.4])

With ivy.NativeArray input:

>>> x = ivy.native_array([-1.3, 3.8, 2.1])
>>> y = ivy.gelu(x)
>>> y
ivy.array([-0.126, 3.8, 2.06])

With ivy.Container input:

>>> x = ivy.Container(a=ivy.array([1., 2.]), b=ivy.array([-0.9, -1.]))
>>> y = ivy.gelu(x)
>>> y
{
    a: ivy.array([0.841, 1.95]),
    b: ivy.array([-0.166, -0.159])
}
Array.gelu(self, /, *, approximate=False, out=None)#

ivy.Array instance method variant of ivy.gelu. This method simply wraps the function, and so the docstring for ivy.gelu also applies to this method with minimal changes.

Parameters:

  • self (Array) – input array.

  • approximate (bool) – whether to use the approximate version of the gelu function. (default: False)

  • out (Optional[Array]) – optional output array, for writing the result to. It must have a shape (default: None) that the inputs broadcast to.

Return type:

Array

Returns:

ret – an array with the gelu activation function applied element-wise.

Examples

>>> x = ivy.array([-1.2, -0.6, 1.5])
>>> y = x.gelu()
>>> print(y)
ivy.array([-0.138, -0.165, 1.4])
Container.gelu(self, /, *, approximate=False, key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False, out=None)#

ivy.Container instance method variant of ivy.gelu. This method simply wraps the function, and so the docstring for ivy.gelu also applies to this method with minimal changes.

Parameters:

  • self (Container) – input container.

  • approximate (bool) – whether to use the gelu approximation algorithm or exact formulation. (default: False)

  • key_chains (Optional[Union[List[str], Dict[str, str]]]) – The key-chains to apply or not apply the method to. Default is None. (default: None)

  • to_apply (bool) – If True, the method will be applied to key_chains, otherwise key_chains (default: True) will be skipped. Default is True.

  • prune_unapplied (bool) – Whether to prune key_chains for which the function was not applied. (default: False) Default is False.

  • map_sequences (bool) – Whether to also map method to sequences (lists, tuples). (default: False) Default is False.

  • out (Optional[Container]) – optional output container, for writing the result to. It must have a shape (default: None) that the inputs broadcast to.

Return type:

Container

Returns:

ret – a container with the gelu unit function applied element-wise.

Examples

>>> x = ivy.Container(a=ivy.array([1., 2.]), b=ivy.array([-0.9, -1.]))
>>> y = x.gelu()
    print(y)
    {
         a: ivy.array([0.841, 1.95]),
         b: ivy.array([-0.166, -0.159])
    }