Swish¶

class paddle.nn. Swish ( name=None ) [source]

Swish Activation.

\[\begin{split}Swish(x) = \\frac{x}{1 + e^{-x}}\end{split}\]

Parameters

name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Shape:

• input: Tensor with any shape.

• output: Tensor with the same shape as input.

Examples

import paddle
import numpy as np

x = paddle.to_tensor(np.array([-2., 0., 1.]))
m = paddle.nn.Swish()
out = m(x) # [-0.238406, 0., 0.731059]

forward ( x )

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments

extra_repr ( )

Extra representation of this layer, you can have custom implementation of your own layer.