softplus¶

paddle.fluid.layers.ops. softplus ( x, beta: float = 1.0, threshold: float = 20.0, name=None ) [source]

alias_main

paddle.nn.functional.softplus

alias

paddle.nn.functional.softplus, paddle.nn.functional.activation.softplus

old_api

paddle.fluid.layers.softplus

Softplus Activation Operator

Equation:

\[\begin{split}out = \\frac{1}{beta} * log(1 + e^{beta * x}) For numerical stability, the implementation reverts to the linear function when: beta * x > threshold.\end{split}\]

Parameters

• x (Tensor) – Input of Softplus op, Tensor, dtype: float32 or float64

• beta (float, optional) – The value of beta for softplus. Default is 1

• threshold (float, optional) – The value of threshold for softplus. Default is 20

• name (str, optional) – Name for the operation (optional, default is None)

Returns

The output of Softplus op, Tensor, dtype: float32 or float64

Return type

Variable

Examples

import paddle
import paddle.nn.functional as F

x = paddle.to_tensor([-0.4, -0.2, 0.1, 0.3])
out = F.softplus(x)
print(out)
# [0.513015, 0.598139, 0.744397, 0.854355]