API

 torch / nn / torch.nn


Softplus

class torch.nn.Softplus(beta: int = 1, threshold: int = 20)[source]

Applies the element-wise function:

Softplus(x)=1βlog(1+exp(βx))\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))

SoftPlus is a smooth approximation to the ReLU function and can be used to constrain the output of a machine to always be positive.

For numerical stability the implementation reverts to the linear function when input×β>thresholdinput \times \beta > threshold .

Parameters
  • beta – the β\beta value for the Softplus formulation. Default: 1

  • threshold – values above this revert to a linear function. Default: 20

Shape:
  • Input: (N,)(N, *) where * means, any number of additional dimensions

  • Output: (N,)(N, *) , same shape as the input

../_images/Softplus.png

Examples:

>>> m = nn.Softplus()
>>> input = torch.randn(2)
>>> output = m(input)

此页内容是否对您有帮助