Softplus

class torch.nn.Softplus(beta=1, threshold=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)

© 2019 Torch Contributors
Licensed under the 3-clause BSD License.
https://pytorch.org/docs/1.8.0/generated/torch.nn.Softplus.html