Rate this Page
★★★★★

Softshrink#

classtorch.nn.modules.activation.Softshrink(lambd=0.5)[source]#

Applies the soft shrinkage function element-wise.

SoftShrinkage(x)={x−λ, if x>λx+λ, if x<−λ0, otherwise \text{SoftShrinkage}(x) =\begin{cases}x - \lambda, & \text{ if } x > \lambda \\x + \lambda, & \text{ if } x < -\lambda \\0, & \text{ otherwise }\end{cases}
Parameters

lambd (float) – theλ\lambda (must be no less than zero) value for the Softshrink formulation. Default: 0.5

Shape:

  • Input:(∗)(*), where∗* means any number of dimensions.

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

../_images/Softshrink.png

Examples:

>>>m=nn.Softshrink()>>>input=torch.randn(2)>>>output=m(input)
extra_repr()[source]#

Return the extra representation of the module.

Return type

str

forward(input)[source]#

Run forward pass.

Return type

Tensor