Softshrink

class torch.nn.Softshrink(lambd=0.5)

Applies the soft shrinkage function element-wise.

\[\text{SoftShrinkage}(x) = \begin{cases} x - \lambda, & \text{ if } x > \lambda \\ x + \lambda, & \text{ if } x < -\lambda \\ 0, & \text{ otherwise } \end{cases} \]

Parameters:

lambd (float) – the \(\lambda\) (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.

Examples:

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