Softshrink

class torch.nn.modules.activation.Softshrink(lambd=0.5) [source]

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)

extra_repr() [source]

Return the extra representation of the module.

Return type

str

forward(input) [source]

Run forward pass.

Return type

Tensor