torch (version 0.14.2)

nn_softshrink: Softshrink module

Description

Applies the soft shrinkage function elementwise:

Usage

nn_softshrink(lambd = 0.5)

Arguments

lambd

the $\lambda$ (must be no less than zero) value for the Softshrink formulation. Default: 0.5

Shape

• Input: $(N,\ast )$ where * means, any number of additional dimensions

• Output: $(N,\ast )$, same shape as the input

Details

$$\text{SoftShrinkage}(x)=\{\begin{array}{ll}x-\lambda ,& \text{ if }x>\lambda \\ x+\lambda ,& \text{ if }x<-\lambda \\ 0,& \text{ otherwise }\end{array}$$

Examples

if (torch_is_installed()) {
m <- nn_softshrink()
input <- torch_randn(2)
output <- m(input)
}