nnf_softshrink: Softshrink

In torch: Tensors and Neural Networks with 'GPU' Acceleration

Softshrink

Description

Applies the soft shrinkage function elementwise

Usage

nnf_softshrink(input, lambd = 0.5)

Arguments

input	(N,*) tensor, where * means, any number of additional dimensions
lambd	the lambda (must be no less than zero) value for the Softshrink formulation. Default: 0.5

torch documentation built on June 7, 2023, 6:19 p.m.