nnf_hardshrink: Hardshrink

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

Hardshrink

Description

Applies the hard shrinkage function element-wise

Usage

nnf_hardshrink(input, lambd = 0.5)

Arguments

input	(N,*) tensor, where * means, any number of additional dimensions
lambd	the lambda value for the Hardshrink formulation. Default: 0.5

torch documentation built on May 29, 2024, 9:54 a.m.