nn_relu6 function

ReLu6 module

ReLu6 module

Applies the element-wise function:

nn_relu6(inplace = FALSE)

Arguments

  • inplace: can optionally do the operation in-place. Default: FALSE

Details

\mboxReLU6(x)=min(max(0,x),6) \mbox{ReLU6}(x) = \min(\max(0,x), 6)

Shape

  • Input: (N,)(N, *) where * means, any number of additional dimensions
  • Output: (N,)(N, *), same shape as the input

Examples

if (torch_is_installed()) { m <- nn_relu6() input <- torch_randn(2) output <- m(input) }
  • Maintainer: Daniel Falbel
  • License: MIT + file LICENSE
  • Last published: 2025-02-14