Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!
Get Started for Free

nn_hardtanh

Hardtanh module


Description

Applies the HardTanh function element-wise HardTanh is defined as:

Usage

nn_hardtanh(min_val = -1, max_val = 1, inplace = FALSE)

Arguments

min_val

minimum value of the linear region range. Default: -1

max_val

maximum value of the linear region range. Default: 1

inplace

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

Details

\mbox{HardTanh}(x) = ≤ft\{ \begin{array}{ll} 1 & \mbox{ if } x > 1 \\ -1 & \mbox{ if } x < -1 \\ x & \mbox{ otherwise } \\ \end{array} \right.

The range of the linear region :math:[-1, 1] can be adjusted using min_val and max_val.

Shape

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

  • Output: (N, *), same shape as the input

Examples

if (torch_is_installed()) {
m <- nn_hardtanh(-2, 2)
input <- torch_randn(2)
output <- m(input)

}

torch

Tensors and Neural Networks with 'GPU' Acceleration

v0.3.0
MIT + file LICENSE
Authors
Daniel Falbel [aut, cre, cph], Javier Luraschi [aut], Dmitriy Selivanov [ctb], Athos Damiani [ctb], Christophe Regouby [ctb], Krzysztof Joachimiak [ctb], RStudio [cph]
Initial release

We don't support your browser anymore

Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.