nn_sigmoid: Sigmoid module

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

Sigmoid module

Description

Applies the element-wise function:

Usage

nn_sigmoid()

Details

\mbox{Sigmoid}(x) = \sigma(x) = \frac{1}{1 + \exp(-x)}

Shape

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

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

Examples

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

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