torch (version 0.8.1)

nn_celu: CELU module

Description

Applies the element-wise function:

Usage

nn_celu(alpha = 1, inplace = FALSE)

Arguments

alpha

the \(\alpha\) value for the CELU formulation. Default: 1.0

inplace

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

Shape

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

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

Details

$$ \mbox{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1)) $$

More details can be found in the paper Continuously Differentiable Exponential Linear Units.

Examples

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