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: $(N,\ast )$ where * means, any number of additional dimensions

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

Details

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

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)
}