nn_gelu {torch} | R Documentation |
GELU module
Description
Applies the Gaussian Error Linear Units function:
Usage
nn_gelu(approximate = "none")
Arguments
approximate |
the gelu approximation algorithm to use: |
Details
where is the Cumulative Distribution Function for Gaussian Distribution.
Shape
Input:
where
*
means, any number of additional dimensionsOutput:
, same shape as the input
Examples
if (torch_is_installed()) {
m <- nn_gelu()
input <- torch_randn(2)
output <- m(input)
}
[Package torch version 0.13.0 Index]