GELU module
Applies the Gaussian Error Linear Units function: [REMOVE_ME]
nn_gelu(approximate = "none")
approximate
: the gelu approximation algorithm to use: 'none'
or 'tanh'
. Default: 'none'
.Applies the Gaussian Error Linear Units function:
where is the Cumulative Distribution Function for Gaussian Distribution.
*
means, any number of additional dimensionsif (torch_is_installed()) { m <- nn_gelu() input <- torch_randn(2) output <- m(input) }
Useful links