torch (version 0.8.1)

nn_softmax: Softmax module

Description

Applies the Softmax function to an n-dimensional input Tensor rescaling them so that the elements of the n-dimensional output Tensor lie in the range [0,1] and sum to 1. Softmax is defined as:

Usage

nn_softmax(dim)

Value

: a Tensor of the same dimension and shape as the input with values in the range [0, 1]

Arguments

dim

(int): A dimension along which Softmax will be computed (so every slice along dim will sum to 1).

Shape

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

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

Details

$$ \mbox{Softmax}(x_{i}) = \frac{\exp(x_i)}{\sum_j \exp(x_j)} $$

When the input Tensor is a sparse tensor then the unspecifed values are treated as -Inf.

Examples

if (torch_is_installed()) {
m <- nn_softmax(1)
input <- torch_randn(2, 3)
output <- m(input)
}