nn_log_softmax: LogSoftmax module

Description Usage Arguments Details Value Shape Examples

Description

Applies the \log(\mbox{Softmax}(x)) function to an n-dimensional input Tensor. The LogSoftmax formulation can be simplified as:

Usage

1

Arguments

dim

(int): A dimension along which LogSoftmax will be computed.

Details

\mbox{LogSoftmax}(x_{i}) = \log≤ft(\frac{\exp(x_i) }{ ∑_j \exp(x_j)} \right)

Value

a Tensor of the same dimension and shape as the input with values in the range [-inf, 0)

Shape

Examples

1
2
3
4
5
6
if (torch_is_installed()) {
m <- nn_log_softmax(1)
input <- torch_randn(2, 3)
output <- m(input)

}

torch documentation built on Oct. 7, 2021, 9:22 a.m.