LogSoftmax module
Applies the \log(\mbox{Softmax}(x)) function to an n-dimensional input Tensor. The LogSoftmax formulation can be simplified as:
nn_log_softmax(dim)
dim |
(int): A dimension along which LogSoftmax will be computed. |
\mbox{LogSoftmax}(x_{i}) = \log≤ft(\frac{\exp(x_i) }{ ∑_j \exp(x_j)} \right)
a Tensor of the same dimension and shape as the input with values in the range [-inf, 0)
Input: (*) where * means, any number of additional
dimensions
Output: (*), same shape as the input
if (torch_is_installed()) {
m <- nn_log_softmax(1)
input <- torch_randn(2, 3)
output <- m(input)
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.