Softmax
Applies a softmax function.
nnf_softmax(input, dim, dtype = NULL)
input |
(Tensor) input |
dim |
(int) A dimension along which softmax will be computed. |
dtype |
( |
Softmax is defined as:
Softmax(x_{i}) = exp(x_i)/∑_j exp(x_j)
It is applied to all slices along dim, and will re-scale them so that the elements
lie in the range [0, 1] and sum to 1.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.