Softplus
Applies element-wise, the function Softplus(x) = 1/β * log(1 + exp(β * x)).
nnf_softplus(input, beta = 1, threshold = 20)
input |
(N,*) tensor, where * means, any number of additional dimensions |
beta |
the beta value for the Softplus formulation. Default: 1 |
threshold |
values above this revert to a linear function. Default: 20 |
For numerical stability the implementation reverts to the linear function when input * β > threshold.
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.