torch.nn.functional.softplus# torch.nn.functional.softplus(input, beta=1, threshold=20) → Tensor# Applies element-wise, the function Softplus(x)=1β∗log(1+exp(β∗x))\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))Softplus(x)=β1∗log(1+exp(β∗x)). For numerical stability the implementation reverts to the linear function when input×β>thresholdinput \times \beta > thresholdinput×β>threshold. See Softplus for more details.
torch.nn.functional.softplus# torch.nn.functional.softplus(input, beta=1, threshold=20) → Tensor# Applies element-wise, the function Softplus(x)=1β∗log(1+exp(β∗x))\text{Softplus}(x) = \frac{1}{\beta} * \log(1 + \exp(\beta * x))Softplus(x)=β1∗log(1+exp(β∗x)). For numerical stability the implementation reverts to the linear function when input×β>thresholdinput \times \beta > thresholdinput×β>threshold. See Softplus for more details.