torchact.nn.Softmax

class torchact.nn.Softmax(dim: Optional[int] = None)

Implementation of Softmax.

\(\text{Softmax}(x_{i}) = \frac{\exp(x_i)}{\sum_j \exp(x_j)}\)

Parameters

dim (int) – Softmax dimension. Default: None

Examples::

>>> import torch, torchact
>>> m = torchact.nn.Softmax()
>>> input = torch.tensor([1.0, -2.0, 0.0, 3.0])
>>> output = m(input)
>>> print(output)
tensor([0.1135, 0.0057, 0.0418, 0.8390])