Sigmoid

class torch.nn.modules.activation.Sigmoid(*args, **kwargs)

Applies the Sigmoid function element-wise.

$$\text{Sigmoid}(x)=\sigma (x)=\frac{1}{1+\exp (-x)}$$

Shape:

• Input: $(\ast )$, where $\ast$ means any number of dimensions.

• Output: $(\ast )$, same shape as the input.

Examples:

>>> m = nn.Sigmoid()
>>> input = torch.randn(2)
>>> output = m(input)

forward(input)

Runs the forward pass.

Return type

Tensor