Sigmoid

class torch.nn.Sigmoid [source]

Applies the element-wise function:

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

Shape:

• Input: $(N, *)$ where * means, any number of additional dimensions
• Output: $(N, *)$ , same shape as the input

Examples:

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