Softsign

class torch.nn.modules.activation.Softsign(*args, **kwargs) [source]

Applies the element-wise Softsign function.

$$\text{SoftSign}(x) = \frac{x}{ 1 + |x|}$$

Shape:

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

Examples:

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

forward(input) [source]

Runs the forward pass.

Return type

Tensor