ncdl.nn.Softsign
- class ncdl.nn.Softsign(*args: Any, **kwargs: Any)
Applies the element-wise 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)
- __init__(*args: Any, **kwargs: Any) None
Methods
__init__(*args, **kwargs)forward(input)