PyTorch
torch / nn / torch.nn
Softshrink¶
-
class
torch.nn.
Softshrink
(lambd: float = 0.5)[source]¶ Applies the soft shrinkage function elementwise:
SoftShrinkage(x)=⎩⎪⎪⎨⎪⎪⎧x−λ,x+λ,0, if x>λ if x<−λ otherwise - Parameters
lambd – the λ (must be no less than zero) value for the Softshrink formulation. Default: 0.5
- Shape:
Input: (N,∗) where * means, any number of additional dimensions
Output: (N,∗) , same shape as the input
Examples:
>>> m = nn.Softshrink() >>> input = torch.randn(2) >>> output = m(input)
此页内容是否对您有帮助
感谢反馈!