SiLU

class torch.nn.SiLU

Applies the silu function, element-wise.

Note

See Gaussian Error Linear Units (GELUs) where the SiLU (Sigmoid Linear Unit) was originally coined, and see Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning and Swish: a Self-Gated Activation Function where the SiLU was experimented with later.

$\text{silu}(x) = x * \sigma((x)) \text{where} \sigma(x) \text{is the logistic sigmoid.}$

Shape:

• Input: $(N, *)$ where * means, any number of additional dimensions

• Output: $(N, *)$ , same shape as the input

Examples:

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