silu¶

dragon.vm.torch.nn.functional.silu(input)[source]¶

Apply the sigmoid linear unit to input. [Hendrycks & Gimpel, 2016].

The SiLU function is defined as:

\[\text{SiLU}(x) = x \cdot \frac{1}{1 + \exp(-x)} \]

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.

Returns:

dragon.vm.torch.Tensor – The output tensor.

See also

torch.nn.SiLU(…)