selu

dragon.nn.selu(
  inputs,
  alpha=1.67326,
  gamma=1.0507,
  inplace=False,
  **kwargs
)[source]

Apply the scaled exponential linear unit. [Klambauer et.al, 2017].

The SELU function is defined as:

\[\text{SELU}(x) = \gamma * \begin{cases} x, & \text{ if } x \geq 0 \\ \alpha * (\exp(x) - 1), & \text{ otherwise } \end{cases} \]

Examples:

x = dragon.constant([-1., 0., 1.])
print(dragon.nn.selu(x))
Parameters:
  • inputs (dragon.Tensor) – The input tensor.
  • alpha (float, optional, default=1.67326) – The value to \(\alpha\).
  • gamma (float, optional, default=1.0507) – The value to \(\gamma\).
  • inplace (bool, optional, default=False) – Call in-place or return a new tensor.
Returns:

dragon.Tensor – The output tensor.