gelu¶

dragon.nn.gelu(
  inputs,
  approximate=False,
  **kwargs
)[source]¶

Apply the gaussian error linear unit. [Hendrycks & Gimpel, 2016].

The GELU function is defined as:

\[\text{GELU}(x) = x\cdot\frac{1}{2}[1 + \text{erf}(x / \sqrt{2})] \]

Examples:

x = dragon.constant([-1., 0., 1.])
print(dragon.nn.gelu(x))

Parameters:

• inputs (dragon.Tensor) – The input tensor.
• approximate (bool, optional, default=False) – Whether to approximate the computation.

Returns:

dragon.Tensor – The output tensor.