GELU

class torch.nn.GELU(approximate='none') [source]

Applies the Gaussian Error Linear Units function:

$$\text{GELU}(x) = x * \Phi(x)$$

where $\Phi(x)$ is the Cumulative Distribution Function for Gaussian Distribution.

When the approximate argument is ‘tanh’, Gelu is estimated with:

$$\text{GELU}(x) = 0.5 * x * (1 + \text{Tanh}(\sqrt(2 / \pi) * (x + 0.044715 * x^3)))$$

Parameters:

approximate (str, optional) – the gelu approximation algorithm to use: 'none' | 'tanh'. Default: 'none'

Shape:

• Input: $(*)$, where $*$ means any number of dimensions.
• Output: $(*)$, same shape as the input.

Examples:

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