GELU

class torch.nn.GELU(approximate='none')

Applies the Gaussian Error Linear Units function.

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

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

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

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

Parameters

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

Shape:

• Input: $(\ast )$, where $\ast$ means any number of dimensions.

• Output: $(\ast )$, same shape as the input.

Examples:

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

extra_repr()

Return the extra representation of the module.

Return type

str

forward(input)

Runs the forward pass.

Return type

Tensor