ELU

class torch.nn.ELU(alpha=1.0, inplace=False) [source]

Applies the Exponential Linear Unit (ELU) function, element-wise.

Method described in the paper: Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs).

ELU is defined as:

$$\text{ELU}(x) = \begin{cases} x, & \text{ if } x > 0\\ \alpha * (\exp(x) - 1), & \text{ if } x \leq 0 \end{cases}$$

Parameters

• alpha (float) – the $\alpha$ value for the ELU formulation. Default: 1.0
• inplace (bool) – can optionally do the operation in-place. Default: False

Shape:

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

Examples:

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

extra_repr() [source]

Return the extra representation of the module.

Return type

str

forward(input) [source]

Runs the forward pass.

Return type

Tensor