CELU

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

Applies the element-wise function:

$$\text{CELU}(x) = \max(0,x) + \min(0, \alpha * (\exp(x/\alpha) - 1))$$

More details can be found in the paper Continuously Differentiable Exponential Linear Units .

Parameters

• alpha (float) – the $\alpha$ value for the CELU 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.CELU()
>>> input = torch.randn(2)
>>> output = m(input)