CELU — PyTorch 2.7 documentation (original) (raw)

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

Applies the CELU function element-wise.

CELU(x)=max⁡(0,x)+min⁡(0,α∗(exp⁡(x/α)−1))\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 α\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)