oneflow.nn.functional.celu

oneflow.nn.functional.celu(x: Tensor, alpha: Float = 1.0, inplace: bool = False) → Tensor

Applies the element-wise function:

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

See CELU for more details.

For examples:

>>> import numpy as np
>>> import oneflow as flow

>>> x = np.array([-0.5, 0, 0.5]).astype(np.float32)
>>> input = flow.tensor(x)
>>> out = flow.nn.functional.celu(input, alpha=0.5)
>>> out
tensor([-0.3161,  0.0000,  0.5000], dtype=oneflow.float32)