mindspore.nn.CELU

class mindspore.nn.CELU(alpha=1.0)[source]

Continuously differentiable exponential linear units activation function.

Applies the continuously differentiable exponential linear units function element-wise.

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

CELU Activation Function Graph:

Parameters: alpha (float) – The \(\alpha\) value for the Celu formulation. Default: 1.0 .

Inputs:

x (Tensor) - The input of CELU. The required dtype is float16 or float32. The shape is \((N,*)\) where \(*\) means, any number of additional dimensions.

Outputs:

Tensor, with the same type and shape as the x.

Raises

TypeError – If alpha is not a float.
ValueError – If alpha has the value of 0.
TypeError – If x is not a Tensor.
TypeError – If the dtype of ‘input_x’ is neither float16 nor float32.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> x = Tensor(np.array([-2.0, -1.0, 1.0, 2.0]), mindspore.float32)
>>> celu = nn.CELU()
>>> output = celu(x)
>>> print(output)
[-0.86466473 -0.63212055  1.          2.        ]