mindspore.ops.celu

mindspore.ops.celu(x, alpha=1.0)[source]

celu activation function, computes celu (Continuously differentiable exponential linear units) of input tensors element-wise. The formula is defined as follows:

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

For more details, please refer to celu.

Warning

This is an experimental API that is subject to change or deletion.

Parameters

x (Tensor) – The input of celu with data type of float16 or float32.
alpha (float, optional) – The \(\alpha\) value for the Celu formulation. Default: 1.0

Returns

Tensor, has the same data type and shape as the input.

Raises

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

Supported Platforms:: Ascend GPU CPU

Examples

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