mindspore.ops.softsign

mindspore.ops.softsign(x)[source]

Softsign activation function.

The function is shown as follows:

\[\text{SoftSign}(x) = \frac{x}{1 + |x|}\]

Parameters

x (Tensor) – Tensor of shape \((N, *)\), where \(*\) means, any number of additional dimensions, with float16 or float32 data type.

Returns

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

Raises

TypeError – If x is not a Tensor.
TypeError – If dtype of x is neither float16 nor float32.

Supported Platforms:: Ascend GPU CPU

Examples

>>> from mindspore.ops import functional as F
>>> x = Tensor(np.array([0, -1, 2, 30, -30]), mindspore.float32)
>>> output = F.softsign(x)
>>> print(output)
[ 0.        -0.5         0.6666667  0.9677419 -0.9677419]