mindspore.ops.Softsign

class mindspore.ops.Softsign(*args, **kwargs)[source]

Softsign activation function.

The function is shown as follows:

\[\text{SoftSign}(x) = \frac{x}{ 1 + |x|}\]
Inputs:
  • input_x (Tensor) - Tensor of shape \((N, *)\), where \(*\) means, any number of additional dimensions, with float16 or float32 data type.

Outputs:

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

Raises
  • TypeError – If input_x is not a Tensor.

  • TypeError – If dtype of input_x is neither float16 nor float32.

Supported Platforms:

Ascend

Examples

>>> input_x = Tensor(np.array([0, -1, 2, 30, -30]), mindspore.float32)
>>> softsign = ops.Softsign()
>>> output = softsign(input_x)
>>> print(output)
[ 0.        -0.5         0.6666667  0.9677419 -0.9677419]