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) - The input tensor whose data type must be float16 or float32.
- Outputs:
Tensor, with the same type and shape as the input_x.
- Raises
- 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]