Softsign

Description

Compute the softsign of the input tensor (x/ (1+|x|)).

Input

One input:

x: tensor of type float16, float, or double.

Output

One output:

y: tensor. Has an identical data type and shape to those of the input.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13