Sign

Description

Computes the sign of the input tensor element-wise.

When the input is of a numeric type:

When the input is of the bool type:

Input

x: input tensor of type int32, float16, or float.

Output

y: output tensor of the identical data type and shape as input x.

ONNX Opset Support

Opset v9/v10/v11/v12/v13/v14/v15/v16/v17/v18