Shrink

Description

Single-input single-output computation, If x < -lambda, y = x + bias; If x > lambda, y = x - bias; Otherwise, y = 0.

Input

One input:

data: tensor of type float16 or float.

Output

One output:

y: tensor. Has the same shape and data type as the input data.

Attribute

bias: float. Defaults to 0.0.

lambda: float. Defaults to 0.5.

ONNX Opset Support

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