Method Shrink
Shrink(TensorFloat, float, float)
Computes an output tensor by applying the element-wise Shrink activation function: f(x) = x + bias if x < lambd. f(x) = x - bias if x > lambd. Otherwise f(x) = 0.
Declaration
public TensorFloat Shrink(TensorFloat X, float bias, float lambd)
Parameters
| Type | Name | Description |
|---|---|---|
| TensorFloat | X | The input tensor. |
| float | bias | The bias value to use for the |
| float | lambd | The lambda value to use for the |
Returns
| Type | Description |
|---|---|
| TensorFloat | The computed output tensor. |