[object Object]

[object Object][object Object]undefined[object Object]

• Description: Performs non-linear transformation on the input tensor, and applies scaling and bias processing to the input using bias based on the relationship between input self and threshold lambd.

• Formula:

  $$out=\begin{cases} self-bias, self > lambd \\ self+bias, self < -lambd \\ 0, -lambd ≤self ≤lambd\\ \end{cases}$$

[object Object]

Each operator has calls. First, aclnnShrinkGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnShrink is called to perform computation.

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter verification. The following errors may be thrown:

  [object Object]

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• Deterministic compute:
  • aclnnShrink defaults to a deterministic implementation.

[object Object]

The following example is for reference only. For details, see .