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

• Description: Implements adaptive scaling and shifting of features.
• Formula:$$out = self \times (1 + scaleOptional) + shiftOptional$$ $self \in R ^ {B \times L \times D}$, $scaleOptional \in R ^ {B \times 1 \times D}$, $shiftOptional \in R ^ {B \times 1 \times D}$ (or $scaleOptional \in R ^ {B \times D}$, $shiftOptional \in R ^ {B \times D}$)

[object Object]

Each operator has calls. First, aclnnModulateGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnModulate 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:
  • aclnnModulate defaults to a deterministic implementation.

[object Object]

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