[object Object]

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

• Description: Computes the group normalization result out, mean value meanOut, and reciprocal of the standard deviation rstdOut of the input self.

• Formula:

  Assume $x = self$, where $E[x] = \bar{x}$ represents the mean value of $x$, and $Var[x] = \frac{1}{n - 1} * \sum_{i=1}^n(x_i - E[x])^2$ represents the sample variance of $x$.

  $$out = \frac{x - E[x]}{\sqrt{Var[x] + eps}} * \gamma + \beta$$ $$meanOut = E[x]$$ $$rstdOut = \frac{1}{\sqrt{Var[x] + eps}}$$

[object Object]

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

[object Object]

• Parameters

  [object Object]

  • [object Object]Atlas training products[object Object] and [object Object]Atlas inference products[object Object]:

    The data types of self, gamma, beta, out, meanOut, and rstdOut cannot be BFLOAT16.

• Returns

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

  The first-phase API implements input parameter validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns

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

[object Object]

• Deterministic computation:
  • aclnnGroupNorm defaults to a deterministic implementation.

[object Object]

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