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

• Description: Performs instance normalization. Compared with , aclnnInstanceNorm normalizes each sample instance instead of the entire batch, making this function more suitable for processing data such as images.
• Formula:$$y = {{x-E(x)}\over\sqrt {Var(x)+eps}} * gamma + beta$$

[object Object]

Each operator has calls. First, aclnnInstanceNormGetWorkspaceSize is called to obtain the input parameters and compute the workspace size required by the process. Then, aclnnInstanceNorm 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 validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns

  aclnnStatus: status code. For details, see .

[object Object]

• Functional dimensions:
  • Supported data types:
    • x, gamma, beta, y, mean, and variance support FLOAT32 and FLOAT16.
  • The data format can be ND.
  • The shape of x and y must be four-dimensional. gamma/beta must be one-dimensional and consistent with the C axis of x and y.
  • The H*W size of x and y must be greater than or equal to 32 bytes, and the C axis size must also be greater than or equal to 32 bytes.
  • dataFormat can only be NHWC or NCHW.
• Boundary value scenarios:
  • When the input is [object Object], the output is [object Object].
  • When the input is [object Object], the output is [object Object].
• Deterministic computation:
  • aclnnInstanceNorm defaults to a deterministic implementation.

[object Object]

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