[object Object]

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

• Function: performs dequantization on the input x based on the input scale and offset.
• Formula:

  • When sqrtMode is false, the calculation formula is as follows:

    $$y = float16((x+offset) * scale)$$

  • When sqrtMode is true, the calculation formula is as follows:

    $$y = float16((x+offset) * scale * scale)$$

[object Object]

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

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas inference products[object Object]:
    • Data type:
      • The input parameter [object Object] supports only INT8.
      • The input parameters [object Object] and [object Object] and output parameter [object Object] do not support BFLOAT16.
    • The input parameter [object Object] can only be set to 1, indicating FLOAT16.

• 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:
  • aclnnAscendAntiQuant defaults to a deterministic implementation.

[object Object]

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