[object Object]

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

Performs 3D adaptive average pooling on tensor self with the specified 3D output shape (outputSize). Unlike aclnnAvgPool3d, aclnnAdaptiveAvgPool3d only needs to specify the output size to automatically deduce the kernel size and corresponding stride.

[object Object]

Each operator has calls. First, aclnnAdaptiveAvgPool3dGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnAdaptiveAvgPool3d is called to perform computation.

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas inference products[object Object]: The data types of the [object Object] and [object Object] parameters do not support BFLOAT16.

• 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:

  • aclnnAdaptiveAvgPool3d defaults to a deterministic implementation.

• Shape description:

  • self.shape = (N, C, Din, Hin, Win) or ( C, Din, Hin, Win)
  • outputSize = [Dout, Hout, Wout]
  • out.shape = (N, C, Dout, Hout, Wout) or ( C, Dout, Hout, Wout)

[object Object]

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