[object Object][object Object]

[object Object]undefined[object Object]

Description: Performs backpropagation of .

[object Object]

Each operator has calls. First, aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnAdaptiveAvgPool3dBackward is called to perform computation.

• [object Object]
• [object Object]

[object Object]

• Parameters:

  • gradOutput (aclTensor*, compute input): gradient of the current node, aclTensor on the device. The data type can be BFLOAT16, FLOAT16, or FLOAT32, and must be the same as that of self. are supported. The shape can be 4D or 5D. The dimension values are positive numbers, and the total number of dimensions is the same as that of self. The can be NCDHW or ND, and must be the same as that of self.
  • self (aclTensor*, compute input): input tensor, leaf node, aclTensor on the device. The data type can be BFLOAT16, FLOAT16, or FLOAT32. are supported. The shape can be 4D or 5D, and the dimension values are positive numbers. The can be NCDHW or ND.
  • out (aclTensor*, compute output): output tensor, corresponding to the gradient of the input leaf node, aclTensor on the device. The data type can be BFLOAT16, FLOAT16, or FLOAT32. The shape must be the same as that of self. The can be NCDHW or ND, and the data type must be the same as that of self.
  • workspaceSize (uint64_t*, output): size of the workspace to be allocated on the device.
  • executor (aclOpExecutor**, output): operator executor, containing the operator computation process.

• Returns:

  aclnnStatus: status code. For details, see .

[object Object]

• Parameters:

  • workspace (void*, input): address of the workspace to be allocated on the device.
  • workspaceSize (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling the first-phase API aclnnAdaptiveAvgPool3dBackwardGetWorkspaceSize.
  • executor (aclOpExecutor*, input): operator executor, containing the operator computation process.
  • stream (aclrtStream, input): stream for executing the task.

• Returns:

  aclnnStatus: status code. For details, see .

[object Object]

• Deterministic compute:
  • aclnnAdaptiveAvgPool3dBackward defaults to a non-deterministic implementation. You can call aclrtCtxSetSysParamOpt to enable deterministic compute.

[object Object]

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