[object Object]

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

• API description: Performs backpropagation of .
• Formula:$$gradInput(N, C, floor ( scalesH * ( H + 0.5 )), floor ( scalesW * ( W+ 0.5 ))) += gradOutput( N, C, H ,W)$$

[object Object]

Each operator has calls. First, aclnnUpsampleNearestExact2dBackwardGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnUpsampleNearestExact2dBackward is called to perform computation.

[object Object]

• Parameters:

  [object Object]

• Returns:

  aclnnStatus: 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:

  aclnnStatus: status code. For details, see .

[object Object]

• The upscaling factor for input data must be less than or equal to 50. That is, both $outputSize[0]/height H of output shape$ and $outputSize[1]/width W of output shape$ must be less than or equal to 50.
• Either the H and W axes of the outputSize parameter or the scalesH and scalesW parameters can be used.
  • If the value of scalesH or scalesW is less than or equal to 0, the value of the corresponding axis in outputSize is used.
  • If the value of scalesH or scalesW is greater than 0, the value of scalesH or scalesW is used. That is, the value of the corresponding axis of outputSize is $floor(inputSize\_H * scalesH)$ or $floor(inputSize\_W * scalesW)$.
• Deterministic computing:
  • aclnnUpsampleNearestExact2dBackward defaults to a non-deterministic implementation. You can call aclrtCtxSetSysParamOpt to enable deterministic computing.

[object Object]

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