[object Object]

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

• API description: Performs backpropagation of . It is used to compute the points of the output gradient tensor and map them to the positions of the input gradient tensor. The output gradient values are accumulated to the input gradient tensor.
• Formula:$$gradInput(N, C, floor ( scales * ( L + 0.5 ))) += gradOutput( N, C, L)$$

[object Object]

Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, [object Object] 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, $outputSize[0]/height L of output shape$ must be less than or equal to 50.
• Either outputSize or scales must be used.
  • If the value of scales is equal to 0, the value of outputSize is used.
  • If the value of scales is greater than 0, the value of scales is used, and $outputSize = [floor(inputSize\_L * scales)]$.
• Deterministic computing:
  • aclnnUpsampleNearestExact1dBackward 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 .