[object Object]

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

• API description: Performs backpropagation of .

• Formulas:

  $$out(N, C, L) += gradOut( N, C, ceil ( scales * L ))$$

[object Object]

Each operator has calls. First, aclnnUpsampleNearest1dBackwardGetWorkspaceSize is called to obtain the input parameters and compute the required workspace size based on the process. Then, aclnnUpsampleNearest1dBackward is called to perform computation.

[object Object]

• Parameters

  [object Object]
  • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: The data types of the input parameter gradOut and output parameter out must be FLOAT16.

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• The inputSize, outputSize, and scales parameters must meet the following restrictions:

  $$outputSize = floor(inputSize\_L * scales)$$

• Deterministic computation:

  • aclnnUpsampleNearest1dBackward defaults to a deterministic implementation.

[object Object]

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