[object Object]

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

• Description: Performs backward computation of the activation function and outputs the gradient of the forward input of the ELU activation function.

• Formula: x denotes an element in selfOrResult.

  • When isResult is True:

    $$gradInput = gradOutput * \begin{cases} scale, \quad x > 0\\ inputScale \ast (x + \alpha \ast scale), \quad x \leq 0 \end{cases}$$

  • When isResult is False:

    $$gradInput = gradOutput * \begin{cases} scale, \quad x > 0\\ inputScale \ast \alpha \ast scale \ast exp(x \ast inputScale), \quad x \leq 0 \end{cases}$$

[object Object]

Each operator has calls. First, aclnnEluBackwardGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation flow. Then, aclnnEluBackward is called to perform computation.

[object Object]

• Parameters

  [object Object]

• 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 computation:
  • aclnnEluBackward defaults to a deterministic implementation.

[object Object]

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