[object Object]

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

• Description: Performs backpropagation of to compute the gradient of the tensor self.
• Formula:$$out_{i} = gradOutput_{i} \times gradSelf_{i}$$ The formula for computing gradSelf is as follows:$$gradSelf_{i} = \begin{cases} 0, & self_{i} \lt -3, \\ self_{i} / 3 + 0.5, & -3 \le self_{i} \le 3, \\ 1, & self_{i} \gt 3 \end{cases}$$

[object Object]

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

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas training products[object Object]: The data type can be FLOAT16 or FLOAT32.

• 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:
  • aclnnHardswishBackward defaults to a deterministic implementation.

[object Object]

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