[object Object]

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

• Description: Defines a self-regularized non-monotonic neural activation function.
• Formula:$$out_i = self_i \times tanh(Softplus(self_i))$$

[object Object]

• aclnnMish and aclnnInplaceMish implement the same function in different ways. Select a proper operator based on your requirements.

  • aclnnMish: An output tensor object needs to be created to store the computation result.
  • aclnnInplaceMish: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.

• Each operator has calls. First, aclnnMishGetWorkspaceSize or aclnnInplaceMishGetWorkspaceSize is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, aclnnMish or aclnnInplaceMish is called to perform computation.

[object Object]

• Parameters:

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

• 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]

• Parameters:

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

• 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 compute:
  • aclnnMish&aclnnInplaceMish defaults to a deterministic implementation.

[object Object]

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

aclnnMish API call example:

aclnnInplaceMish API call example: