[object Object]

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

• Description: Computes the SELU activation function element-wise on the input tensor and outputs the result tensor.
• Formula:$$output_i = scale \cdot [\max(0, input_i) + \min(0, \alpha \cdot (\exp(input_i) - 1))] \\ \alpha = 1.6732632423543772848170429916717 \\ scale = 1.0507009873554804934193349852946$$

[object Object]

• aclnnSelu and aclnnInplaceSelu implement the same function in different ways. Select a proper operator based on your requirements.
  • aclnnSelu: An output tensor object needs to be created to store the computation result.
  • aclnnInplaceSelu: 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, aclnnSeluGetWorkspaceSize or aclnnInplaceSeluGetWorkspaceSize is called to obtain input parameters and compute the required workspace size based on the computation process. Then, aclnnSelu or aclnnInplaceSelu is called to perform computation.

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas training products[object Object]: The data type can be FLOAT, FLOAT16, INT32, or INT8.

• 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 FLOAT, FLOAT16, INT32, or INT8.

• 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:
  • aclnnSelu and aclnnInplaceSelu default to a deterministic implementation.

[object Object]

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