[object Object]

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

• Description: Computes the Softmax value of the input tensor.

• Formula:

  $$Softmax\left ( {{x}_{i}} \right )= {\frac {{e}^{{x}_{i}}} {\sum ^{n-1}_{j=0} {{e}^{{x}_{j}}}}}$$

  During actual calculation, the maximum value of the input is subtracted to prevent floating-point overflow and ensure the stability of numerical calculation.

[object Object]

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

[object Object]

• Parameters:

  [object Object]
  • [object Object]Atlas inference products[object Object], [object Object]Atlas training products[object Object], and [object Object]Atlas 200I/500 A2 inference products[object Object]: The data type can be FLOAT16, FLOAT32, or DOUBLE.

• 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:
  • aclnnSoftmax defaults to a deterministic implementation.

[object Object]

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