[object Object]

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

• Description: Performs backpropagation of . It is used to compute the gradient input based on the gradient generated during upper-layer propagation and the forward input of LogSigmoid.

• Formula:

  $$\sigma(x) = LogSigmoid(x) = \log(\frac{1}{1+e^{-x}})$$ $$gradInput = gradOutput * \sigma^\prime(x) = gradOutput * \frac{1}{1+e^{x}}$$

  $x$ is the forward input of the LogSigmoid function, $\sigma(x)$ is the LogSigmoid function, and $\sigma^\prime(x)$ is the derivative of the LogSigmoid function.

[object Object]

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

[object Object]

• Parameters:

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

• 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:
  • aclnnLogSigmoidBackward defaults to a deterministic implementation.

[object Object]

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