[object Object]

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

• This API is used to calculate the mean squared error between each element in the input x and the target y. reduction specifies the reduction to be applied to the output. The value can be none, mean, or sum. mean indicates that the output will be averaged by reducing axis 0, and sum indicates that the output will be summed by reducing axis 0.

• Formula:

  If [object Object] is [object Object]:

  $$\ell(x, y) = L = \{l_1,\dots,l_N\}^\top, \quad l_n = \left( x_n - y_n \right)^2,$$

  $x$ is self, $y$ is target, and $N$ is the batch size. If [object Object] is not [object Object]:

  $$\ell(x, y) = \begin{cases} \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\ \operatorname{sum}(L), & \text{if reduction} = \text{'sum'.} \end{cases}$$

[object Object]

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

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters:

  [object Object]

• Returns:

  [object Object]: status code. For details, see .

[object Object]

• Deterministic compute:
  • aclnnMseLossOut defaults to a deterministic implementation.

[object Object]

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