[object Object]

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

• Description: Returns the mean and variance of the dimension specified by the input tensor.
• Calculation formula: If [object Object] is [object Object], the dimension is calculated. [object Object] is the shape. Take [object Object] and calculate the mean value [object Object] in this dimension. The formula for computing the variance is as follows:$$varOut = \frac{1}{max(0, N - correction)}\sum_{j=0}^{N-1}(self_{ij}-\bar{self_{i}})^2$$ If [object Object], the dimension is retained after the reduce operation, and the value of the dimension in the output shape is 1. If [object Object], the dimension is not retained. When [object Object] is [object Object] or [object Object], all dimensions are calculated.

[object Object]

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

• [object Object]
• [object Object]

[object Object]

• Parameters

  • [object Object] (aclTensor*, compute input): input [object Object] in the formula. The shape supports 0 to 8 dimensions. The data types of [object Object], [object Object], and [object Object] must meet the . are supported. The can be ND.
    • [object Object]Atlas training products[object Object], [object Object]Atlas A2 training products/Atlas A2 inference products[object Object], and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: The data type can be FLOAT16 or FLOAT.
  • [object Object] (aclIntArray*, input): [object Object] in the formula. It is [object Object] on the host, indicating the dimension involved in computation. The value range is [-self.dim(), self.dim()-1], and the data must be unique. The supported data type is INT64. When [object Object] is [object Object] or [object Object], all dimensions are calculated.
  • [object Object] (int64_t, input): input [object Object] in the formula. The data type is int64_t.
  • [object Object] (bool, input): whether to retain the dimension of the reduced axis. The data type is bool.
  • [object Object] (aclTensor*, compute output): mean output result. The data types of [object Object] and [object Object] must meet the . are supported. The can be ND.
    • [object Object]Atlas training products[object Object], [object Object]Atlas A2 training products/Atlas A2 inference products[object Object], and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: The data type can be FLOAT16 or FLOAT.
  • varOut (aclTensor*, compute output): output [object Object] in the formula. It is the variance calculation result. The data types of self and varOut must meet the . are supported. The can be ND.
    • [object Object]Atlas training products[object Object], [object Object]Atlas A2 training products/Atlas A2 inference products[object Object], and [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: The data type can be FLOAT16 or FLOAT.
  • [object Object] (uint64_t*, output): size of the workspace to be allocated on the device.
  • [object Object] (aclOpExecutor**, output): operator executor, containing the operator computation process.

• Returns:

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

[object Object]

• Parameters

  • [object Object] (void*, input): address of the workspace to be allocated on the device.
  • [object Object] (uint64_t, input): size of the workspace to be allocated on the device, which is obtained by calling [object Object].
  • [object Object] (aclOpExecutor*, input): operator executor, containing the operator computation process.
  • [object Object] (aclrtStream, input): stream for executing the task.

• Returns:

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

[object Object]

• Deterministic computing:
  • [object Object] defaults to a deterministic implementation.

[object Object]

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