- Function: Returns the value of the error function corresponding to each element in the input tensor.
- Formula:
[object Object] and [object Object] implement the same function in different ways. Select a proper operator based on your requirements.
[object Object]: An output tensor object needs to be created to store the computation result.[object Object]: No output tensor object needs to be created, and the computation result is stored in the memory of the input tensor.
Each operator is divided into two phases (../common/twp-phase_api.md). You must call aclnnErfGetWorkspaceSize or aclnnInplaceErfGetWorkspaceSize to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call aclnnErf or aclnnInplaceErf to perform the computation.
Parameters
[object Object]- [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: self supports BFLOAT16, and out supports BFLOAT16.
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]
Parameters
[object Object]- [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: selfRef supports BFLOAT16 in addition to the existing data types.
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]
- Deterministic computation:
[object Object]and[object Object]default to a deterministic implementation.
The following example is for reference only. For details, see .