[object Object]

[object Object][object Object]undefined
[object Object]
  • Function: Determines which elements in a tensor are infinite values, that is, inf and -inf.

  • Formulas:

    outi=(inputi==±inf)out_i=(input_i == ±inf)
  • Example:

    • If x = [9, 6, 3], the result of isinf(x) is [False, False, False].
    • If x = [[-3.14, inf], [2.7183, nan]], the result of isinf(x) is [[False, True], [False, False]]. Note that integers and Booleans are finite.
[object Object]

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

[object Object]
[object Object]
[object Object]
  • Parameter description:

    [object Object]
    • For the [object Object]Atlas training products[object Object], BFLOAT16 is not supported.
  • 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]
  • Parameter description:

    [object Object]
  • Returns

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

[object Object]
  • Deterministic computation:
    • The aclnnIsInf is implemented in deterministic mode by default.
[object Object]

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

[object Object]