[object Object]

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

• Description: Limits all input elements within the range of [clipValueMin,clipValueMax]. If an element is greater than clipValueMax, the element is limited to clipValueMax. If an element is less than clipValueMin, the element is limited to clipValueMin. Otherwise, the element itself is used.
• Formula:$$HardTanh(x) = \left\{\begin{matrix}\begin{array}{l} clipValueMax, \ if\ x>clipValueMax \\ clipValueMin, \ if\ x<clipValueMin \\ x, \ otherwise \\\end{array}\end{matrix}\right.\begin{array}{l}\end{array}$$

[object Object]

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

  • [object Object]
  • [object Object]
  • [object Object]
  • [object Object]

[object Object]

• Parameters:

  • [object Object] (aclTensor*, computation input): [object Object] in the formula, aclTensor on the device. The data type and shape must be the same as those of [object Object]. are supported. The can be ND.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (aclScalar*, computation input): aclScalar on the host, lower bound. The data type must be convertible to that of [object Object]. If [object Object] and [object Object] coexist, they must be the same.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (aclScalar*, computation input): aclScalar on the host, upper bound. The data type must be convertible to that of [object Object]. If [object Object] and [object Object] coexist, they must be the same.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (aclTensor*, computation output): aclTensor on the device. The data type and shape must be the same as those of [object Object]. are supported. The supports ND.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [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 the first-phase API [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]

• Parameters:

  • [object Object] (aclTensor*, computation input): aclTensor on the device. are supported. The can be ND.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (aclScalar*, computation input): aclScalar on the host, lower bound. The data type must be convertible to the data type of [object Object]. If [object Object] and [object Object] coexist, they must be the same.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (aclScalar*, computation input): aclScalar on the host, upper bound. The data type must be convertible to that of [object Object]. If [object Object] and [object Object] coexist, they must be the same.
    • [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]: FLOAT16, BFLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
    • [object Object]Atlas inference products[object Object] and [object Object]Atlas training products[object Object]: FLOAT16, FLOAT, FLOAT64, INT8, UINT8, INT16, INT32, or INT64 is supported.
  • [object Object] (uint64_t*, output): size of the workspace to be allocated on the device.
  • [object Object] (aclOpExecutor**, output): operator executor, covering 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 the first-phase API [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]

None

[object Object]

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