[object Object]

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

Description: Performs 3D reflection padding.

[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*, computation input). are supported. The supports ND, and the shape supports four or five dimensions. Padding is performed on the last three dimensions.

    • [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]: BFLOAT16, FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL, COMPLEX64, or COMPLEX128.
    • [object Object]Atlas training products[object Object]: FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, or BOOL.

  • [object Object] (aclIntArray*, computation input): The data type is INT64, the length is 6, and the values indicate the padding values on the left, right, top, bottom, front, and back, respectively. The first two values of [object Object] must be less than the value of the last dimension of [object Object], the middle two values must be less than the value of the second-to-last dimension of [object Object], and the last two values must be less than the value of the third-to-last dimension of [object Object].

  • [object Object] (aclTensor*, computation output): The data type, , and shape are the same as those of [object Object]. The value of the third-to-last dimension of [object Object] is equal to the value of the third-to-last dimension of [object Object] plus the last two values of [object Object]. The value of the second-to-last dimension of [object Object] is equal to the value of the second-to-last dimension of [object Object] plus the middle two values of [object Object]. The value of the last dimension of [object Object] is equal to the value of the last dimension of [object Object] plus the first two values of [object Object]. are supported.

    • [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]: BFLOAT16, FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, BOOL, COMPLEX64, or COMPLEX128.
    • [object Object]Atlas training products[object Object]: FLOAT16, FLOAT32, DOUBLE, INT8, INT16, INT32, INT64, UINT8, or BOOL.

  • [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 [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 computation:

  • [object Object] defaults to a deterministic implementation.

• If the computation load is too large, the operator execution may time out (AI Core error, errorStr: timeout or trap error). This occurs when the last two axes combined are less than 16 and the first axes combined are too large.

• The 5D [object Object] is an empty tensor and the value of a non-batch size dimension is 0. The 4D [object Object] cannot be an empty tensor.

[object Object]

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