文档
下载
文档中心
aclnnAdaptiveAvgPool2d

aclnnAdaptiveAvgPool2d

📄 View Source Code

Applicable Products

ProductSupported
Ascend 950PR/Ascend 950DT✗
Atlas A3 training products/Atlas A3 inference products✓
Atlas A2 training products/Atlas A2 inference products✓
Atlas 200I/500 A2 inference products✗
Atlas inference products✓
Atlas training products✓

Function

Performs 2D adaptive average pooling on the tensor self with the specified 2D output shape information (outputSize). Unlike aclnnAvgPool2d, aclnnAdaptiveAvgPool2d automatically derives the kernel size and corresponding stride by specifying only the output size.

Function Prototype

Each operator is divided into a two-phase API. The "aclnnAdaptiveAvgPool2dGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnAdaptiveAvgPool2d" API is called to perform the computation.

aclnnStatus aclnnAdaptiveAvgPool2dGetWorkspaceSize(
  const aclTensor   *self,
  const aclIntArray *outputSize,
  aclTensor         *out,
  uint64_t          *workspaceSize,
  aclOpExecutor     **executor)
aclnnStatus aclnnAdaptiveAvgPool2d(
  void              *workspace,
  uint64_t          workspaceSize,
  aclOpExecutor     *executor,
  const aclrtStream stream)

aclnnAdaptiveAvgPool2dGetWorkspaceSize

  • Parameters:

    Parameter Input/Output Description Instruction Data Type Data Format Dimension (Shape) Non-contiguous Tensor
    self Input Represents the target tensor to be computed. - FLOAT32, FLOAT16, BFLOAT16 NCL, NCHW 3-4 √
    outputSize Input Size of the output tensor in the HW dimensions. The array length is always 2. INT64 - - -
    out Output Output tensor, which has the same data type as self. Shape is jointly determined by self and outputSize. FLOAT32, FLOAT16, BFLOAT16 NCL, NCHW 3-4 √
    workspaceSize output Returns the workspace size to be requested on the Device side. - - - - -
    executor Output Returns the op executor, which contains the operator computation flow. - - - - -
    • Atlas inference products, Atlas training products: The data type of the parameters self and out does not support BFLOAT16.

  • Return value

    aclnnStatus: return code. For details, see aclnn Return Code.

    The first-phase API performs input parameter validation and returns an error in the following scenarios:

    Return Code Error Code Description
    ACLNN_ERR_PARAM_NULLPTR 161001 The passed self, outputSize, or out is a null pointer.
    ACLNN_ERR_PARAM_INVALID 161002 The data type or data format of self is not within the supported range.
    The data type or data format of self and out is inconsistent.
    The outputSize is invalid, such as division by zero, negative values, or out-of-bounds values that violate the normal logic of the operator.
    The dimension of self is not 3 or 4.
    The dimension of outputSize is not 2.
    The dimensions of self and out are inconsistent.
    The shapes of self and out do not conform to the deduction.

aclnnAdaptiveAvgPool2d

  • Parameters:

    Parameter Input/Output Description
    workspace Input Address of the workspace memory applied for on the Device side.
    workspaceSize Input Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnAdaptiveAvgPool2dGetWorkspaceSize.
    executor Input Operator executor, which contains the operator computation flow.
    stream Input Specifies the stream for task execution.

  • Return value

    aclnnStatus: return code. For details, see aclnn Return Code.

Constraints

  • Deterministic computation:

    • aclnnAdaptiveAvgPool2d defaults to a deterministic implementation.

  • Shape description:

    • self.shape = (N, C, Hin, Win) or (C, Hin, Win)

    • outputSize = [Hout, Wout]

    • out.shape = (N, C, Hout, Wout) or (C, Hout, Wout)

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include <cstdio>
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_adaptive_avg_pool2d.h"

#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)

#define LOG_PRINT(message, ...)     \
  do {                              \
    printf(message, ##__VA_ARGS__); \
  } while (0)

int64_t GetShapeSize(const std::vector<int64_t>& shape) {
  int64_t shapeSize = 1;
  for (auto i : shape) {
    shapeSize *= i;
  }
  return shapeSize;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate for resource initialization.
  auto ret = aclInit(nullptr);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
  ret = aclrtSetDevice(deviceId);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
  ret = aclrtCreateStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
  return 0;
}

template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
  auto size = GetShapeSize(shape) * sizeof(T);
  // Call aclrtMalloc to allocate device-side memory.
  auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
  // Call aclrtMemcpy to copy host-side data to device-side memory.
  ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);

  // Compute the strides of the contiguous tensor.
  std::vector<int64_t> strides(shape.size(), 1);
  for (int64_t i = shape.size() - 2; i >= 0; i--) {
    strides[i] = shape[i + 1] * strides[i + 1];
  }

  // Call the aclCreateTensor API to create an aclTensor.
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_NCHW,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int main() {
  // 1. (Boilerplate) Initialize the device/stream. Refer to the ACL API manual.
  // Enter the deviceId based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the input and output, which requires custom construction based on the API interface.
  std::vector<int64_t> inputShape = {2, 2, 3, 3};
  std::vector<int64_t> outShape = {2, 2, 2, 2};
  std::vector<int64_t> outSize = {2, 2};
  void* inputDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input = nullptr;
  aclTensor* out = nullptr;
  aclIntArray* outputSize = aclCreateIntArray(outSize.data(), 2);
  std::vector<float> inputHostData = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36};
  std::vector<float> outHostData(16, 0);
  // Create the input aclTensor.
  ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the out aclTensor.
  ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 3. Call the CANN operator library API. Replace with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnAdaptiveAvgPool2d.
  ret = aclnnAdaptiveAvgPool2dGetWorkspaceSize(input, outputSize, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool2dGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Allocate device memory based on the workspaceSize computed by the first-phase API.
  void* workspaceAddr = nullptr;
  if (workspaceSize > 0) {
    ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
  }
  // Call the second-phase API of aclnnAdaptiveAvgPool2d.
  ret = aclnnAdaptiveAvgPool2d(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAdaptiveAvgPool2d failed. ERROR: %d\n", ret); return ret);

  // 4. (boilerplate) Synchronously wait for task execution to complete.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. Obtain the output value and copy the result from the device memory to the host memory. Modify based on the specific API definition.
  auto size = GetShapeSize(outShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    size * sizeof(resultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }

  // 6. Release aclTensor. Modify based on the specific API definition.
  aclDestroyTensor(input);
  aclDestroyTensor(out);

  // 7. Release device resources. Modify based on the specific API definition.
  aclrtFree(inputDeviceAddr);
  aclrtFree(outDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}
我们使用cookie来确保您的高速浏览体验。继续浏览本站，即表示您同意我们使用cookie。查看详情