aclnnAffineGrid

Applicable Products

Function

Given a set of 3D affine parameter matrices (theta) and the size of the output image (size), generates a 2D or 3D grid that represents the coordinates of the points in the original image after affine transformation.

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnAffineGridGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, and then call the "aclnnAffineGrid" API to perform the computation.

aclnnStatus aclnnAffineGridGetWorkspaceSize(
  const aclTensor*   theta,
  const aclIntArray* size,
  bool               alignCorners,
  aclTensor*         out,
  uint64_t*          workspaceSize,
  aclOpExecutor**    executor)

aclnnStatus aclnnAffineGrid(
  void*          workspace,
  uint64_t       workspaceSize,
  aclOpExecutor* executor,
  aclrtStream    stream)

aclnnAffineGridGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data type.	Data format.	Dimension (shape).	Non-contiguous tensor.
  theta (aclTensor*)	Input	Affine transformation parameters that control rotation, scaling, and translation during the affine transformation.	-	-	ND	(N, 2, 3) or (N, 3, 4)	√
  size(aclIntArray*)	Input	Specifies the size of the output image.	-	-	-	(N, C, H, W) or 5(N, C, D, H, W)	-
  alignCorners (bool)	Input	Indicates whether corner pixels are aligned.	If True, the corner pixels of the output grid align with the corner pixels of the input grid. If False, the center pixels of the output grid align with the center pixels of the input grid. Defaults to False.	-	-	-	-
  out(aclTensor*)	Output	Represents the coordinates of the affine-transformed image on the original image.		Same as theta.	ND		Yes
  workspaceSize (uint64_t*)	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor (aclOpExecutor**)	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return value

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

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

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	Passes a null pointer for theta, size, or out.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of theta is not within the supported range.
  		The data types of out and theta are inconsistent.
  		The dimension of theta is not 3.
  		The size of the size array is not 4 or 5.
  		When size is 4, the shape of theta is not (N, 2, 3); when size is 5, the shape of theta is not (N, 3, 4).
  		When size is 4, the shape of out is not (N, H, W, 2); when size is 5, the shape of out is not (N, D, H, W, 3).

aclnnAffineGrid

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	The workspace memory address applied for on the Device side.
  workspaceSize	Input	The workspace size applied for on the Device side, obtained from the first-phase API aclnnAffineGridGetWorkspaceSize.
  executor	Input	The op executor, which contains the operator computation flow.
  stream	Input	Specifies the stream that executes the task.

• Return value

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

Constraints

• Deterministic computation:

  • aclnnAffineGrid defaults to a deterministic implementation.

The values of N, H, and W in size must fall within the range (0, 100000].

Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_affine_grid.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 shape_size = 1;
  for (auto i : shape) {
    shape_size *= i;
  }
  return shape_size;
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate: AscendCL 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);
  // Allocate device memory by calling aclrtMalloc.
  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);

  // Copy host data to device memory by calling aclrtMemcpy.
  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);

  // Calculate the strides of a 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];
  }

  // Create an aclTensor by calling aclCreateTensor.
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                            shape.data(), shape.size(), *deviceAddr);
  return 0;
}

int main() {
  // 1. (Boilerplate) Initialize the device/stream. See the AscendCL API list.
  // Fill in the deviceId based on your actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check based on your needs.
  CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the inputs and outputs. Customize the construction based on the API interface.
  std::vector<int64_t> thetaShape = {1, 2, 3};
  std::vector<int64_t> outShape = {1, 2, 3, 2};
  void* thetaDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* theta = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> thetaHostData = {0, 1, 2, 3, 4, 5};
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
  std::vector<int64_t> sizeData = {1, 1, 2, 3};
  bool alignCorners = false;

  // Create the theta aclTensor.
  ret = CreateAclTensor(thetaHostData, thetaShape, &thetaDeviceAddr, aclDataType::ACL_FLOAT, &theta);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the size aclIntArray.
  aclIntArray *size = aclCreateIntArray(sizeData.data(), sizeData.size());
  // Create 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.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  // Call the first-phase API of aclnnAffineGrid.
  ret = aclnnAffineGridGetWorkspaceSize(theta, size, alignCorners, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAffineGridGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // Apply for 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 aclnnAffineGrid.
  ret = aclnnAffineGrid(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnAffineGrid failed. ERROR: %d\n", ret); return ret);
  // 4. (Boilerplate) Synchronously wait for task execution to finish.
  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 device memory to host memory. Modify based on the specific API definition.
  auto length = GetShapeSize(outShape);
  std::vector<float> resultData(length, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr,
                    length * 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 < length; i++) {
    LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
  }

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

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