aclnnBinaryCrossEntropyWithLogits

📄 View Source Code

Applicable Products

Function

• Description: Computes the BCELoss between the input logits and the target labels.

• Formula:

  • Single-label scenario:

    $$\ell(self, target) = L = \{l_{1},..., l_{n}\}^{T}$$ $$\ell_{n} = -weight_{n}[target_{n} \cdot log(\sigma(self_{n})) + (1 - target_{n}) \cdot log(1 - \sigma(self_{n}))]$$ $$\ell(self, target) = \begin{cases} L, & if\ reduction = none\\ mean(L), & if\ reduction = mean\\ sum(L), & if\ reduction = sum\\ \end{cases}$$

  • Multi-label scenario:

    $$\ell_c(self, target) = L_c = \{l_{1,c},..., l_{n,c}\}^{T}$$ $$\ell_{n,c} = -weight_{n,c}[pos\_weight_{n,c} \cdot target_{n,c} \cdot log(\sigma(self_{n,c})) + (1 - target_{n,c}) \cdot log(1 - \sigma(self_{n,c}))]$$

Function Prototype

Each operator is divided into a two-phase API. First call the "aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize" API to obtain the input parameters and calculate the required workspace size based on the process, then call the "aclnnBinaryCrossEntropyWithLogits" API to perform the computation.

aclnnStatus aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize(
    const aclTensor *self,
    const aclTensor *target,
    const aclTensor *weightOptional,
    const aclTensor *posWeightOptional,
    int64_t          reduction,
    aclTensor       *out,
    uint64_t        *workspaceSize,
    aclOpExecutor  **executor)

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

aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-Contiguous Tensor
  self (aclTensor*)	Input	Output of the connected layer.	-	FLOAT16, FLOAT, BFLOAT16	ND	1-8	√
  target (aclTensor*)	Input	Label value.	-	Same as self.	ND	Same as self.	√
  weightOptional (aclTensor*)	Input	Weight for the binary cross-entropy.	The shape must be able to broadcast to target.	Keep it consistent with self.	ND	1-8	√
  posWeightOptional (aclTensor*)	Input	Weight of the positive class for each category.	The shape must be able to broadcast to target.	Consistent with self.	ND	1-8	√
  reduction (int64_t)	Input	Method for computing the output result.	Supports 0 (none) | 1 (mean) | 2 (sum). 0: no operation is performed. 1: computes the mean of the result. 2: computes the sum of the result.	INT64	-	-	-
  Output (aclTensor*)	Output	Outputs the error.	If reduction = 0, the shape is the same as self; otherwise, the shape is [1].	Same as target.	ND	Consistent with self.	√
  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.	-	-	-	-	-

  • Atlas inference products, Atlas training products: The BFLOAT16 data type is not supported.

• 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 Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input self or out is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data types and data formats of self, target, weightOptional, and posWeightOptional are not within the supported range.
  		The dimensions of self and target are inconsistent.
  		weightOptional and posWeightOptional cannot be broadcast to the shape of self/target.

aclnnBinaryCrossEntropyWithLogits

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Workspace memory address applied for on the Device side.
  workspaceSize	Input	Workspace size applied for on the Device side, obtained through the first-phase API aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation process.
  stream	Input	Specifies the stream that executes the task.

• Return value

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

Constraints

• deterministic computation:

  • aclnnBinaryCrossEntropyWithLogits defaults to a deterministic implementation.

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_binary_cross_entropy_with_logits.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: 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 apply for device 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);

  // Copy data from the host to the 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 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];
  }

  // 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 ACL API manual.
  // Set deviceId based on the actual device.
  int32_t deviceId = 0;
  aclrtStream stream;
  auto ret = Init(deviceId, &stream);
  // Handle the check based on your own needs.
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

  // 2. Construct the input and output. Customize the construction based on the API.
  std::vector<int64_t> inputShape = {4, 2};
  std::vector<int64_t> targetShape = {4, 2};
  std::vector<int64_t> weightShape = {4, 2};
  std::vector<int64_t> posWeightShape = {4, 2};
  std::vector<int64_t> outShape = {4, 2};

  void* inputDeviceAddr = nullptr;
  void* targetDeviceAddr = nullptr;
  void* weightDeviceAddr = nullptr;
  void* posWeightDeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* input = nullptr;
  aclTensor* target = nullptr;
  aclTensor* weight = nullptr;
  aclTensor* posWeight = nullptr;
  aclTensor* out = nullptr;

  std::vector<float> inputHostData = {0.1, 0.1, 0.2, 0.2, 0.3, 0.3, 0.4, 0.4};
  std::vector<float> targetHostData = {0.2, 0.2, 0.1, 0.1, 0.2, 0.2, 0.1, 0.1};
  std::vector<float> weightHostData = {0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5};
  std::vector<float> posWeightHostData = {0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5};
  std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0};

  // Create the input aclTensor.
  ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the target aclTensor.
  ret = CreateAclTensor(targetHostData, targetShape, &targetDeviceAddr, aclDataType::ACL_FLOAT, &target);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the weight aclTensor.
  ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_FLOAT, &weight);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // Create the posWeight aclTensor.
  ret = CreateAclTensor(posWeightHostData, posWeightShape, &posWeightDeviceAddr, aclDataType::ACL_FLOAT, &posWeight);
  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);

  int64_t reduction = 0;

  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // Example of calling the aclnnBinaryCrossEntropyWithLogits API
  // 3. Call the CANN operator library API. Replace with the specific API name.
  // Call the first-phase API of aclnnBinaryCrossEntropyWithLogits.
  ret = aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize(input, target, weight, posWeight, reduction, out, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize 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 aclnnBinaryCrossEntropyWithLogits.
  ret = aclnnBinaryCrossEntropyWithLogits(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBinaryCrossEntropyWithLogits 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 and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(input);
  aclDestroyTensor(target);
  aclDestroyTensor(weight);
  aclDestroyTensor(posWeight);
  aclDestroyTensor(out);

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