aclnnBinaryCrossEntropyWithLogits
支持的产品型号
- Atlas 推理系列产品。
- Atlas 训练系列产品。
- Atlas A2训练系列产品/Atlas 800I A2推理产品。
接口原型
每个算子分为两段式接口,必须先调用“aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize”接口获取入参并根据流程计算所需workspace大小,再调用“aclnnBinaryCrossEntropyWithLogits”接口执行计算。
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, aclrtStream stream)
功能描述
算子功能: 计算输入logits与标签target之间的BCELoss损失。
计算公式:
单标签场景:
多标签场景:
aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize
参数说明:
- self(const aclTensor *, 计算输入): 连接层输出,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持),支持非连续的Tensor,数据格式支持ND。
- target(const aclTensor *, 计算输入): lable标签值,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持),shape需要与
self
一致,支持非连续的Tensor,数据格式支持ND。 - weightOptional(const aclTensor *, 计算输入): 二分交叉熵权重,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持),shape需要能够broadcast到
target
,支持非连续的Tensor,数据格式支持ND。 - posWeightOptional(const aclTensor *, 计算输入): 各类的正类权重,Device侧的aclTensor,数据类型支持FLOAT16、FLOAT、BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持),shape需要能够broadcast到
target
,支持非连续的Tensor,数据格式支持ND。 - reduction(int64_t, 计算输入): 输出结果计算方式,Host侧的整型值,数据类型支持INT64,0代表None不操作;1代表Mean求损失函数均值;2代表Sum求损失函数的和。
- out(aclTensor*, 计算输出): 输出误差,Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16(仅Atlas A2训练系列产品/Atlas 800I A2推理产品支持),且数据类型与
target
一致,如果reduction = None,shape与self
一致,其他情况shape为[1],支持非连续的Tensor,数据格式支持ND。 - workspaceSize(uint64_t *, 出参): 返回需要在Device侧申请的workspace大小。
- executor(aclOpExecutor **, 出参): 返回op执行器,包含了算子计算流程。
返回值:
aclnnStatus: 返回状态码,具体参见aclnn返回码。
第一段接口完成入参校验,出现以下场景时报错:
161001(ACLNN_ERR_PARAM_NULLPTR):1. 传入的self或out为空指针。
161002(ACLNN_ERR_PARAM_INVALID):1. self、target、weightOptional和posWeightOptional的数据类型和数据格式不在支持的范围内。
2. self和target维度不一致。
3. weightOptional、posWeightOptional不能扩展成self/target形状。
aclnnBinaryCrossEntropyWithLogits
参数说明:
- workspace(void *, 入参): 在Device侧申请的workspace内存地址。
- workspaceSize(uint64_t, 入参): 在Device侧申请的workspace大小,由第一段接口aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize获取。
- executor(aclOpExecutor *, 入参): op执行器,包含了算子计算流程。
- stream(aclrtStream, 入参): 指定执行任务的 AscendCL Stream流。
返回值:
aclnnStatus: 返回状态码,具体参见aclnn返回码。
约束与限制
无
调用示例
示例代码如下,仅供参考,具体编译和执行过程请参考编译与运行样例。
#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) {
// 固定写法,AscendCL初始化
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);
// 调用aclrtMalloc申请Device侧内存
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);
// 调用aclrtMemcpy将Host侧数据拷贝到Device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建aclTensor
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
shape.data(), shape.size(), *deviceAddr);
return 0;
}
int main() {
// 1. (固定写法)device/stream初始化,参考AscendCL对外接口列表
// 根据自己的实际device填写deviceId
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
// check根据自己的需要处理
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
// 2. 构造输入与输出,需要根据API的接口自定义构造
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};
// 创建input aclTensor
ret = CreateAclTensor(inputHostData, inputShape, &inputDeviceAddr, aclDataType::ACL_FLOAT, &input);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建target aclTensor
ret = CreateAclTensor(targetHostData, targetShape, &targetDeviceAddr, aclDataType::ACL_FLOAT, &target);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建weight aclTensor
ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_FLOAT, &weight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建posWeight aclTensor
ret = CreateAclTensor(posWeightHostData, posWeightShape, &posWeightDeviceAddr, aclDataType::ACL_FLOAT, &posWeight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建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;
// aclnnBinaryCrossEntropyWithLogits接口调用示例
// 3. 调用CANN算子库API,需要修改为具体的API名称
// 调用aclnnBinaryCrossEntropyWithLogits第一段接口
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);
// 根据第一段接口计算出的workspaceSize申请device内存
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);
}
// 调用aclnnBinaryCrossEntropyWithLogits第二段接口
ret = aclnnBinaryCrossEntropyWithLogits(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBinaryCrossEntropyWithLogits failed. ERROR: %d\n", ret); return ret);
// 4. (固定写法)同步等待任务执行结束
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. 获取输出的值,将Device侧内存上的结果拷贝至Host侧,需要根据具体API的接口定义修改
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. 释放aclTensor和aclScalar,需要根据具体API的接口定义修改
aclDestroyTensor(input);
aclDestroyTensor(target);
aclDestroyTensor(weight);
aclDestroyTensor(posWeight);
aclDestroyTensor(out);
// 7. 释放device资源,需要根据具体API的接口定义修改
aclrtFree(inputDeviceAddr);
aclrtFree(targetDeviceAddr);
aclrtFree(weightDeviceAddr);
aclrtFree(posWeightDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}