CANN/ops-nn二元交叉熵损失算子

aclnnBinaryCrossEntropyWithLogits【免费下载链接】ops-nn本项目是CANN提供的神经网络类计算算子库实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-nn 查看源码产品支持情况产品是否支持Ascend 950PR/Ascend 950DT√Atlas A3 训练系列产品/Atlas A3 推理系列产品√Atlas A2 训练系列产品/Atlas A2 推理系列产品√Atlas 200I/500 A2 推理产品×Atlas 推理系列产品√Atlas 训练系列产品√功能说明接口功能计算输入logits与标签target之间的BCELoss损失。计算公式单标签场景$$ \ell(self, target) L {l_{1},..., l_{n}}^{T} $$$$ \ell_{n} -weight_{n}[target_{n} \cdot log(\sigma(self_{n})) (1 - target_{n}) \cdot log(1 - \sigma(self_{n}))] $$$$ \ell(self, target) \begin{cases} L, if\ reduction none\ mean(L), if\ reduction mean\ sum(L), if\ reduction sum\ \end{cases} $$多标签场景$$ \ell_c(self, target) L_c {l_{1,c},..., l_{n,c}}^{T} $$$$ \ell_{n,c} -weight_{n,c}[pos_weight_{n,c} \cdot target_{n,c} \cdot log(\sigma(self_{n,c})) (1 - target_{n,c}) \cdot log(1 - \sigma(self_{n,c}))] $$函数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, const aclrtStream stream)aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize参数说明参数名输入/输出描述使用说明数据类型数据格式维度(shape)非连续TensorselfaclTensor*输入连接层输出。-FLOAT16、FLOAT、BFLOAT16ND1-8√targetaclTensor*输入label标签值。-与self保持一致ND与self保持一致√weightOptionalaclTensor*输入二分交叉熵权重。shape需要能够broadcast到target与self保持一致ND1-8√posWeightOptionalaclTensor*输入各类的正类权重。shape需要能够broadcast到target与self保持一致ND1-8√reductionint64_t输入输出结果计算方式。支持0(none)|1(mean)|2(sum)。0表示不做任何操作1表示对结果取平均值2表示对结果求和INT64---outaclTensor*输出输出误差。如果reduction 0shape与self一致其他情况shape为[1]与target保持一致ND与self保持一致√workspaceSizeuint64_t*输出返回需要在Device侧申请的workspace大小。-----executoraclOpExecutor**输出返回op执行器包含了算子计算流程。-----Atlas 推理系列产品 、 Atlas 训练系列产品 数据类型不支持BFLOAT16。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返回值错误码描述ACLNN_ERR_PARAM_NULLPTR161001传入的self或out为空指针。ACLNN_ERR_PARAM_INVALID161002self、target、weightOptional和posWeightOptional的数据类型和数据格式不在支持的范围内。self和target维度不一致。weightOptional、posWeightOptional不能扩展成self/target形状。aclnnBinaryCrossEntropyWithLogits参数说明参数名输入/输出描述workspace输入在Device侧申请的workspace内存地址。workspaceSize输入在Device侧申请的workspace大小由第一段接口aclnnBinaryCrossEntropyWithLogitsGetWorkspaceSize获取。executor输入op执行器包含了算子计算流程。stream输入指定执行任务的Stream。返回值aclnnStatus: 返回状态码具体参见aclnn返回码。约束说明确定性计算aclnnBinaryCrossEntropyWithLogits默认确定性实现。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::vectorint64_t shape) { int64_t shapeSize 1; for (auto i : shape) { shapeSize * i; } return shapeSize; } int Init(int32_t deviceId, aclrtStream* stream) { // 固定写法资源初始化 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::vectorT hostData, const std::vectorint64_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::vectorint64_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acl API手册 // 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::vectorint64_t inputShape {4, 2}; std::vectorint64_t targetShape {4, 2}; std::vectorint64_t weightShape {4, 2}; std::vectorint64_t posWeightShape {4, 2}; std::vectorint64_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::vectorfloat inputHostData {0.1, 0.1, 0.2, 0.2, 0.3, 0.3, 0.4, 0.4}; std::vectorfloat targetHostData {0.2, 0.2, 0.1, 0.1, 0.2, 0.2, 0.1, 0.1}; std::vectorfloat weightHostData {0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5}; std::vectorfloat posWeightHostData {0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5}; std::vectorfloat 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::vectorfloat 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; }【免费下载链接】ops-nn本项目是CANN提供的神经网络类计算算子库实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-nn创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考