Hi3559AV100 NNIE开发（4）mobilefacenet.cfg参数配置挖坑解决与SVP_NNIE_Cnn实现分析
- 2021 年 3 月 11 日
- 筆記
- hi3559, Hi35xx项目开发, mobilefacenet.cfg, NNIE_SVP_CNN
前面随笔给出了NNIE开发的基本知识，下面几篇随笔将着重于Mobilefacenet NNIE开发，实现mobilefacenet.wk的chip版本，并在Hi3559AV100上实现mobilefacenet网络功能，外接USB摄像头通过MPP平台输出至VO HDMI显示结果。下文是Hi3559AV100 NNIE开发（4）mobilefacenet.cfg参数配置挖坑解决与SVP_NNIE_Cnn实现分析，目前项目需要对mobilefacenet网络进行.wk的开发，下面给出在.wk生成过程中遇到的坑与解决方式，并给出SVP_NNIE_Cnn整体实现的各个step分析，为后面在板载上实现mobilefacenet网络打下基础。
1、mobilefacenet.cfg参数配置挖坑解决
CNN_convert_bin_and_print_featuremap.py和Get Caffe Output这里的预处理方式都是先乘以【data_scale】，再减均值【mean_file】，而在量化生成 .mk 文件时却是先减均值再乘以scale的。
给出预处理这一个环节对输入数据data的处理方式：
1 data = inputs 2 if norm_type == '4' or norm_type == '5': 3 data = data * float(data_scale)
data是uint8类型的array，是先乘以了【data_scale】的，也就是说和NNIE 生成wk中的操作顺序是不一致的，对于mobilefacenet.cfg网络输入数据预处理方法时，当norm_type = 5时，输入数据减通道均值后再乘以 data_scale，如下所示：
所在在实际操作中，需要对均值文件进行处理，转换方式如下：
(data – 128.0) * 0.0078125 <==> data * 0.0078125 – 1
因此这里需要做的修改就是需要将【mean_file】pixel_mean_compare.txt修设置为1.0：
最终生成mobilefacenet.wk，结果如下所示，具体的测试需要下一步进行。
1 begin parameter compressing.... 2 3 end parameter compressing 4 5 begin compress index generating.... 6 7 end compress index generating 8 9 begin binary code generating.... 10 11 ......................................................................................................................... 12 ....................................................................end binary code generating 13 14 begin quant files writing.... 15 16 end quant files writing 17 18 . 19 ===============D:\Hi3559_NNIE\3559\mobileface\mobileface.cfg Successfully!=============== 20 21 End [RuyiStudio Wk NNIE Mapper] [D:\Hi3559_NNIE\3559\mobileface\mobileface.cfg] mobileface
2、SVP_NNIE_Cnn实现分析
下面给出SAMPLE_SVP_NNIE_Cnn函数的执行过程，主要分为下面八个步骤：
1 HI_CHAR *pcSrcFile = "./data/nnie_image/y/0_28x28.y"; 2 HI_CHAR *pcModelName = "./data/nnie_model/classification/inst_mnist_cycle.wk"; 3 4 5 /*Set configuration parameter */ 6 stNnieCfg.pszPic= pcSrcFile; 7 stNnieCfg.u32MaxInputNum = u32PicNum; //max input image num in each batch 8 stNnieCfg.u32MaxRoiNum = 0; 9 stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;//set NNIE core 10 s_stCnnSoftwareParam.u32TopN = 5; 11 12 13 14 /*Sys init ---step1*/ 15 SAMPLE_COMM_SVP_CheckSysInit(); 16 17 /*CNN Load model ------step2*/ 18 s32Ret = SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel); 19 20 21 /*CNN parameter initialization -------step3*/ 22 /*Cnn software parameters are set in SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit, 23 if user has changed net struct, please make sure the parameter settings in 24 SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit function are correct*/ 25 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 26 s32Ret = SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg,&s_stCnnNnieParam,&s_stCnnSoftwareParam); 27 28 29 /*record tskBuf -------step4*/ 30 s32Ret = HI_MPI_SVP_NNIE_AddTskBuf(&(s_stCnnNnieParam.astForwardCtrl[0].stTskBuf)); 31 32 33 /*Fill src data -------step5*/ 34 SAMPLE_SVP_TRACE_INFO("Cnn start!\n"); 35 stInputDataIdx.u32SegIdx = 0; 36 stInputDataIdx.u32NodeIdx = 0; 37 s32Ret = SAMPLE_SVP_NNIE_FillSrcData(&stNnieCfg,&s_stCnnNnieParam,&stInputDataIdx); 38 39 40 /*NNIE process(process the 0-th segment) -------step6*/ 41 stProcSegIdx.u32SegIdx = 0; 42 s32Ret = SAMPLE_SVP_NNIE_Forward(&s_stCnnNnieParam,&stInputDataIdx,&stProcSegIdx,HI_TRUE); 43 44 45 46 /*Software process --------step7*/ 47 /*if user has changed net struct, please make sure SAMPLE_SVP_NNIE_Cnn_GetTopN 48 function's input datas are correct*/ 49 s32Ret = SAMPLE_SVP_NNIE_Cnn_GetTopN(&s_stCnnNnieParam,&s_stCnnSoftwareParam); 50 51 52 53 /*Print result --------step8*/ 54 SAMPLE_SVP_TRACE_INFO("Cnn result:\n"); 55 s32Ret = SAMPLE_SVP_NNIE_Cnn_PrintResult(&(s_stCnnSoftwareParam.stGetTopN), 56 s_stCnnSoftwareParam.u32TopN);
（1）step1为SAMPLE_COMM_SVP_CheckSysInit()，完成的是MPP系统的初始化，主要实现的是Sys_Init和VB_Init，实现MPP内存池的配置，具体实现如下：
1 HI_VOID SAMPLE_COMM_SVP_CheckSysInit(HI_VOID) 2 { 3 .............. 4 SAMPLE_COMM_SVP_SysInit() 5 { 6 //省略了部分过程，列出实现关键函数 7 HI_MPI_SYS_Exit(); 8 HI_MPI_VB_Exit(); 9 10 memset(&struVbConf,0,sizeof(VB_CONFIG_S)); 11 12 struVbConf.u32MaxPoolCnt = 2; 13 struVbConf.astCommPool[1].u64BlkSize = 768*576*2; 14 struVbConf.astCommPool[1].u32BlkCnt = 1; 15 16 s32Ret = HI_MPI_VB_SetConfig((const VB_CONFIG_S *)&struVbConf); //设置MPP视频缓存池属性 17 18 19 s32Ret = HI_MPI_VB_Init(); //初始化MPP缓存池 20 21 22 s32Ret = HI_MPI_SYS_Init(); //初始化MPP系统 23 24 } 25 26 ............. 27 }
（2）step2为SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel)从用户事先加载到 buf 中的模型中解析出网络模型，其函数实现较为复杂，具体的函数参数解析和函数运行过程已经在前面随笔给出了，需要的话，可以参考随笔：
Hi3559AV100 NNIE开发（1）-RFCN(.wk)LoadModel函数参数解析 （//www.cnblogs.com/iFrank/p/14500648.html）
Hi3559AV100 NNIE开发（2）-RFCN(.wk)LoadModel及NNIE Init函数运行过程分析 （//www.cnblogs.com/iFrank/p/14503482.html）
（3）step3为SAMPLE_SVP_NNIE_Cnn_ParamInit，首先给出调用与定义，便于分析：
1 /*Set configuration parameter*/ 2 stNnieCfg.pszPic= pcSrcFile; 3 stNnieCfg.u32MaxInputNum = u32PicNum; //max input image num in each batch 4 stNnieCfg.u32MaxRoiNum = 0; 5 stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;//set NNIE core 6 7 s_stCnnSoftwareParam.u32TopN = 5; 8 9 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 10 s32Ret = SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg, 11 &s_stCnnNnieParam, 12 &s_stCnnSoftwareParam); 13 14 15 16 static HI_S32 SAMPLE_SVP_NNIE_Cnn_ParamInit(SAMPLE_SVP_NNIE_CFG_S* pstNnieCfg, 17 SAMPLE_SVP_NNIE_PARAM_S *pstCnnPara, 18 SAMPLE_SVP_NNIE_CNN_SOFTWARE_PARAM_S* pstCnnSoftWarePara) 19 { 20 ........ 21 22 /*init hardware para*/ 23 s32Ret = SAMPLE_COMM_SVP_NNIE_ParamInit(pstNnieCfg, 24 pstCnnPara); 25 26 27 /*init software para*/ 28 if(pstCnnSoftWarePara!=NULL) 29 { 30 s32Ret = SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit(pstNnieCfg, 31 pstCnnPara, 32 pstCnnSoftWarePara); 33 "Error(%#x),SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit failed!\n",s32Ret); 34 } 35 36 ........ 37 }
其中SAMPLE_COMM_SVP_NNIE_ParamInit函数及参数分析可见之前随笔:
Hi3559AV100 NNIE开发（2）-RFCN(.wk)LoadModel及NNIE Init函数运行过程分析 （//www.cnblogs.com/iFrank/p/14503482.html），之前的随笔介绍的很详细，这里就不在赘述了。
对SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit函数，首先给出定义：
1 static HI_S32 SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit( 2 SAMPLE_SVP_NNIE_CFG_S* pstNnieCfg, 3 SAMPLE_SVP_NNIE_PARAM_S *pstCnnPara,
SAMPLE_SVP_NNIE_CNN_SOFTWARE_PARAM_S* pstCnnSoftWarePara) 4 { 5 HI_U32 u32GetTopNMemSize = 0; 6 HI_U32 u32GetTopNAssistBufSize = 0; 7 HI_U32 u32GetTopNPerFrameSize = 0; 8 HI_U32 u32TotalSize = 0; 9 HI_U32 u32ClassNum = pstCnnPara->pstModel->astSeg[0].astDstNode[0].unShape.stWhc.u32Width; 10 HI_U64 u64PhyAddr = 0; 11 HI_U8* pu8VirAddr = NULL; 12 HI_S32 s32Ret = HI_SUCCESS; 13 14 /*get mem size*/ 15 u32GetTopNPerFrameSize = pstCnnSoftWarePara->u32TopN*sizeof(SAMPLE_SVP_NNIE_CNN_GETTOPN_UNIT_S); 16 u32GetTopNMemSize = SAMPLE_SVP_NNIE_ALIGN16(u32GetTopNPerFrameSize)*pstNnieCfg->u32MaxInputNum; 17 u32GetTopNAssistBufSize = u32ClassNum*sizeof(SAMPLE_SVP_NNIE_CNN_GETTOPN_UNIT_S); 18 u32TotalSize = u32GetTopNMemSize+u32GetTopNAssistBufSize; 19 20 /*malloc mem*/ 21 s32Ret = SAMPLE_COMM_SVP_MallocMem("SAMPLE_CNN_INIT",NULL,(HI_U64*)&u64PhyAddr, 22 (void**)&pu8VirAddr,u32TotalSize); 23 SAMPLE_SVP_CHECK_EXPR_RET(HI_SUCCESS != s32Ret,s32Ret,SAMPLE_SVP_ERR_LEVEL_ERROR, 24 "Error,Malloc memory failed!\n"); 25 memset(pu8VirAddr, 0, u32TotalSize); 26 27 /*init GetTopn */ 28 pstCnnSoftWarePara->stGetTopN.u32Num= pstNnieCfg->u32MaxInputNum; 29 pstCnnSoftWarePara->stGetTopN.unShape.stWhc.u32Chn = 1; 30 pstCnnSoftWarePara->stGetTopN.unShape.stWhc.u32Height = 1; 31 pstCnnSoftWarePara->stGetTopN.unShape.stWhc.u32Width = u32GetTopNPerFrameSize/sizeof(HI_U32); 32 pstCnnSoftWarePara->stGetTopN.u32Stride = SAMPLE_SVP_NNIE_ALIGN16(u32GetTopNPerFrameSize); 33 pstCnnSoftWarePara->stGetTopN.u64PhyAddr = u64PhyAddr; 34 pstCnnSoftWarePara->stGetTopN.u64VirAddr = (HI_U64)pu8VirAddr; 35 36 /*init AssistBuf */ 37 pstCnnSoftWarePara->stAssistBuf.u32Size = u32GetTopNAssistBufSize; 38 pstCnnSoftWarePara->stAssistBuf.u64PhyAddr = u64PhyAddr+u32GetTopNMemSize; 39 pstCnnSoftWarePara->stAssistBuf.u64VirAddr = (HI_U64)pu8VirAddr+u32GetTopNMemSize; 40 41 return s32Ret; 42 }
函数体内最主要功能是实现s_stCnnSoftwareParam参数的赋值，包含大量赋值语句，其中s_stCnnSoftwareParam结构体各个元素赋值的意义等需要的时候再进行研讨，此外函数还实现在用户态分配 MMZ 内存。通过对两个函数的分析，step3 SAMPLE_SVP_NNIE_Cnn_ParamInit()完成。
（4）step4为HI_MPI_SVP_NNIE_AddTskBuf，为了记录 TskBuf 地址信息，其作用和注意事项：
①记录 TskBuf 地址信息，用于减少内核态内存映射次数，提升效率；
②TskBuf 地址信息的记录是通过链表进行管理，链表长度默认值为 32，链表长度可通过模块参数 nnie_max_tskbuf_num 进行配；
③若没调用 HI_MPI_SVP_NNIE_AddTskBuf 预先把 TskBuf 地址信息记录到系统，那么之后调用 Forward/ForwardWithBbox 每次都会 Map/Unmap 操作 TskBuf 内核态虚拟地址，效率会比较低。
给出函数调用和定义:
1 /*SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel);*/ 2 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 3 4 s32Ret = HI_MPI_SVP_NNIE_AddTskBuf(&(s_stCnnNnieParam.astForwardCtrl[0].stTskBuf)); 5 6 7 //定义 8 HI_S32 HI_MPI_SVP_NNIE_AddTskBuf(const SVP_MEM_INFO_S* pstTskBuf);
（5）step5为SAMPLE_SVP_NNIE_FillSrcData，实现src数据的填充，此函数十分关键，对所给图像数据：./data/nnie_image/y/0_28x28.y进行处理，为了更好的分析数据处理函数，首先给出函数调用信息：
1 stNnieCfg.pszPic= pcSrcFile; 2 stNnieCfg.u32MaxInputNum = u32PicNum; //max input image num in each batch 3 stNnieCfg.u32MaxRoiNum = 0; 4 stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;//set NNIE core 5 6 /*SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel);*/ 7 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 8 9 stInputDataIdx.u32SegIdx = 0; 10 stInputDataIdx.u32NodeIdx = 0; 11 s32Ret = SAMPLE_SVP_NNIE_FillSrcData(&stNnieCfg,
&s_stCnnNnieParam,
&stInputDataIdx);
为了更加清楚函数功能，先给出函数定义，方便后面分析（忽略一些次要信息）：
1 static HI_S32 SAMPLE_SVP_NNIE_FillSrcData(SAMPLE_SVP_NNIE_CFG_S* pstNnieCfg, 2 SAMPLE_SVP_NNIE_PARAM_S *pstNnieParam, 3 SAMPLE_SVP_NNIE_INPUT_DATA_INDEX_S* pstInputDataIdx)
总的来说，函数实现以下功能：
①open file fopen(pstNnieCfg->pszPic,”rb”);
1 //定义文件名 2 HI_CHAR *pcSrcFile = "./data/nnie_image/y/0_28x28.y"; 3 4 stNnieCfg.pszPic= pcSrcFile; 5 6 //函数定义 7 HI_S32 SAMPLE_SVP_NNIE_FillSrcData(SAMPLE_SVP_NNIE_CFG_S* pstNnieCfg, 8 SAMPLE_SVP_NNIE_PARAM_S *pstNnieParam, 9 SAMPLE_SVP_NNIE_INPUT_DATA_INDEX_S* pstInputDataIdx) 10 //函数调用 11 SAMPLE_SVP_NNIE_FillSrcData(&stNnieCfg, 12 &s_stCnnNnieParam, 13 &stInputDataIdx); 14 15 fp = fopen(pstNnieCfg->pszPic,"rb");
②为后面fread读取数据量确定u32VarSize大小：
1 /*get data size s32Ret = fread(pu8PicAddr,u32Dim*u32VarSize,1,fp);*/ 2 if(SVP_BLOB_TYPE_U8 <= pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType && 3 SVP_BLOB_TYPE_YVU422SP >= pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType) 4 { 5 u32VarSize = sizeof(HI_U8); 6 } 7 else 8 { 9 u32VarSize = sizeof(HI_U32); 10 }
③随即通过pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType参数（参数找定义，应该是与输入模型.wk的模型参数有关，后面可以直接通过printf进行打印输出，看结果是啥）进行if-lese分支选择，之后通过fread对fp文件指针读取数据，确定数据内存地址，并刷新 cache 里的内容到内存并且使 cache 里的内容无效，最后fclose(fp)。
先给出enType参数类型：
代码实现：
1 /*fill src data*/ 2 if(SVP_BLOB_TYPE_SEQ_S32 == pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType) 3 { 4 u32Dim = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].unShape.stSeq.u32Dim; 5 u32Stride = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Stride; 6 pu32StepAddr = (HI_U32*)(pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].unShape.stSeq.u64VirAddrStep); 7 pu8PicAddr = (HI_U8*)(pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64VirAddr); 8 for(n = 0; n < pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Num; n++) 9 { 10 for(i = 0;i < *(pu32StepAddr+n); i++) 11 { 12 s32Ret = fread(pu8PicAddr,u32Dim*u32VarSize,1,fp); 13 SAMPLE_SVP_CHECK_EXPR_GOTO(1 != s32Ret,FAIL,SAMPLE_SVP_ERR_LEVEL_ERROR,"Error,Read image file failed!\n"); 14 pu8PicAddr += u32Stride; 15 } 16 u32TotalStepNum += *(pu32StepAddr+n); 17 } 18 SAMPLE_COMM_SVP_FlushCache(pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64PhyAddr, 19 (HI_VOID *) pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64VirAddr, 20 u32TotalStepNum*u32Stride); 21 } 22 else 23 { 24 u32Height = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].unShape.stWhc.u32Height; 25 u32Width = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].unShape.stWhc.u32Width; 26 u32Chn = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].unShape.stWhc.u32Chn; 27 u32Stride = pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Stride; 28 pu8PicAddr = (HI_U8*)(pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64VirAddr); 29 if(SVP_BLOB_TYPE_YVU420SP== pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType) 30 { 31 for(n = 0; n < pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Num; n++) 32 { 33 for(i = 0; i < u32Chn*u32Height/2; i++) 34 { 35 s32Ret = fread(pu8PicAddr,u32Width*u32VarSize,1,fp); 36 SAMPLE_SVP_CHECK_EXPR_GOTO(1 != s32Ret,FAIL,SAMPLE_SVP_ERR_LEVEL_ERROR,"Error,Read image file failed!\n"); 37 pu8PicAddr += u32Stride; 38 } 39 } 40 } 41 else if(SVP_BLOB_TYPE_YVU422SP== pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType) 42 { 43 for(n = 0; n < pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Num; n++) 44 { 45 for(i = 0; i < u32Height*2; i++) 46 { 47 s32Ret = fread(pu8PicAddr,u32Width*u32VarSize,1,fp); 48 SAMPLE_SVP_CHECK_EXPR_GOTO(1 != s32Ret,FAIL,SAMPLE_SVP_ERR_LEVEL_ERROR,"Error,Read image file failed!\n"); 49 pu8PicAddr += u32Stride; 50 } 51 } 52 } 53 else 54 { 55 for(n = 0; n < pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Num; n++) 56 { 57 for(i = 0;i < u32Chn; i++) 58 { 59 for(j = 0; j < u32Height; j++) 60 { 61 s32Ret = fread(pu8PicAddr,u32Width*u32VarSize,1,fp); 62 SAMPLE_SVP_CHECK_EXPR_GOTO(1 != s32Ret,FAIL,SAMPLE_SVP_ERR_LEVEL_ERROR,"Error,Read image file failed!\n"); 63 pu8PicAddr += u32Stride; 64 } 65 } 66 } 67 } 68 SAMPLE_COMM_SVP_FlushCache(pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64PhyAddr, 69 (HI_VOID *) pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u64VirAddr, 70 pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].u32Num*u32Chn*u32Height*u32Stride); 71 } 72 73 fclose(fp);
（6）step6为SAMPLE_SVP_NNIE_Forward实现NNIE process，便于分析先给出函数的调用及参数的定义：
1 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 2 /* SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel); */ 3 4 stInputDataIdx.u32SegIdx = 0; 5 stInputDataIdx.u32NodeIdx = 0; 6 7 stProcSegIdx.u32SegIdx = 0; 8 9 s32Ret = SAMPLE_SVP_NNIE_Forward(&s_stCnnNnieParam, 10 &stInputDataIdx, 11 &stProcSegIdx, 12 HI_TRUE); 13 14 static HI_S32 SAMPLE_SVP_NNIE_Forward( 15 SAMPLE_SVP_NNIE_PARAM_S *pstNnieParam, 16 SAMPLE_SVP_NNIE_INPUT_DATA_INDEX_S* pstInputDataIdx, 17 SAMPLE_SVP_NNIE_PROCESS_SEG_INDEX_S* pstProcSegIdx, 18 HI_BOOL bInstant)
SAMPLE_SVP_NNIE_Forward中①SAMPLE_COMM_SVP_FlushCache函数主要实现将内存数据刷新到内存中；②HI_MPI_SVP_NNIE_Forward函数同时对输入样本(s)进行CNN预测，对对应样本(s)进行输出响应；③HI_MPI_SVP_NNIE_Query函数用于查询nnie上运行函数的状态，在阻塞模式下，系统等待，直到被查询的函数被调用；在非阻塞模式下，查询当前状态，不做任何操作。
（7）step7为SAMPLE_SVP_NNIE_Cnn_GetTopN实现软件过程，给出函数调用与参数细节：
1 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 2 /* SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel); */ 3 4 s_stCnnSoftwareParam.u32TopN = 5; 5 SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg, //通过此函数对s_stCnnSoftwareParam进行了赋值操作 6 &s_stCnnNnieParam, 7 &s_stCnnSoftwareParam); 8 9 s32Ret = SAMPLE_SVP_NNIE_Cnn_GetTopN(&s_stCnnNnieParam, 10 &s_stCnnSoftwareParam); 11 12 HI_S32 SAMPLE_SVP_NNIE_Cnn_GetTopN(SAMPLE_SVP_NNIE_PARAM_S*pstNnieParam, 13 SAMPLE_SVP_NNIE_CNN_SOFTWARE_PARAM_S* pstSoftwareParam)
此函数目前基本不修改，函数内部具体实现目前暂不说明，只需注意一点如果改变了网络结构，请确保SAMPLE_SVP_NNIE_Cnn_GetTopN
函数的输入数据正确。
（8）step8为SAMPLE_SVP_NNIE_Cnn_PrintResult打印blob参数值，给出函数调用与参数细节：
1 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel; 2 /* SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel); */ 3 4 s_stCnnSoftwareParam.u32TopN = 5; 5 SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg, //通过此函数对s_stCnnSoftwareParam进行了赋值操作 6 &s_stCnnNnieParam, 7 &s_stCnnSoftwareParam); 8 9 s32Ret = SAMPLE_SVP_NNIE_Cnn_PrintResult(&(s_stCnnSoftwareParam.stGetTopN), 10 s_stCnnSoftwareParam.u32TopN); 11 12 HI_S32 SAMPLE_SVP_NNIE_Cnn_PrintResult(SVP_BLOB_S *pstGetTopN, 13 HI_U32 u32TopN)
有什么问题，大家可以提出来，一起讨论，后面将给出mobilefacenet的NNIE实现。
