Hi3559AV100 NNIE開發（4）mobilefacenet.cfg引數配置挖坑解決與SVP_NNIE_Cnn實現分析
阿新 • • 發佈：2021-03-12
前面隨筆給出了NNIE開發的基本知識，下面幾篇隨筆將著重於Mobilefacenet NNIE開發，實現mobilefacenet.wk的chip版本，並在Hi3559AV100上實現mobilefacenet網路功能，外接USB攝像頭通過MPP平臺輸出至VO HDMI顯示結果。下文是Hi3559AV100 NNIE開發（4）mobilefacenet.cfg引數配置挖坑解決與SVP_NNIE_Cnn實現分析，目前專案需要對mobilefacenet網路進行.wk的開發，下面給出在.wk生成過程中遇到的坑與解決方式，並給出SVP_NNIE_Cnn整體實現的各個step分析，為後面在板載上實現mobilefacenet網路打下基礎。
1、mobilefacenet.cfg引數配置挖坑解決
CNN_convert_bin_and_print_featuremap.py和Get Caffe Output這裡的預處理方式都是先乘以【data_scale】，再減均值【mean_file】，而在量化生成 .mk 檔案時卻是先減均值再乘以scale的。
給出預處理這一個環節對輸入資料data的處理方式：
1 data = inputs 2 if norm_type == '4' or norm_type == '5': 3 data = data * float(data_scale)
data是uint8型別的array，是先乘以了【data_scale】的，也就是說和NNIE 生成wk中的操作順序是不一致的，對於mobilefacenet.cfg網路輸入資料預處理方法時，當norm_type = 5時，輸入資料減通道均值後再乘以 data_scale，如下所示：
所在在實際操作中，需要對均值檔案進行處理，轉換方式如下：
(data - 128.0) * 0.0078125 <==> data * 0.0078125 - 1
因此這裡需要做的修改就是需要將【mean_file】pixel_mean_compare.txt修設定為1.0：
最終生成mobilefacenet.wk，結果如下所示，具體的測試需要下一步進行。
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實現分析
下面給出SAMPLE_SVP_NNIE_Cnn函式的執行過程，主要分為下面八個步驟：
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為SAMPLE_COMM_SVP_CheckSysInit()
完成的是MPP系統的初始化，主要實現的是Sys_Init和VB_Init，實現MPP記憶體池的配置，具體實現如下：
1 HI_VOID SAMPLE_COMM_SVP_CheckSysInit(HI_VOID)
2 {
3 ..............
4 SAMPLE_COMM_SVP_SysInit()
5 {
6 //省略了部分過程，列出實現關鍵函式
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); //設定MPP視訊快取池屬性
17
18
19 s32Ret = HI_MPI_VB_Init(); //初始化MPP快取池
20
21
22 s32Ret = HI_MPI_SYS_Init(); //初始化MPP系統
23
24 }
25
26 .............
27 }
（2）step2為SAMPLE_COMM_SVP_NNIE_LoadModel
函式從使用者事先載入到 buf 中的模型中解析出網路模型，其函式實現較為複雜，具體的函式引數解析和函式執行過程已經在前面隨筆給出了，需要的話，可以參考隨筆：
Hi3559AV100 NNIE開發（1）-RFCN(.wk)LoadModel函式引數解析 （https://www.cnblogs.com/iFrank/p/14500648.html）
Hi3559AV100 NNIE開發（2）-RFCN(.wk)LoadModel及NNIE Init函式執行過程分析 （https://www.cnblogs.com/iFrank/p/14503482.html）
（3）step3為SAMPLE_SVP_NNIE_Cnn_ParamInit
首先給出呼叫與定義，便於分析：
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函式及引數分析可見之前隨筆:
Hi3559AV100 NNIE開發（2）-RFCN(.wk)LoadModel及NNIE Init函式執行過程分析 （https://www.cnblogs.com/iFrank/p/14503482.html），之前的隨筆介紹的很詳細，這裡就不在贅述了。
對SAMPLE_SVP_NNIE_Cnn_SoftwareParaInit函式，首先給出定義：
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 }
函式體內最主要功能是實現s_stCnnSoftwareParam引數的賦值，包含大量賦值語句，其中s_stCnnSoftwareParam結構體各個元素賦值的意義等需要的時候再進行研討，此外函式還實現在使用者態分配 MMZ 記憶體。通過對兩個函式的分析，step3 SAMPLE_SVP_NNIE_Cnn_ParamInit()完成。
（4）step4為HI_MPI_SVP_NNIE_AddTskBuf
為了記錄 TskBuf 地址資訊，其作用和注意事項：
①記錄 TskBuf 地址資訊，用於減少核心態記憶體對映次數，提升效率；
②TskBuf 地址資訊的記錄是通過連結串列進行管理，連結串列長度預設值為 32，連結串列長度可通過模組引數 nnie_max_tskbuf_num 進行配；
③若沒呼叫 HI_MPI_SVP_NNIE_AddTskBuf 預先把 TskBuf 地址資訊記錄到系統，那麼之後呼叫 Forward/ForwardWithBbox 每次都會 Map/Unmap 操作 TskBuf 核心態虛擬地址，效率會比較低。
給出函式呼叫和定義:
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 //定義 8 HI_S32 HI_MPI_SVP_NNIE_AddTskBuf(const SVP_MEM_INFO_S* pstTskBuf);
（5）step5為SAMPLE_SVP_NNIE_FillSrcData
實現src資料的填充，此函式十分關鍵，對所給影象資料：./data/nnie_image/y/0_28x28.y進行處理，為了更好的分析資料處理函式，首先給出函式呼叫資訊：
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);
為了更加清楚函式功能，先給出函式定義，方便後面分析（忽略一些次要資訊）：
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)
總的來說，函式實現以下功能：
①open file fopen(pstNnieCfg->pszPic,"rb");
1 //定義檔名 2 HI_CHAR *pcSrcFile = "./data/nnie_image/y/0_28x28.y"; 3 4 stNnieCfg.pszPic= pcSrcFile; 5 6 //函式定義 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 //函式呼叫 11 SAMPLE_SVP_NNIE_FillSrcData(&stNnieCfg, 12 &s_stCnnNnieParam, 13 &stInputDataIdx); 14 15 fp = fopen(pstNnieCfg->pszPic,"rb");
②為後面fread讀取資料量確定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隨即通過pstNnieParam->astSegData[u32SegIdx].astSrc[u32NodeIdx].enType引數（引數找定義，應該是與輸入模型.wk的模型引數有關，後面可以直接通過printf進行列印輸出，看結果是啥）進行if-lese分支選擇，之後通過fread對fp檔案指標讀取資料，確定資料記憶體地址，並重新整理 cache 裡的內容到記憶體並且使 cache 裡的內容無效，最後fclose(fp)。
先給出enType引數型別：
程式碼實現：
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為SAMPLE_SVP_NNIE_Forward實現NNIE process
便於分析先給出函式的呼叫及引數的定義：
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函式主要實現將記憶體資料重新整理到記憶體中；②HI_MPI_SVP_NNIE_Forward函式同時對輸入樣本(s)進行CNN預測，對對應樣本(s)進行輸出響應；③HI_MPI_SVP_NNIE_Query函式用於查詢nnie上執行函式的狀態，在阻塞模式下，系統等待，直到被查詢的函式被呼叫；在非阻塞模式下，查詢當前狀態，不做任何操作。
（7）step7為SAMPLE_SVP_NNIE_Cnn_GetTopN實現軟體過程
給出函式呼叫與引數細節：
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, //通過此函式對s_stCnnSoftwareParam進行了賦值操作 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)
此函式目前基本不修改，函式內部具體實現目前暫不說明，只需注意一點如果改變了網路結構，請確保SAMPLE_SVP_NNIE_Cnn_GetTopN
函式的輸入資料正確。
（8）step8為SAMPLE_SVP_NNIE_Cnn_PrintResult列印blob引數值
給出函式呼叫與引數細節：
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, //通過此函式對s_stCnnSoftwareParam進行了賦值操作 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)
有什麼問題，大家可以提出來，一起討論，後面將給出mobilefacenet的NNIE實