Press "Enter" to skip to content

Hi3559AV100 NNIE开发(4)mobilefacenet.cfg参数配置挖坑解决与SVP_NNIE_Cnn实现分析

本站内容均来自兴趣收集,如不慎侵害的您的相关权益,请留言告知,我们将尽快删除.谢谢.

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     
 6     stNnieCfg.pszPic= pcSrcFile;
 7     stNnieCfg.u32MaxInputNum = u32PicNum; 
 8     stNnieCfg.u32MaxRoiNum = 0;
 9     stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;
10     s_stCnnSoftwareParam.u32TopN = 5;
11 
12 
13 
14     
15     SAMPLE_COMM_SVP_CheckSysInit();
16 
17     
18     s32Ret = SAMPLE_COMM_SVP_NNIE_LoadModel(pcModelName,&s_stCnnModel);
19 
20 
21     
22     
25     s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel;
26     s32Ret = SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg,&s_stCnnNnieParam,&s_stCnnSoftwareParam);
27 
28 
29     
30     s32Ret = HI_MPI_SVP_NNIE_AddTskBuf(&(s_stCnnNnieParam.astForwardCtrl[0].stTskBuf));
31 
32 
33     
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     
41     stProcSegIdx.u32SegIdx = 0;
42     s32Ret = SAMPLE_SVP_NNIE_Forward(&s_stCnnNnieParam,&stInputDataIdx,&stProcSegIdx,HI_TRUE);
43 
44 
45 
46     
47     
49     s32Ret = SAMPLE_SVP_NNIE_Cnn_GetTopN(&s_stCnnNnieParam,&s_stCnnSoftwareParam);
50 
51 
52 
53     
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         
 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);  
17 
18 
19         s32Ret = HI_MPI_VB_Init();  
20 
21 
22         s32Ret = HI_MPI_SYS_Init(); 
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 (https://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 (https://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 
 2 stNnieCfg.pszPic= pcSrcFile;
 3 stNnieCfg.u32MaxInputNum = u32PicNum; 
 4 stNnieCfg.u32MaxRoiNum = 0;
 5 stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;
 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     
23     s32Ret = SAMPLE_COMM_SVP_NNIE_ParamInit(pstNnieCfg,
24                                             pstCnnPara);
25 
26 
27     
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 (https://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     
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     
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     
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     
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,那幺之后调用 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      
2 s_stCnnNnieParam.pstModel = &s_stCnnModel.stModel;
3     
4 s32Ret = HI_MPI_SVP_NNIE_AddTskBuf(&(s_stCnnNnieParam.astForwardCtrl[0].stTskBuf));
5 
6 
7 
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; 
 3     stNnieCfg.u32MaxRoiNum = 0;
 4     stNnieCfg.aenNnieCoreId[0] = SVP_NNIE_ID_0;
 5 
 6 
 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 
 2 HI_CHAR *pcSrcFile = "./data/nnie_image/y/0_28x28.y";
 3 
 4 stNnieCfg.pszPic= pcSrcFile;
 5 
 6 
 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 
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     
 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     
 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     
 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     
 3                         
 4     s_stCnnSoftwareParam.u32TopN = 5;
 5     SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg, 
 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     
 3                         
 4     s_stCnnSoftwareParam.u32TopN = 5;
 5     SAMPLE_SVP_NNIE_Cnn_ParamInit(&stNnieCfg, 
 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)

 

有什幺问题,大家可以提出来,一起讨论,后面将给出mobilefacenet的NNIE实现。

Be First to Comment

发表评论

您的电子邮箱地址不会被公开。 必填项已用*标注