Navigation

    全志在线开发者论坛

    • Register
    • Login
    • Search
    • Categories
    • Tags
    • 在线文档
    • 社区主页
    1. Home
    2. sunxi
    3. Topics
    S
    • Profile
    • Following 0
    • Followers 0
    • my integral 1265
    • Topics 13
    • Posts 23
    • Best 2
    • Groups 0

    Topics created by sunxi

    • S

      V853的经常报USB错误
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      0 Replies
      33 Views

      No one has replied

      0
    • S

      V853去掉LCD怎么配置
      V853系列-AI视觉 • Posted at • sunxi

      1 Votes
      3 Replies
      115 Views

      N Replied at

      @sunxi uboot和内核目录的config文件中

      3
    • S

      v853上电自动打开eth0怎么设置
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      4 Replies
      92 Views

      S Replied at

      @xjy_5 谢谢

      4
    • S

      全志人形识别的模型Gamma.nb是用什么框架训练的
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      0 Replies
      65 Views

      No one has replied

      0
    • S

      编译v853确实ssl库
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      4 Replies
      73 Views

      W Replied at

      @sunxi
      下面网址有详细说明。
      https://v853.docs.aw-ol.com/study/study_2ubuntu/

      4
    • S

      v853启动后没有wlan0
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      0 Replies
      52 Views

      No one has replied

      0
    • S

      tina编译demo失败
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      1 Replies
      57 Views

      A Replied at

      @sunxi source后 mkmpp,你的环境变量没有导入,不能直接make mk文件

      1
    • S

      NPU资源释放问题
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      1 Replies
      97 Views

      S Replied at

      请教:我需要连续高频次调用目标检测,我的思路是先进行一个初始化NPU_Yolo_init和一个预处理Detect_pr,然后调用Detect(),会造成内存不停疯长,一会就撑满了。不知道问题在哪里。劳烦大神指教。
      //初始化,执行一次
      int NPU_Yolo::NPU_Yolo_init(string moduleFile)
      {
      /* Initialize vip lite /
      status = vip_init(80 * 1024 * 1024);
      _CHECK_STATUS(status, final);
      printf("Initialize vip lite success\n");
      / Initialize network items /
      status = vnn_InitNetworkItem(&network_items,moduleFile);
      _CHECK_STATUS(status, final);
      printf("Initialize network items success\n");
      / Create the neural network */
      status = vnn_CreateNeuralNetwork(network_items);
      _CHECK_STATUS(status, final);
      printf("Create the neural network success\n");
      final:
      return status;
      }

      //作为预处理,执行一次
      void NPU_Yolo::Detect_pre(cv::Mat frame)
      {
      int sizeInt=640;//v5 640 v3 416
      int w=sizeInt;
      float h=frame.rowssizeInt/frame.cols;
      cv::resize(frame,frame,cv::Size(sizeInt,int(h)));
      Mat mat(Size(sizeInt,sizeInt),CV_8UC3,Scalar(0));
      Mat roi=mat(Rect(0,0,frame.cols,frame.rows));
      Mat mask=Mat(roi.rows,roi.cols,roi.depth(),Scalar(1));
      frame.copyTo(roi,mask);
      / Pre process the input/output data /
      status = vnn_PreProcessNeuralNetwork(network_items,frame);
      _CHECK_STATUS(status, final);
      printf("Pre process the input/output data success\n");
      / Run the neural network */
      status = vnn_RunNeuralNetwork(network_items);
      _CHECK_STATUS(status, final);
      printf("Run the neural network success\n");

      final:
      mat.release();

      }
      // 高频次调用进行目标检测
      vector<Object> NPU_Yolo::Detect(cv::Mat frame)
      {
      cout<<" *** 1 "<<endl;
      int sizeInt=640;//v5 640 v3 416
      int w=sizeInt;
      float h=frame.rows*sizeInt/frame.cols;
      cv::resize(frame,frame,cv::Size(sizeInt,int(h)));
      Mat mat(Size(sizeInt,sizeInt),CV_8UC3,Scalar(0));
      Mat roi=mat(Rect(0,0,frame.cols,frame.rows));
      cout<<" *** 2 "<<endl;
      Mat mask=Mat(roi.rows,roi.cols,roi.depth(),Scalar(1));
      frame.copyTo(roi,mask);
      std::vector<Object> objects= vnn_PostProcessNeuralNetwork(network_items,mat);
      cout<<" *** 3 "<<endl;
      _CHECK_STATUS(status, final);
      printf("Post process output data success\n");
      final:
      mat.release();
      cout<<" *** 4 "<<endl;
      }

      1
    • S

      求v853使用OpenCL对图片和视频编解码例子
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      8 Replies
      127 Views

      A Replied at

      @sunxi 是独立的视频引擎编码,不使用CPU也不使用NPU

      8
    • S

      V853 websocket报溢出
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      0 Replies
      47 Views

      No one has replied

      0
    • S

      v853开发板使用make menuconfig在哪里配置本地网卡和wifi
      V853系列-AI视觉 • Posted at • sunxi

      1 Votes
      1 Replies
      74 Views

      N Replied at

      @sunxi 我记得menuconfig里面也有kernelmodel的配置项,里面也有network的配置项,在这里就有网卡和wifi驱动的配置

      1
    • S

      yolov5量化导入模型报错
      V853系列-AI视觉 • Posted at • sunxi

      0 Votes
      2 Replies
      99 Views

      S Replied at

      @null037 感谢,已经找到原因了。

      2
    • 1 / 1