GithubHelp home page GithubHelp logo

baronleelzp / hi3516dv300_nnie-yolov3-demo Goto Github PK

View Code? Open in Web Editor NEW
29.0 29.0 13.0 64.77 MB

在海思Hisilicon的Hi3516dv300芯片上,利用nnie和opencv库,简洁了官方yolov3用例中各种复杂的嵌套调用/复杂编译,提供了交叉编译后可成功上板部署运行的demo。

Makefile 0.02% C 25.39% Shell 0.01% C++ 74.46% Objective-C 0.12%

hi3516dv300_nnie-yolov3-demo's People

Contributors

baronleelzp avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

hi3516dv300_nnie-yolov3-demo's Issues

关于模型转换的问题

大佬,可以分享以下您在caffe转nnie时使用的caffe网络模型吗?想确认一下我的是否正确。

OpenCV库的问题

微信图片编辑_20230822175506
您好,请问这是哪里出了问题呢?我把代码下载好,就改动了makefile里面的交叉编译工具地址

可执行程序test执行错误

您好,我用提供的代码成功生成可执行程序test,但是在上板后出现像这种错误,可以看下是因为什么嘛?谢谢
./test: reTocation error: /usr/Lib/Libopencv_ core.so.4.1: symbol mmz_ userdev :mmz_ userdeV_ release:ZNSt15_exception ptr13exception ptrClEv, version CXXABI_ 1.3.11MMB L EAK(pid=300) : 0xA10A3000, 62939136 bytes, 'SAMPLE NNIE MOD not defined in file libstdc++ . smmz_ userdev :mmz_ userdev_ release: 0.6 with Link time reference mmb<0xa10a300> mapped to userspace 0xb1ca3000 will be unmaped!
mmz_ userdev:mmz_ userdev_ release: MMB LEAK(pid=300): 0xA4CA9000, 16003072 bytes, ,SAMPLE NNIE TAS 1

opencv依赖库是不是缺了一些东西?

我打算先通过cv::imread读取jpg格式的图片,再通过cvtColor函数转成yuv格式最后喂给模型进行识别,发现imread这个函数读图片结果是空的,确认了图片、路径都没有问题,怀疑是不是opencv的库不全?

opencv 依赖问题

你好,我直接使用仓库里面的opencv运行的。./test报错
./test: error while loading shared libraries: ../../lib/libopencv_videoio.so: cannot open shared object file: No such file or directory
已经实现把libopencv 和libhisi添加到环境变量中了.
export LD_LIBRARY_PATH='/usr/local/lib:/usr/lib:/home/work/libopencv/lib:/home/work/libhisi/lib'
通过查看read_elf libopencv_highgui.so我发现.so文件中指定了动态链接的相对路径。
![_AIDJP{OG@}I6%@)TJ0 OE](https://user-images.githubusercontent.com/48244371/186081768-17bbd094-d39a-40f6-a380-86bc597eefe6.png)
`
网上说需要从头编译opencv,修改编译参数才行。请问您是如何解决这个问题的呢?如果不得不重新编译opencv的话,请问海思/华为是否有提供编译好的opencv来下载呢。非常感谢

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.