Giter Site home page Giter Site logo

Comments (8)

UNeedCryDear avatar UNeedCryDear commented on June 20, 2024
  1. opencv版本确认下,3.x的我没试过,4.x的至少要opencv4.5.0及其以上。
  2. 读取失败的报错信息是什么?另外opencv不支持动态输入,也就是导出不能加--dynamic标志位
  3. 如果修改了后缀,请换成readNetFromONNX()看下

from yolov5-seg-opencv-onnxruntime-cpp.

theyunfeng avatar theyunfeng commented on June 20, 2024
  1. opencv版本确认下,3.x的我没试过,4.x的至少要opencv4.5.0及其以上。
  2. 读取失败的报错信息是什么?另外opencv不支持动态输入,也就是导出不能加--dynamic标志位
  3. 如果修改了后缀,请换成readNetFromONNX()看下

emmm,第一点,opencv版本是4.5.5的,第二点,ros下没输出报错信息,但是没移植到ros工作空间下时整个项目是可以正常于运行的,第三点,readNetFromONNX试过了,也不行

from yolov5-seg-opencv-onnxruntime-cpp.

UNeedCryDear avatar UNeedCryDear commented on June 20, 2024

没移植之前你正常运行确认下是否为opencv推理的,有可能你跑的是onnxruntime。
如果确认是opencv的话,那我就不知道什么原因了,我没试过ros系统,看不到具体报错信息我也没法确认是什么问题,只能你自己解决了。
或者你可以试一下走onnxruntime看看行不行。

from yolov5-seg-opencv-onnxruntime-cpp.

theyunfeng avatar theyunfeng commented on June 20, 2024

没移植之前你正常运行确认下是否为opencv推理的,有可能你跑的是onnxruntime。 如果确认是opencv的话,那我就不知道什么原因了,我没试过ros系统,看不到具体报错信息我也没法确认是什么问题,只能你自己解决了。 或者你可以试一下走onnxruntime看看行不行。

我发现问题了,即使制定了opencv4,ros在编译的时候也会用自己的opencv链接cv_bridge,就会导致出错,所以把cv_bridge链接的opencv库文件改为自己的opencv4.5.5就行了,这ros太坑人了

from yolov5-seg-opencv-onnxruntime-cpp.

theyunfeng avatar theyunfeng commented on June 20, 2024

请问除了用gpu加速外,有什么别的办法加速推理吗?比如减少识别的种类或者改点代码冗余的部分等(不太懂深度学习,可能说的不对)?

from yolov5-seg-opencv-onnxruntime-cpp.

UNeedCryDear avatar UNeedCryDear commented on June 20, 2024

除了显卡,其他针对ros系统优化的我不知道。
你说的识别种类可以(提升有,但是不会很大),还有就是将s模型换成n,减少输入图片大小,不用分割,只要检测等等,你自己多尝试一些

from yolov5-seg-opencv-onnxruntime-cpp.

theyunfeng avatar theyunfeng commented on June 20, 2024

除了显卡,其他针对ros系统优化的我不知道。 你说的识别种类可以(提升有,但是不会很大),还有就是将s模型换成n,减少输入图片大小,不用分割,只要检测等等,你自己多尝试一些

请问像这种场景,一个目标有多个矩形框是什么原因?NMS之后一个目标不应该只有一个检测框?
image

from yolov5-seg-opencv-onnxruntime-cpp.

UNeedCryDear avatar UNeedCryDear commented on June 20, 2024

你要不一个一个的画上去看下?画一个看一个?或者将同类的颜色随机赋值一下,每个实例颜色不一样你就能看出来是怎么回事了。
另外,nms是可以调整的,你如果觉得默认值不满足,你自己调整一下就是了啊

from yolov5-seg-opencv-onnxruntime-cpp.

Related Issues (20)

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.