Jetson-Deepstream踩坑记录

最新推荐文章于 2024-02-18 13:21:32 发布

D4MONZZZ

最新推荐文章于 2024-02-18 13:21:32 发布

阅读量209

点赞数

分类专栏： Deepstream笔记文章标签： python

本文链接：https://blog.csdn.net/weixin_42202176/article/details/130384749

版权

Deepstream笔记专栏收录该内容

4 篇文章 1 订阅

订阅专栏

1 刷机

报错

File System and OS - target_image: Depends: python2 (= 2.7.16-1) but 2.7.17-2ubuntu4 is to be installed

网上苦寻无果，在chatgpt的帮助下解决
chatgpt回答：
It seems that there is still a version conflict between the Python2 package you are trying to install and the version of Python2 that is currently installed on your system.

One possible solution to this issue is to try explicitly specifying the version numbers for both python2-minimal and libpython2-stdlib packages as follows:

sudo apt-get install python2=2.7.16-1 python2-minimal=2.7.16-1 libpython2-stdlib=2.7.16-1

This command should install the specific version of Python2 and its dependencies that you need.

If this still does not work, you can try using the dpkg command to force install the specific version of python2 as follows:

sudo dpkg -i --force-all /var/cache/apt/archives/python2_2.7.16-1_amd64.deb

This command will try to forcefully install the python2 package even if it conflicts with existing packages or dependencies. However, please note that this should be used with caution as it may cause issues with your system stability.

I hope this helps! Let me know if you have any further questions or concerns.

执行第一个命令之后就ok了

10:00:06 ERROR: File System and OS - target_image: Err:20 https://dl.bintray.com/etcher/debian stable Release
10:00:13 ERROR: File System and OS - target_image: E: The repository 'https://deb.etcher.io stable Release' does not have a Release file.
10:00:18 ERROR: File System and OS - target_image: command terminated with error
10:00:18 SUMMARY: File System and OS - target_image: First Error: Installation failed.

2 常见错误总结

在尝试从batch中获取frame到CPU时报错

thread *** received signal SIGSEGV, Segmentation fault

底层c指针错误回收/指向错误导致

解决方法：

mem_type = 3 # 0 for jetson

caps = Gst.Caps.from_string("video/x-raw(memory:NVMM), format=RGBA")
nvfilter = Gst.ElementFactory.make("capsfilter", "filter")
nvfilter.set_property("caps", caps)

streammux.set_property("nvbuf-memory-type", mem_type)
nvvideoconvert.set_property("nvbuf-memory-type", mem_type)

在pipeline中加入上述Element之后，再在下游获取frame即可。