PaddlePaddle / PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
https://paddlepaddle.github.io/PaddleOCR/
Apache License 2.0
42.78k stars 7.69k forks source link

Segmentation fault (core dumped) #8827

Closed Biaocsu closed 1 year ago

Biaocsu commented 1 year ago

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem


C++ Traceback (most recent call last):

0 paddle::AnalysisPredictor::ZeroCopyRun() 1 paddle::framework::NaiveExecutor::Run() 2 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, phi::Place const&) 3 paddle::operators::TensorRTEngineOp::RunImpl(paddle::framework::Scope const&, phi::Place const&) const 4 paddle::operators::TensorRTEngineOp::PrepareTRTEngine(paddle::framework::Scope const&, paddle::inference::tensorrt::TensorRTEngine) const 5 paddle::inference::tensorrt::OpConverter::ConvertBlockToTRTEngine(paddle::framework::BlockDesc, paddle::framework::Scope const&, std::vector<std::string, std::allocator > const&, std::unordered_set<std::string, std::hash, std::equal_to, std::allocator > const&, std::vector<std::string, std::allocator > const&, paddle::inference::tensorrt::TensorRTEngine*) 6 paddle::inference::tensorrt::TensorRTEngine::FreezeNetwork()


Error Message Summary:

FatalError: Segmentation fault is detected by the operating system. [TimeInfo: Aborted at 1673430128 (unix time) try "date -d @1673430128" if you are using GNU date ] [SignalInfo: SIGSEGV (@0x8) received by PID 935 (TID 0x7f16e9cb2f40) from PID 8 ]

Segmentation fault (core dumped) `

image image

其他说明: 关闭tensorrt,不论使用GPU、CPU均正常 打开tensorrt,即use_tensorrt=true时,才会报上述错误

LDOUBLEV commented 1 year ago

使用的paddle预测库是否是带TRT的,https://www.paddlepaddle.org.cn/inference/v2.3/user_guides/download_lib.html#python

Biaocsu commented 1 year ago

@LDOUBLEV 从PaddlePaddle官网下载的安装包,因此不带TRT,TensorRT是我自己从Nvidia官网下载安装的,已经安装成功了,上面有我的安装成功检测

请帮忙分析下原因,看到好多同样的issue,但是没有统一的解决方案

Biaocsu commented 1 year ago

@LDOUBLEV 根据您给的链接,是否需要我卸载掉paddlepaddle,然后手动安装带trt的paddlepaddle安装包? 我自己从nvidia官网下载安装的tensorrt为什么不行呢?是因为paddlepaddle支持性问题吗?

Biaocsu commented 1 year ago

使用的paddle预测库是否是带TRT的,https://www.paddlepaddle.org.cn/inference/v2.3/user_guides/download_lib.html#python

1、卸载已有paddlepaddle安装包,根据上面链接安装带trt的paddlepaddle安装包,仍然出现前述相同报错 2、使用新的docker容器,镜像还是上述给出这个,重新操作一遍,仍然出现上述问题 这应该是一个bug了,该问题可复现

Biaocsu commented 1 year ago

@LDOUBLEV @tink2123 @sdcb @ZeyuChen 请帮忙看下该问题,太多人遇到了,而且我这边可复现,应该是Bug

LDOUBLEV commented 1 year ago

需要重新安装带TRT的paddle 下载TRT压缩包,设置LD_LIBRARY_PATH为TRT的路径 TRT和带TRT的paddle安装参考文档,https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/test_tipc/docs/install.md#32-%E5%AE%89%E8%A3%85tensorrt

安装待TRT版本的paddle也可以从我上面发你的链接里下载:https://www.paddlepaddle.org.cn/inference/v2.3/user_guides/download_lib.html#python

Biaocsu commented 1 year ago

需要重新安装带TRT的paddle 下载TRT压缩包,设置LD_LIBRARY_PATH为TRT的路径 TRT和带TRT的paddle安装参考文档,https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/test_tipc/docs/install.md#32-%E5%AE%89%E8%A3%85tensorrt

安装待TRT版本的paddle也可以从我上面发你的链接里下载:https://www.paddlepaddle.org.cn/inference/v2.3/user_guides/download_lib.html#python

你好,已经根据你的说明,下载带TRT的paddle,仍然出现了上述问题,你仔细看下我的描述 所以很困惑,目前不知道该怎么解决此问题

github-actions[bot] commented 1 year ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.

Katherinaxxx commented 2 months ago

需要重新安装带TRT的paddle 下载TRT压缩包,设置LD_LIBRARY_PATH为TRT的路径 TRT和带TRT的paddle安装参考文档,https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/test_tipc/docs/install.md#32-%E5%AE%89%E8%A3%85tensorrt 安装待TRT版本的paddle也可以从我上面发你的链接里下载:https://www.paddlepaddle.org.cn/inference/v2.3/user_guides/download_lib.html#python

你好,已经根据你的说明,下载带TRT的paddle,仍然出现了上述问题,你仔细看下我的描述 所以很困惑,目前不知道该怎么解决此问题

请问解决了吗

b4bbuilder commented 2 weeks ago

@Biaocsu you figure out a solution? Having the same problem.