server模型推理出错（core dumped）

[wanggp01]

问题描述 / Problem Description

使用ch_PP-OCRv4_det_infer模型进行推理时是正常的，但是使用server模型推理时，就报core dumped：

运行环境 / Runtime Environment

• OS: ubuntu18.04
• Paddle: 2.1.3
• PaddleOCR: release/2.7.1

复现代码 / Reproduction Code

使用的指令：python tools/infer/predict_system.py --image_dir="./tests/1.jpg" --det_model_dir="./models/server_model/ch_PP-OCRv4_det_server_infer/" --rec_model_dir="./models/server_model/ch_PP-OCRv4_rec_server_infer/" --cls_model_dir="models/server_model/ch_ppocr_mobile_v2.0_cls_infer" --use_angle_cls=true

完整报错 / Complete Error Message

---

C++ Traceback (most recent call last):

0 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
1 std::unique_ptr<paddle::PaddlePredictor, std::default_deletepaddle::PaddlePredictor > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
2 paddle::AnalysisPredictor::Init(std::shared_ptrpaddle::framework::Scope const&, std::shared_ptrpaddle::framework::ProgramDesc const&)
3 paddle::AnalysisPredictor::PrepareProgram(std::shared_ptrpaddle::framework::ProgramDesc const&)
4 paddle::AnalysisPredictor::OptimizeInferenceProgram()
5 paddle::inference::analysis::Analyzer::RunAnalysis(paddle::inference::analysis::Argument*)
6 paddle::inference::analysis::IrAnalysisPass::RunImpl(paddle::inference::analysis::Argument*)
7 paddle::inference::analysis::IRPassManager::Apply(std::unique_ptr<paddle::framework::ir::Graph, std::default_deletepaddle::framework::ir::Graph >)
8 paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
9 paddle::framework::ir::ConvEltwiseAddBNFusePass::ApplyImpl(paddle::framework::ir::Graph*) const
10 paddle::framework::ir::GraphPatternDetector::operator()(paddle::framework::ir::Graph*, std::function<void (std::map<paddle::framework::ir::PDNode*, paddle::framework::ir::Node*, std::lesspaddle::framework::ir::PDNode*, std::allocator<std::pair<paddle::framework::ir::PDNode* const, paddle::framework::ir::Node*> > > const&, paddle::framework::ir::Graph*)>)
11 paddle::framework::LoDTensor* paddle::framework::Variable::GetMutablepaddle::framework::LoDTensor()
12 paddle::framework::SignalHandle(char const*, int)
13 paddle::platform::GetCurrentTraceBackStringabi:cxx11

---

Error Message Summary:

FatalError: Segmentation fault is detected by the operating system.
[TimeInfo: *** Aborted at 1716639975 (unix time) try "date -d @1716639975" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x0) received by PID 16460 (TID 0x7f98e8477080) from PID 0 ***]

Segmentation fault (core dumped)

可能解决方案 / Possible solutions

附件 / Appendix

[UserWangZz]

考虑是否paddlepaddle-gpu与cuda版本是否匹配

[wanggp01]

考虑是否paddlepaddle-gpu与cuda版本是否匹配

目前cuda版本：10.1，cudnn版本：7.6.5， paddlepaddle-gpu版本：2.1.3

[GreatV]

安装 develop 版本 的 paddlepaddle 试试看 https://www.paddlepaddle.org.cn/