inflateReset2 CRASH

[lxin49]

bug描述 Describe the Bug

OS: Debian12
Python: 3.10
paddlepaddle: 2.6.2-gpu
paddleocr: 2.9.1
cuda+cudnn: 11.8+9.0

from paddleocr import PaddleOCR, draw_ocr

ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path, cls=True)

output

--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   inflateReset2

----------------------
Error Message Summary:
----------------------
FatalError: `Segmentation fault` is detected by the operating system.
  [TimeInfo: *** Aborted at 1735470467 (unix time) try "date -d @1735470467" if you are using GNU date ***]
  [SignalInfo: *** SIGSEGV (@0x8) received by PID 33576 (TID 0x7f3352196b80) from PID 8 ***]

段错误

其他补充信息 Additional Supplementary Information

我尝试了cpu版本，仍然报了这个错误，网上搜索有说zlib问题的，本地是zlib1g 1.2.13。个人猜测是不是系统底层哪个函数命令不兼容，但无法验证。

我换了台电脑，使用cpu版本，其他不变，报错如下：

--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&)
1   std::unique_ptr<paddle::PaddlePredictor, std::default_delete<paddle::PaddlePredictor> > paddle::CreatePaddlePredictor<paddle::AnalysisConfig, (paddle::PaddleEngineKind)2>(paddle::AnalysisConfig const&)
2   paddle::AnalysisPredictor::Init(std::shared_ptr<paddle::framework::Scope> const&, std::shared_ptr<paddle::framework::ProgramDesc> const&)
3   paddle::AnalysisPredictor::PrepareProgram(std::shared_ptr<paddle::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_delete<paddle::framework::ir::Graph> >)
8   paddle::framework::ir::Pass::Apply(paddle::framework::ir::Graph*) const
9   paddle::framework::ir::SelfAttentionFusePass::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*, paddle::framework::ir::GraphPatternDetector::PDNodeCompare, std::allocator<std::pair<paddle::framework::ir::PDNode* const, paddle::framework::ir::Node*> > > const&, paddle::framework::ir::Graph*)>)

----------------------
Error Message Summary:
----------------------
FatalError: `Illegal instruction` is detected by the operating system.
  [TimeInfo: *** Aborted at 1735607958 (unix time) try "date -d @1735607958" if you are using GNU date ***]
  [SignalInfo: *** SIGILL (@0x7f007748331a) received by PID 7108 (TID 0x7f007ebe1b80) from PID 2001220378 ***]

再补充一个信息，我使用了docker，2.6.2-gpu-cuda11.2-cudnn8.2-trt8.0，使用GPU预测时，应该是正常的（不确定），因为我小本的显存不够，报显存溢出了。但是使用CPU预测时，还是报了上面类似的错误。我也查看了CPU构架，显示是支持avx2的。