PaddleOCR seg faults

[umayrh]

Hi. While processing a bunch of JPEGs using PaddleOCR, I occasionally encounter a mysterious seg fault. I haven't yet looked into the image being read before the crash, but wonder if the error message might help figure out what's going on.

NB. Seems like the seg fault goes away if I set use_angle_cls=False.

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

• 系统环境/System Environment：

Linux 6.5.0-15-generic #15~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Jan 12 18:54:30 UTC 2 x86_64 x86_64 x86_64 GNU/Linux. Python 3.11.7.

• 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：

paddlepaddle==2.6.0
paddleocr==2.7.0.3

• 运行指令/Command Code：

text_det = paddleocr.PaddleOCR(lang="en", use_gpu=False, use_angle_cls=True)
doc_text = text_det.ocr(jpeg_image_path)

There there multiple paddleocr.PaddleOCR() instances being created, each by a different thread spawned by Flask-APScheduler's BackgroundScheduler (https://apscheduler.readthedocs.io/en/3.x/modules/schedulers/background.html).

• 完整报错/Complete Error Message：

 umayr-home bash[36696]: [2024/02/17 16:32:16] ppocr DEBUG: dt_boxes num : 49, elapsed : 0.15033006
66809082
 16:32:16 umayr-home bash[36696]: [2024/02/17 16:32:16] ppocr DEBUG: dt_boxes num : 89, elapsed : 0.16058468
81866455
 16:32:16 umayr-home bash[36696]: [2024/02/17 16:32:16] ppocr DEBUG: cls num  : 49, elapsed : 0.111751317977
90527
 16:32:16 umayr-home bash[36696]: --------------------------------------
 16:32:16 umayr-home bash[36696]: C++ Traceback (most recent call last):
 16:32:16 umayr-home bash[36696]: --------------------------------------
 16:32:16 umayr-home bash[36696]: 0   paddle::AnalysisPredictor::ZeroCopyRun()
 16:32:16 umayr-home bash[36696]: 1   paddle::framework::NaiveExecutor::Run()
 16:32:16 umayr-home bash[36696]: 2   paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, 
phi::Place const&)
 16:32:16 umayr-home bash[36696]: 3   paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scop
e const&, phi::Place const&) const
 16:32:16 umayr-home bash[36696]: 4   paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scop
e const&, phi::Place const&, paddle::framework::RuntimeContext*) const
 16:32:16 umayr-home bash[36696]: 5   void phi::KernelImpl<void (*)(phi::OneDNNContext const&, phi::DenseTen
sor const&, phi::DenseTensor const&, paddle::optional<phi::DenseTensor> const&, paddle::optional<phi::DenseTensor> c
onst&, std::vector<int, std::allocator<int> > const&, std::vector<int, std::allocator<int> > const&, std::string con
st&, std::vector<int, std::allocator<int> > const&, int, std::string const&, std::string const&, std::string const&,
 bool, bool, phi::DenseTensor*), &(void phi::fusion::FusedConv2DKernel<float, phi::OneDNNContext>(phi::OneDNNContext
 const&, phi::DenseTensor const&, phi::DenseTensor const&, paddle::optional<phi::DenseTensor> const&, paddle::option
al<phi::DenseTensor> const&, std::vector<int, std::allocator<int> > const&, std::vector<int, std::allocator<int> > c
onst&, std::string const&, std::vector<int, std::allocator<int> > const&, int, std::string const&, std::string const
&, std::string const&, bool, bool, phi::DenseTensor*))>::KernelCallHelper<paddle::optional<phi::DenseTensor> const&, paddle::optional<phi::DenseTensor> const&, std::vector<int, std::allocator<int> > const&, std::vector<int, std::allocator<int> > const&, std::string const&, std::vector<int, std::allocator<int> > const&, int, std::string const&, std::string const&, std::string const&, bool, bool, phi::DenseTensor*, phi::TypeTag<int> >::Compute<1, 2, 0, 0, phi::OneDNNContext const, phi::DenseTensor const, phi::DenseTensor const>(phi::KernelContext*, phi::OneDNNContext const&, phi::DenseTensor const&, phi::DenseTensor const&)
 16:32:16 umayr-home bash[36696]: 6   void phi::fusion::FusedConv2DKernel<float, phi::OneDNNContext>(phi::OneDNNContext const&, phi::DenseTensor const&, phi::DenseTensor const&, paddle::optional<phi::DenseTensor> const&, paddle::optional<phi::DenseTensor> const&, std::vector<int, std::allocator<int> > const&, std::vector<int, std::allocator<int> > const&, std::string const&, std::vector<int, std::allocator<int> > const&, int, std::string const&, std::string const&, std::string const&, bool, bool, phi::DenseTensor*)
 16:32:16 umayr-home bash[36696]: 7   void phi::ConvOnednn<float, phi::OneDNNContext>(phi::OneDNNContext const&, phi::DenseTensor const*, phi::DenseTensor const*, phi::DenseTensor const*, phi::DenseTensor const*, std::vector<int, std::allocator<int> > const&, std::vector<int, std::allocator<int> > const&, std::string const&, std::vector<int, std::allocator<int> > const&, int, std::string const&, bool, bool, std::string const&, bool, bool, phi::DenseTensor*)
 16:32:16  16:32:16 umayr-home bash[36696]: 8   phi::ComputeFP32<float, float>(phi::OneDNNContext const&, phi::DenseTe
nsor const*, phi::DenseTensor const*, phi::DenseTensor const*, phi::DenseTensor const*, std::vector<int, std::alloca
tor<int> > const&, std::vector<int, std::allocator<int> > const&, std::string const&, std::vector<int, std::allocato
r<int> > const&, int, std::string const&, bool, bool, std::string const&, bool, bool, phi::DenseTensor*)::{lambda()#
1}::operator()() const::{lambda()#1}::operator()() const
 16:32:16 umayr-home bash[36696]: 9   phi::funcs::OneDNNHandlerT<float, dnnl::convolution_forward, dnnl::con
volution_backward_data, dnnl::convolution_backward_weights>::AcquireReorder(std::shared_ptr<dnnl::memory> const&, std::shared_ptr<dnnl::memory> const&)
 16:32:16 umayr-home bash[36696]: 10  dnnl::reorder::primitive_desc::primitive_desc(dnnl::memory const&, dnnl::memory const&, dnnl::primitive_attr const&, bool)
 16:32:16 umayr-home bash[36696]: 11  dnnl::memory::get_desc() const
 16:32:16 umayr-home bash[36696]: ----------------------
 16:32:16 umayr-home bash[36696]: Error Message Summary:
 16:32:16 umayr-home bash[36696]: ----------------------
 16:32:16 umayr-home bash[36696]: FatalError: `Segmentation fault` is detected by the operating system.
 16:32:16 umayr-home bash[36696]:   [TimeInfo: *** Aborted at 1708169536 (unix time) try "date -d @1708169536" if you are using GNU date ***]
 16:32:16 umayr-home bash[36696]:   [SignalInfo: *** SIGSEGV (@0x0) received by PID 36696 (TID 0x7f76ab7fd640) from PID 0 ***]

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no): no

请尽量不要包含图片在问题中/Please try to not include the image in the issue.

[fanxing-6]

我也遇到了 wsl2 ubuntu22.04环境

[zjlw]

内存或者显存不够了吧？

[fanxing-6]

不是 是需要用 conda 安装paddle pip安装会出现这个问题

[umayrh]

不是 是需要用 conda 安装paddle pip安装会出现这个问题

Alright. Thanks