Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
6017 Discussions

Valgrind memory leak with openvino inference engine: LoadNetwork

matpe333
Beginner
527 Views

Hi, I used valgrind to check my program for memory leaks. Besides the already reported definitely lost leak  I got another probable leak in InferenceEngine::Core::LoadNetwork. I looked into a possibility to free the memory somehow with the provided API but I did not find a way to do that. I used OpenVino 2021.4.1.

Valgrind report:

 160 bytes in 1 blocks are still reachable in loss record 20 of 29
    at 0x4C3217F: operator new(unsigned long) (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
    by 0x69D49EF: InferenceEngine::ExecutorManager::getIdleCPUStreamsExecutor(InferenceEngine::IStreamsExecutor::Config const&) (in libinference_engine.so)
    by 0x7D21173: ???
    by 0x699E420: InferenceEngine::IInferencePlugin::LoadNetwork(InferenceEngine::CNNNetwork const&, std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > > const&, std::shared_ptr<InferenceEngine::RemoteContext> const&) (in libinference_engine.so)
    by 0x6996354: InferenceEngine::IInferencePlugin::LoadNetwork(InferenceEngine::CNNNetwork const&, std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > > const&) (in libinference_engine.so)
    by 0x69FD723: ??? (in libinference_engine.so)
    by 0x6A01142: ??? (in libinference_engine.so)
    by 0x6A2B2A7: InferenceEngine::Core::LoadNetwork(InferenceEngine::CNNNetwork const&, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, std::map<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, std::less<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > >, std::allocator<std::pair<std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > > > > const&) (in libinference_engine.so)

 

0 Kudos
5 Replies
Wan_Intel
Moderator
504 Views

Hi Matpe333,

Thanks for reaching out to us.


We sincerely apologize for any inconvenience you may have experienced.


For your information, we are aware of this issue and our developers are trying to fix it in the future release.


Your continued support is appreciated.



Regards,

Wan


matpe333
Beginner
476 Views

Hi Wan,

 

thanks for your reply. Glad to hear that you are already working on it

 

Regards,

Matpe333

Wan_Intel
Moderator
446 Views

Hi Matpe333,

Thanks for your question!

 

If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

 

 

Regards,

Wan


Wan_Intel
Moderator
392 Views

Hi Matpe333,


Could you please try the latest OpenVINO which is 2021.4.2 which should have the fix for a memory leak.



Regards,

Wan


Wan_Intel
Moderator
360 Views

Hi Matpe333,

Thanks for your question.


This thread will no longer be monitored since we have provided a solution. 

If you need any additional information from Intel, please submit a new question.



Regards,

Wan


Reply