Как я могу исправить проблему сеанса Onnxruntime-> Run? ⇐ C++

[Anonymous]

Я пытаюсь написать оболочку для onnxruntime.
Модель получает один тензор на входе и один тензор на выходе.
Во время сеанса->Выполнения внутри библиотеки onnxruntime возникает ошибка сегментации . Как загруженная библиотека, так и собранная из исходного кода выдают одну и ту же ошибку.
Вот ошибка:

Код: Выделить всё

Thread 1 "app" received signal SIGSEGV, Segmentation fault.
0x00007ffff6b16eb1 in onnxruntime::logging::ISink::Send (this=0x5555559154c0, timestamp=..., logger_id="", message=...) at /home/listray/Work/Libs/onnxruntime/include/onnxruntime/core/common/logging/isink.h:23
23      SendImpl(timestamp, logger_id, message);

Вот это:

Код: Выделить всё

#0  0x00007ffff6b16eb1 in onnxruntime::logging::ISink::Send (this=0x5555559154c0, timestamp=..., logger_id="", message=...)
at /home/listray/Work/Libs/onnxruntime/include/onnxruntime/core/common/logging/isink.h:23
#1  0x00007ffff6b174b8 in onnxruntime::logging::LoggingManager::Log (this=0x55555576cbb0, logger_id="", message=...) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/common/logging/logging.cc:153
#2  0x00007ffff6b16cae in onnxruntime::logging::Logger::Log (this=0x7fffffffcdd0, message=...) at /home/listray/Work/Libs/onnxruntime/include/onnxruntime/core/common/logging/logging.h:291
#3  0x00007ffff6b16ce0 in onnxruntime::logging::Capture::~Capture (this=0x7fffffffc4e0, __in_chrg=) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/common/logging/capture.cc:57
#4  0x00007ffff6a86301 in onnxruntime::SequentialExecutor::Execute(onnxruntime::SessionState const&, std::vector const&, std::vector const&, std::vector const&, std::vector&, std::unordered_map const&, onnxruntime::logging::Logger const&) (this=0x5555559da4c0, session_state=..., feed_mlvalue_idxs=std::vector of length 1, capacity 1 = {...},
feeds=std::vector of length 1, capacity 1 = {...}, fetch_mlvalue_idxs=std::vector of length 1, capacity 1 = {...}, fetches=std::vector of length 1, capacity 1 = {...},
fetch_allocators=std::unordered_map with 0 elements, logger=...) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/framework/sequential_executor.cc:309
#5  0x00007ffff6a6d787 in onnxruntime::utils::ExecuteGraphImpl(const onnxruntime::SessionState &, const onnxruntime::FeedsFetchesManager &, const std::vector &, std::vector &, const std::unordered_map  &, ExecutionMode, const bool &, const onnxruntime::logging::Logger &, bool) (session_state=..., feeds_fetches_manager=..., feeds=std::vector of length 1, capacity 1 = {...},
fetches=std::vector of length 1, capacity 1 = {...}, fetch_allocators=std::unordered_map with 0 elements, execution_mode=ORT_SEQUENTIAL, terminate_flag=@0x7fffffffd168: false, logger=...,
only_execute_path_to_fetches=false) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/framework/utils.cc:454
#6  0x00007ffff6a6df37 in onnxruntime::utils::ExecuteGraph (session_state=..., feeds_fetches_manager=..., feeds=std::vector of length 1, capacity 1 = {...}, fetches=std::vector of length 1, capacity 1 = {...},
execution_mode=ORT_SEQUENTIAL, terminate_flag=@0x7fffffffd168: false, logger=..., only_execute_path_to_fetches=false) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/framework/utils.cc:513
#7  0x00007ffff63e00c2 in onnxruntime::InferenceSession::Run (this=0x555555917110, run_options=..., feed_names=std::vector of length 1, capacity 1 = {...}, feeds=std::vector of length 1, capacity 1 = {...},
output_names=std::vector of length 1, capacity 1 = {...}, p_fetches=0x7fffffffd120) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/session/inference_session.cc:1206
#8  0x00007ffff637ecc3 in OrtApis::Run (sess=0x555555917110, run_options=0x0, input_names=0x5555559c1a10, input=0x7fffffffd2f8, input_len=1, output_names1=0x555555a521a0, output_names_len=1,
output=0x555555a3fb30) at /home/listray/Work/Libs/onnxruntime/onnxruntime/core/session/onnxruntime_c_api.cc:506
#9  0x00007ffff7ba6a93 in Ort::Session::Run (this=0x555555916440, run_options=..., input_names=0x5555559c1a10, input_values=0x7fffffffd2f8, input_count=1, output_names=0x555555a521a0,
output_values=0x555555a3fb30, output_count=1) at /home/listray/Work/Libs/onnx_debug/include/onnxruntime_cxx_inline.h:246
#10 0x00007ffff7ba69da in Ort::Session::Run (this=0x555555916440, run_options=..., input_names=0x5555559c1a10, input_values=0x7fffffffd2f8, input_count=1, output_names=0x555555a521a0, output_names_count=1)
at /home/listray/Work/Libs/onnx_debug/include/onnxruntime_cxx_inline.h:237
#11 0x00007ffff7bb0b31 in ai::common::OnnxruntimeGenericModelWrapper::process (this=0x55555576cb60, tensors=...)
at /home/listray/Work/Projects/ml-library/framework/onnxruntime/onnx_generic_model_wrapper.h:48
...

Загруженная библиотека останавливается на onnxruntime::logging::LoggingManager::Log.
Вот код-оболочка.
Загрузка модели:< /p>

Код: Выделить всё

void load_graph(const ByteBuffer& model)
{
// enviroment maintains thread pools and other state info
Ort::Env env(ORT_LOGGING_LEVEL_WARNING, "Vicue Run");
// initialize session options
Ort::SessionOptions session_options(nullptr);
//session_options.SetIntraOpNumThreads(1);

//Loading models
session = std::make_unique(env,
static_cast(model.data.get()),
model.length,
session_options);
}

Код: Выделить всё

session

— поле оболочки:

Код: Выделить всё

std::unique_ptr session;

Код: Выделить всё

ByteBuffer:
struct ByteBuffer
{
std::unique_ptr data;
size_t length;
}

На самом деле оболочка была универсальной, но этот код вызывает ту же ошибку.

Код: Выделить всё

std::array process(std::array tensors) override
{
std::array result;

// maybe this should be different if we have multiple input
Ort::AllocatorWithDefaultOptions allocator;
auto memory_info = Ort::MemoryInfo::CreateCpu(OrtArenaAllocator, OrtMemTypeDefault);

if(outputs == 1 &&  inputs == 1) {
auto input_shape = session->GetInputTypeInfo(0).GetTensorTypeAndShapeInfo().GetShape();

Ort::Value input_tensor = Ort::Value::CreateTensor(memory_info,
tensors[0].data.data(),
tensors[0].data.size(),
input_shape.data(),
input_shape.size());

std::vector input_node_names = { session->GetInputName(0, allocator) };
std::vector output_node_names = { session->GetOutputName(0, allocator) };
std::vector output_tensors = session->Run(Ort::RunOptions{nullptr},
input_node_names.data(),
&input_tensor,
inputs,
output_node_names.data(),
outputs);

Одна странная вещь, которую я не понимаю. Во время ошибки я вижу это:

Код: Выделить всё

(gdb) print this
$4 = (onnxruntime::logging::Capture * const) 0x7fffffffc4e0
(gdb) print this->logger_->logging_manager_->sink_
$5 = std::unique_ptr = {get() = 0x5555559154c0}
(gdb) print *(this->logger_->logging_manager_->sink_)
$6 = {_vptr.ISink = 0x0}

При создании средства ведения журнала его *(logging_manager_->sink_) также имеет значение {_vptr.ISink = 0x0}.

Подробнее здесь: https://stackoverflow.com/questions/627 ... un-problem