c++ - 升级到 TensorRT 7 后加载或构建 cuda 引擎偶尔会崩溃

Question

我正在尝试在 C++ 中运行 TensorRT 推理。有时，在尝试构建新引擎或从文件加载引擎时，代码会崩溃。它偶尔会发生(有时它运行没有任何问题)。我按照以下步骤准备网络:

initLibNvInferPlugins(&gLogger.getTRTLogger(), "");

if (mParams.loadEngine.size() > 0)
{
    std::vector<char> trtModelStream;
    size_t size{0};
    std::ifstream file(mParams.loadEngine, std::ios::binary);

    if (file.good())
    {
        file.seekg(0, file.end);
        size = file.tellg();
        file.seekg(0, file.beg);
        trtModelStream.resize(size);
        file.read(trtModelStream.data(), size);
        file.close();
    }
    IRuntime* infer_Runtime = nvinfer1::createInferRuntime(gLogger);
    if (mParams.dlaCore >= 0)
    {
        infer_Runtime->setDLACore(mParams.dlaCore);
    }


    mEngine = std::shared_ptr<nvinfer1::ICudaEngine>(
                infer_Runtime->deserializeCudaEngine(trtModelStream.data(), size, nullptr), samplesCommon::InferDeleter());

    gLogInfo << "TRT Engine loaded from: " << mParams.loadEngine << endl;

    infer_Runtime->destroy();
    if (!mEngine)
    {
        return false;
    }
    else
    {
        return true;
    }
}

auto builder = SampleUniquePtr<nvinfer1::IBuilder>(nvinfer1::createInferBuilder(gLogger.getTRTLogger()));


const auto explicitBatch = 1U << static_cast<uint32_t>(NetworkDefinitionCreationFlag::kEXPLICIT_BATCH);
auto network = SampleUniquePtr<nvinfer1::INetworkDefinition>(builder->createNetworkV2(explicitBatch));
auto config = SampleUniquePtr<nvinfer1::IBuilderConfig>(builder->createBuilderConfig());
auto parser = SampleUniquePtr<nvonnxparser::IParser>(nvonnxparser::createParser(*network, gLogger.getTRTLogger()));

mEngine = nullptr;

parser->parseFromFile(
        locateFile(mParams.onnxFileName, mParams.dataDirs).c_str(), static_cast<int>(gLogger.getReportableSeverity()));

// Calibrator life time needs to last until after the engine is built.
std::unique_ptr<IInt8Calibrator> calibrator;

config->setAvgTimingIterations(1);
config->setMinTimingIterations(1);
config->setMaxWorkspaceSize(4_GiB);
builder->setMaxBatchSize(mParams.batchSize);


mEngine = std::shared_ptr<nvinfer1::ICudaEngine>(
            builder->buildEngineWithConfig(*network, *config), samplesCommon::InferDeleter());

错误发生在这里:

[05/12/2021-16:46:42] [I] [TRT] Detected 1 inputs and 1 output network tensors.

16:46:42: The program has unexpectedly finished.

加载现有引擎时，此行崩溃:

mEngine = std::shared_ptr<nvinfer1::ICudaEngine(
    infer_Runtime->deserializeCudaEngine(trtModelStream.data(), size, nullptr), samplesCommon::InferDeleter());

或者在构建引擎时:

mEngine = std::shared_ptr<nvinfer1::ICudaEngine>(
            builder->buildEngineWithConfig(*network, *config), samplesCommon::InferDeleter()); 

更多信息:

TensorRT 7.2.3
Ubuntu 18.04
cuDNN 8.1.1
CUDA 11.1 update1
ONNX 1.6.0
Pytorch 1.5.0

Answer 1

终于拿到了!
我重写了 CMake.txt 并添加了所有必需的库和路径，并删除了重复的库和路径。这可能是 cuBLAS 中的 lib 冲突。