Method infer

samples/sampleINT8API/sampleINT8API.cpp:618–661

\brief Runs the TensorRT inference engine for this sample \details This function is the main execution function of the sample. It allocates the buffer, sets inputs, executes the engine, and verifies the output

//!          the buffer, sets inputs, executes the engine, and verifies the output
//!
sample::Logger::TestResult SampleINT8API::infer()
{
    // Create RAII buffer manager object
    samplesCommon::BufferManager buffers(mEngine);

    auto context = SampleUniquePtr<nvinfer1::IExecutionContext>(mEngine->createExecutionContext());
    if (!context)
    {
        return sample::Logger::TestResult::kFAILED;
    }

    // Read the input data into the managed buffers
    // There should be just 1 input tensor

    if (!prepareInput(buffers))
    {
        return sample::Logger::TestResult::kFAILED;
    }

    // Create CUDA stream for the execution of this inference
    cudaStream_t stream;
    CHECK(cudaStreamCreate(&stream));

    // Asynchronously copy data from host input buffers to device input buffers
    buffers.copyInputToDeviceAsync(stream);

    // Asynchronously enqueue the inference work
    if (!context->enqueueV2(buffers.getDeviceBindings().data(), stream, nullptr))
    {
        return sample::Logger::TestResult::kFAILED;
    }

    // Asynchronously copy data from device output buffers to host output buffers
    buffers.copyOutputToHostAsync(stream);

    // Wait for the work in the stream to complete
    CHECK(cudaStreamSynchronize(stream));

    // Release stream
    CHECK(cudaStreamDestroy(stream));

    // Check and print the output of the inference
    return verifyOutput(buffers) ? sample::Logger::TestResult::kRUNNING : sample::Logger::TestResult::kFAILED;
}

//!
//! \brief Used to clean up any state created in the sample class