深度学习算法优化系列二十二 | 利用TensorRT部署YOLOV3-Tiny INT8量化模型

namespace nvinfer1 {
 class int8EntroyCalibrator : public nvinfer1::IInt8EntropyCalibrator {
 public:
  int8EntroyCalibrator(const int &bacthSize,
   const std::string &imgPath,
   const std::string &calibTablePath);

  virtual ~int8EntroyCalibrator();

  int getBatchSize() const override { return batchSize; }

  bool getBatch(void *bindings[], const char *names[], int nbBindings) override;

  const void *readCalibrationCache(std::size_t &length) override;

  void writeCalibrationCache(const void *ptr, std::size_t length) override;

 private:

  bool forwardFace;

  int batchSize;
  size_t inputCount;
  size_t imageIndex;

  std::string calibTablePath;
  std::vector<std::string> imgPaths;

  float *batchData{ nullptr };
  void  *deviceInput{ nullptr };



  bool readCache;
  std::vector<char> calibrationCache;
 };

 int8EntroyCalibrator::int8EntroyCalibrator(const int &bacthSize, const std::string &imgPath,
  const std::string &calibTablePath) :batchSize(bacthSize), calibTablePath(calibTablePath), imageIndex(0), forwardFace(
   false) {
  int inputChannel = 3;
  int inputH = 416;
  int inputW = 416;
  inputCount = bacthSize*inputChannel*inputH*inputW;
  std::fstream f(imgPath);
  if (f.is_open()) {
   std::string temp;
   while (std::getline(f, temp)) imgPaths.push_back(temp);
  }
  int len = imgPaths.size();
  for (int i = 0; i < len; i++) {
   cout << imgPaths[i] << endl;
  }
  batchData = new float[inputCount];
  CHECK(cudaMalloc(&deviceInput, inputCount * sizeof(float)));
 }

 int8EntroyCalibrator::~int8EntroyCalibrator() {
  CHECK(cudaFree(deviceInput));
  if (batchData)
   delete[] batchData;
 }

 bool int8EntroyCalibrator::getBatch(void **bindings, const char **names, int nbBindings) {
  cout << imageIndex << " " << batchSize << endl;
  cout << imgPaths.size() << endl;
  if (imageIndex + batchSize > int(imgPaths.size()))
   return false;
  // load batch
  float* ptr = batchData;
  for (size_t j = imageIndex; j < imageIndex + batchSize; ++j)
  {
   //cout << imgPaths[j] << endl;
   Mat img = cv::imread(imgPaths[j]);
   vector<float>inputData = prepareImage(img);
   cout << inputData.size() << endl;
   cout << inputCount << endl;
   if ((int)(inputData.size()) != inputCount)
   {
    std::cout << "InputSize error. check include/ctdetConfig.h" << std::endl;
    return false;
   }
   assert(inputData.size() == inputCount);
   int len = (int)(inputData.size());
   memcpy(ptr, inputData.data(), len * sizeof(float));

   ptr += inputData.size();
   std::cout << "load image " << imgPaths[j] << "  " << (j + 1)*100. / imgPaths.size() << "%" << std::endl;
  }
  imageIndex += batchSize;
  CHECK(cudaMemcpy(deviceInput, batchData, inputCount * sizeof(float), cudaMemcpyHostToDevice));
  bindings[0] = deviceInput;
  return true;
 }
 const void* int8EntroyCalibrator::readCalibrationCache(std::size_t &length)
 {
  calibrationCache.clear();
  std::ifstream input(calibTablePath, std::ios::binary);
  input >> std::noskipws;
  if (readCache && input.good())
   std::copy(std::istream_iterator<char>(input), std::istream_iterator<char>(),
    std::back_inserter(calibrationCache));

  length = calibrationCache.size();
  return length ? &calibrationCache[0] : nullptr;
 }

 void int8EntroyCalibrator::writeCalibrationCache(const void *cache, std::size_t length)
 {
  std::ofstream output(calibTablePath, std::ios::binary);
  output.write(reinterpret_cast<const char*>(cache), length);
 }
}

// ONNX模型转为TensorRT引擎
bool onnxToTRTModel(const std::string& modelFile, // onnx文件的名字
 const std::string& filename,  // TensorRT引擎的名字 
 IHostMemory*& trtModelStream) // output buffer for the TensorRT model
{
 // 创建builder
 IBuilder* builder = createInferBuilder(gLogger.getTRTLogger());
 assert(builder != nullptr);
 nvinfer1::INetworkDefinition* network = builder->createNetwork();

 if (!builder->platformHasFastInt8()) return false;

 // 解析ONNX模型
 auto parser = nvonnxparser::createParser(*network, gLogger.getTRTLogger());


 //可选的 - 取消下面的注释可以查看网络中每层的详细信息
 //config->setPrintLayerInfo(true);
 //parser->reportParsingInfo();

 //判断是否成功解析ONNX模型
 if (!parser->parseFromFile(modelFile.c_str(), static_cast<int>(gLogger.getReportableSeverity())))
 {
  gLogError << "Failure while parsing ONNX file" << std::endl;
  return false;
 }

 
 // 建立推理引擎
 builder->setMaxBatchSize(BATCH_SIZE);
 builder->setMaxWorkspaceSize(1 << 30);

 nvinfer1::int8EntroyCalibrator *calibrator = nullptr;
 if (calibFile.size()>0) calibrator = new nvinfer1::int8EntroyCalibrator(BATCH_SIZE, calibFile, "F:/TensorRT-6.0.1.5/data/v3tiny/calib.table");


 //builder->setFp16Mode(true);
 std::cout << "setInt8Mode" << std::endl;
 if (!builder->platformHasFastInt8())
  std::cout << "Notice: the platform do not has fast for int8" << std::endl;
 builder->setInt8Mode(true);
 builder->setInt8Calibrator(calibrator);
 /*if (gArgs.runInInt8)
 {
  samplesCommon::setAllTensorScales(network, 127.0f, 127.0f);
 }*/
 //samplesCommon::setAllTensorScales(network, 1.0f, 1.0f);
 cout << "start building engine" << endl;
 ICudaEngine* engine = builder->buildCudaEngine(*network);
 cout << "build engine done" << endl;
 assert(engine);
 if (calibrator) {
  delete calibrator;
  calibrator = nullptr;
 }
 // 销毁模型解释器
 parser->destroy();

 // 序列化引擎
 trtModelStream = engine->serialize();

 // 保存引擎
 nvinfer1::IHostMemory* data = engine->serialize();
 std::ofstream file;
 file.open(filename, std::ios::binary | std::ios::out);
 cout << "writing engine file..." << endl;
 file.write((const char*)data->data(), data->size());
 cout << "save engine file done" << endl;
 file.close();

 // 销毁所有相关的东西
 engine->destroy();
 network->destroy();
 builder->destroy();

 return true