TensorRTx-YOLOv5工程解读（二）

具体Workflow

    if (!wts_name.empty()) {
    
        IHostMemory* modelStream{
     nullptr };
        APIToModel(BATCH_SIZE, &modelStream, is_p6, gd, gw, wts_name);
        assert(modelStream != nullptr);
        std::ofstream p(engine_name, std::ios::binary);
        if (!p) {
    
            std::cerr << "could not open plan output file" << std::endl;
            return -1;
        }
        p.write(reinterpret_cast<const char*>(modelStream->data()), modelStream->size());
        modelStream->destroy();
        return 0;
    }

在加载完毕权重之后，建立IHostMemory*类型的变量modelStream，并将构建好的engine保存在本地磁盘之中。

之所以要把engine文件保存在本地，是因为如果每次运行程序之前都要重新制作一遍engine，整个过程将会非常的缓慢。而具体的engine制作工艺的流程就在函数APItoModel之内。因此具体分析一下APItoModel。

void APIToModel(unsigned int maxBatchSize, IHostMemory** modelStream, bool& is_p6, float& gd, float& gw, std::string& wts_name) {
    
    // Create builder
    IBuilder* builder = createInferBuilder(gLogger);
    IBuilderConfig* config = builder->createBuilderConfig();

    // Create model to populate the network, then set the outputs and create an engine
    ICudaEngine *engine = nullptr;
    if (is_p6) {
    
        engine = build_engine_p6(maxBatchSize, builder, config, DataType::kFLOAT, gd, gw, wts_name);
    } else {
    
        engine = build_engine(maxBatchSize, builder, config, DataType::kFLOAT, gd, gw, wts_name);
    }
    assert(engine != nullptr);

    // Serialize the engine
    (*modelStream) = engine->serialize();

    // Close everything down
    engine->destroy();
    builder->destroy();
    config->destroy();
}

APItoModel中的就是engine的一般传统工艺。首先声明IBuilder*类型的builder，后面很多组件都会需要builder来build之。接着声明IBuilderConfig*类型的config，使用builder中的方法createBuilderConfig来创建，顾名思义，就是创建了一个build过程中的配置变量。

然后声明一个ICudaEngine*类型的engine变量。这个变量初始化为空指针即可。

接着就是调用build_engine()函数去创建engine，具体build_engine函数在下面分析。拿到engine后，将其序列化，赋值给*modelStream。engine在序列化后才能够保存到本地。

回到主函数，创建一个std::ofstream的对象p，并用p.write()函数保存modelStream->data()和modelStream->size()，再destroy()modelStream。

回过头来看build_engine()函数。

ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt, float& gd, float& gw, std::string& wts_name) {
    
    INetworkDefinition* network = builder->createNetworkV2(0U);

    // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
    ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{
     3, INPUT_H, INPUT_W });
    assert(data);

    std::map<std::string, Weights> weightMap = loadWeights(wts_name);

    /* ------ yolov5 backbone------ */
    auto focus0 = focus(network, weightMap, *data, 3, get_width(64, gw), 3, "model.0");
    auto conv1 = convBlock(network, weightMap, *focus0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
    auto bottleneck_CSP2 = C3(network, weightMap, *conv1->getOutput(0), get_width(128, gw), get_width(128, gw), get_depth(3, gd), true, 1, 0.5, "model.2");
    auto conv3 = convBlock(network, weightMap, *bottleneck_CSP2->getOutput(0), get_width(256, gw), 3, 2, 1, "model.3");
    auto bottleneck_csp4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(9, gd), true, 1, 0.5, "model.4");
    auto conv5 = convBlock(network, weightMap, *bottleneck_csp4->getOutput(0), get_width(512, gw), 3, 2, 1, "model.5");
    auto bottleneck_csp6 = C3(network, weightMap, *conv5->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(9, gd), true, 1, 0.5, "model.6");
    auto conv7 = convBlock(network, weightMap, *bottleneck_csp6->getOutput(0), get_width(1024, gw), 3, 2, 1, "model.7");
    auto spp8 = SPP(network, weightMap, *conv7->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, 9, 13, "model.8");

    /* ------ yolov5 head ------ */
    auto bottleneck_csp9 = C3(network, weightMap, *spp8->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.9");
    auto conv10 = convBlock(network, weightMap, *bottleneck_csp9->getOutput(0), get_width(512, gw), 1, 1, 1, "model.10");

    auto upsample11 = network->addResize(*conv10->getOutput(0));
    assert(upsample11);
    upsample11->setResizeMode(ResizeMode::kNEAREST);
    upsample11->setOutputDimensions(bottleneck_csp6->getOutput(0)->getDimensions());

    ITensor* inputTensors12[] = {
     upsample11->getOutput(0), bottleneck_csp6->getOutput(0) };
    auto cat12 = network->addConcatenation(inputTensors12, 2);
    auto bottleneck_csp13 = C3(network, weightMap, *cat12->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.13");
    auto conv14 = convBlock(network, weightMap, *bottleneck_csp13->getOutput(0), get_width(256, gw), 1, 1, 1, "model.14");

    auto upsample15 = network->addResize(*conv14->getOutput(0));
    assert(upsample15);
    upsample15->setResizeMode(ResizeMode::kNEAREST);
    upsample15->setOutputDimensions(bottleneck_csp4->getOutput(0)->getDimensions());

    ITensor* inputTensors16[] = {
     upsample15->getOutput(0), bottleneck_csp4->getOutput(0) };
    auto cat16 = network->addConcatenation(inputTensors16, 2);

    auto bottleneck_csp17 = C3(network, weightMap, *cat16->getOutput(0), get_width(512, gw), get_width(256, gw), get_depth(3, gd), false, 1, 0.5, "model.17");

    /* ------ detect ------ */
    IConvolutionLayer* det0 = network->addConvolutionNd(*bottleneck_csp17->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{
     1, 1 }, weightMap["model.24.m.0.weight"], weightMap["model.24.m.0.bias"]);
    auto conv18 = convBlock(network, weightMap, *bottleneck_csp17->getOutput(0), get_width(256, gw), 3, 2, 1, "model.18");
    ITensor* inputTensors19[] = {
     conv18->getOutput(0), conv14->getOutput(0) };
    auto cat19 = network->addConcatenation(inputTensors19, 2);
    auto bottleneck_csp20 = C3(network, weightMap, *cat19->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.20");
    IConvolutionLayer* det1 = network->addConvolutionNd(*bottleneck_csp20->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{
     1, 1 }, weightMap["model.24.m.1.weight"], weightMap["model.24.m.1.bias"]);
    auto conv21 = convBlock(network, weightMap, *bottleneck_csp20->getOutput(0), get_width(512, gw), 3, 2, 1, "model.21");
    ITensor* inputTensors22[] = {
     conv21->getOutput(0), conv10->getOutput(0) };
    auto cat22 = network->addConcatenation(inputTensors22, 2);
    auto bottleneck_csp23 = C3(network, weightMap, *cat22->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.23");
    IConvolutionLayer* det2 = network->addConvolutionNd(*bottleneck_csp23->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{
     1, 1 }, weightMap["model.24.m.2.weight"], weightMap["model.24.m.2.bias"]);

    auto yolo = addYoLoLayer(network, weightMap, "model.24", std::vector<IConvolutionLayer*>{
    det0, det1, det2});
    yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
    network->markOutput(*yolo->getOutput(0));

    // Build engine
    builder->setMaxBatchSize(maxBatchSize);
    config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
#if defined(USE_FP16)
    config->setFlag(BuilderFlag::kFP16);
#elif defined(USE_INT8)
    std::cout << "Your platform support int8: " << (builder->platformHasFastInt8() ? "true" : "false") << std::endl;
    assert(builder->platformHasFastInt8());
    config->setFlag(BuilderFlag::kINT8);
    Int8EntropyCalibrator2* calibrator = new Int8EntropyCalibrator2(1, INPUT_W, INPUT_H, "./coco_calib/", "int8calib.table", INPUT_BLOB_NAME);
    config->setInt8Calibrator(calibrator);
#endif

    std::cout << "Building engine, please wait for a while..." << std::endl;
    ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
    std::cout << "Build engine successfully!" << std::endl;

    // Don't need the network any more
    network->destroy();

    // Release host memory
    for (auto& mem : weightMap)
    {
    
        free((void*)(mem.second.values));
    }

    return engine;
}

这个函数很明显是在手写YOLOv5的network结构。首先先声明INetworkDefinition*类型的变量network，此处也是需要使用builder->createNetworkV2()来创建。再创建网络的输入张量，即声明ITensor*类型的data变量，由network->addInput来创建即可。这个输入张量需要在函数中指定输入张量的大小。

接下来就是定义YOLOv5的各个层。自定义层稍后做分析。

网络搭建完成后，通过builder->setMaxBatchSize()设置最大Batch的大小，再使用config->setMaxWorkspaceSize()设置每一层在实现时最大需要多少临时工作空间。最后使用config->setFlag设置推理的数据类型，一般设置成kFP16，不少平台不支持int8。

设置完毕后，在builder中调用builder->buildEngineWithConfig(*network, *config);即可完成engine的创建，再将netwok销毁，并释放内存空间。