yolov5模型在推理阶段出现 assert(engine-＞getNbBindings() == 2

int main(int argc, char** argv) { cudaSetDevice(DEVICE); std::string wts_name = ""; std::string engine_name = ""; bool is_p6 = false; float gd = 0.0f, gw = 0.0f; //std::string img_dir; if (!parse_args(argc, argv, wts_name, engine_name, is_p6, gd, gw)) { std::cerr << "arguments not right!" << std::endl; std::cerr << "./yolov5_det -s [.wts] [.engine] [n/s/m/l/x/n6/s6/m6/l6/x6 or c/c6 gd gw] // serialize model to plan file" << std::endl; std::cerr << "./yolov5_det -d [.engine] ../samples // deserialize plan file and run inference" << std::endl; return -1; } // create a model using the API directly and serialize it to a stream 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; } // deserialize the .engine and run inference std::ifstream file(engine_name, std::ios::binary); if (!file.good()) { std::cerr << "read " << engine_name << " error!" << std::endl; return -1; } char *trtModelStream = nullptr; size_t size = 0; file.seekg(0, file.end); size = file.tellg(); file.seekg(0, file.beg); trtModelStream = new char[size]; assert(trtModelStream); file.read(trtModelStream, size); file.close(); // std::vector<std::string> file_names; // if (read_files_in_dir(img_dir.c_str(), file_names) < 0) { // std::cerr << "read_files_in_dir failed." << std::endl; // return -1; // } static float prob[BATCH_SIZE * OUTPUT_SIZE]; IRuntime* runtime = createInferRuntime(gLogger); assert(runtime != nullptr); ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size); assert(engine != nullptr); IExecutionContext* context = engine->createExecutionContext(); assert(context != nullptr); delete[] trtModelStream; assert(engine->getNbBindings() == 2); float* buffers[2]; // In order to bind the buffers, we need to know the names of the input and output tensors. // Note that indices are guaranteed to be less than IEngine::getNbBindings() const int inputIndex = engine->getBindingIndex(INPUT_BLOB_NAME); const int outputIndex = engine->getBindingIndex(OUTPUT_BLOB_NAME); assert(inputIndex == 0); assert(outputIndex == 1); // Create GPU buffers on device CUDA_CHECK(cudaMalloc((void**)&buffers[inputIndex], BATCH_SIZE * 3 * INPUT_H * INPUT_W * sizeof(float))); CUDA_CHECK(cudaMalloc((void**)&buffers[outputIndex], BATCH_SIZE * OUTPUT_SIZE * sizeof(float))); // Create stream cudaStream_t stream; CUDA_CHECK(cudaStreamCreate(&stream)); uint8_t* img_host = nullptr; uint8_t* img_device = nullptr; // prepare input data cache in pinned memory CUDA_CHECK(cudaMallocHost((void**)&img_host, MAX_IMAGE_INPUT_SIZE_THRESH * 3)); // prepare input data cache in device memory CUDA_CHECK(cudaMalloc((void**)&img_device, MAX_IMAGE_INPUT_SIZE_THRESH * 3)); cv::VideoCapture capture("/media/builderx/UUI/tsy_work/rb002/REC/2024_01_17T14_46_37__stream0.mp4"); //cv::VideoCapture capture(0); cv::Mat frame; int fcount = 0;帮我分析一下每行代码都是什么意思

void Create(LinkList &Head, int score, int rank, int sex, char name[], char college[], char item[]) { LinkNode *p = Head->next, *s; //如果链表为空，则做初始化链表 if (p == NULL) { s = (LinkNode *)malloc(sizeof(LinkNode)); assert(s != NULL); s->score = score; s->rank = rank; s->sex = sex; strcpy(s->name, name); strcpy(s->college, college); strcpy(s->item, item); s->next = NULL; Head->next = s; } else { while (p->next != NULL) { p = p->next; } s = (LinkNode *)malloc(sizeof(LinkNode)); assert(s != NULL); s->score = score; s->rank = rank; s->sex = sex; strcpy(s->name, name); strcpy(s->college, college); strcpy(s->item, item); s->next = NULL; p->next = s; } }