🎉 Support C++ for End2end

README.md

@@ -5,7 +5,7 @@
 YOLOv7、YOLOv6、 YOLOX、 YOLOV5
 
 ## Update 
-- 2022.8.13 rename reop public new version
+- 2022.8.13 rename reop、 public new version、 **C++ for end2end**
 - 2022.8.11 nms plugin support ==> Now you can set --end2end flag while use `export.py` get a engine file  
 - 2022.7.8 support YOLOV7 
 - 2022.7.3 support TRT int8  post-training quantization 
@@ -32,23 +32,10 @@ show in `Examples.ipynb` <a href="https://github.com/Linaom1214/TensorRT-For-YOL
 
 ### C++ 
 
-Now C++ don`t support model with nms plugin
-
-Edit code 
-```c++
-static const int INPUT_W = 640;
-static const int INPUT_H = 640;
-const char* INPUT_BLOB_NAME = "image_arrays";
-const char* OUTPUT_BLOB_NAME = "outputs";
-```
+support **NMS plugin**
+show in [C++ Demo](cpp/README.MD)
 
 
-```shell
-cd cpp && mkdir build && build
-cmake ..
-make
-./yolo ../model_trt.engine -i ../*.jpg
-```
 
 ## Old version
 [v0.0.1](https://github.com/Linaom1214/TensorRT-For-YOLO-Series/releases/tag/v0.0.1)

cpp/README.MD

@@ -0,0 +1,37 @@
+## With NMS Plugin
+
+**Edit code for you model**
+
+```c++
+const cv::Size& new_shape = cv::Size(640, 640),
+static const int INPUT_H = 640;
+auto in_dims = engine->getBindingDimensions(engine->getBindingIndex("image_arrays"));
+```
+**run**
+
+```shell
+cd end2end && mkdir build && build
+cmake ..
+make
+./yolo -model_path  engine   -image_path xxx.jpg
+```
+
+
+## Without NMS Plugin
+
+**Edit code for you model**
+
+```c++
+static const int INPUT_W = 640;
+static const int INPUT_H = 640;
+const char* INPUT_BLOB_NAME = "image_arrays";
+const char* OUTPUT_BLOB_NAME = "outputs";
+```
+**run**
+
+```shell
+cd norm && mkdir build && build
+cmake ..
+make
+./yolo ../model_trt.engine -i ../*.jpg
+```

cpp/end2end/CMakeLists.txt

@@ -0,0 +1,34 @@
+cmake_minimum_required(VERSION 2.6)
+
+project(yolo)
+
+add_definitions(-std=c++11)
+
+option(CUDA_USE_STATIC_CUDA_RUNTIME OFF)
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_BUILD_TYPE Debug)
+# add_definitions("-Wall -g")
+find_package(CUDA REQUIRED)
+
+include_directories(${PROJECT_SOURCE_DIR}/include)
+# include and link dirs of cuda and tensorrt, you need adapt them if yours are different
+# cuda
+include_directories(/usr/local/cuda/include)
+link_directories(/usr/local/cuda/lib64)
+# tensorrt
+include_directories(/usr/include/x86_64-linux-gnu/)
+link_directories(/usr/lib/x86_64-linux-gnu/)
+
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11 -Wall -Ofast -Wfatal-errors -D_MWAITXINTRIN_H_INCLUDED")
+
+find_package(OpenCV)
+include_directories(${OpenCV_INCLUDE_DIRS})
+
+add_executable(yolo ${PROJECT_SOURCE_DIR}/main.cpp)
+target_link_libraries(yolo nvinfer)
+target_link_libraries(yolo nvinfer_plugin)
+target_link_libraries(yolo cudart)
+
+target_link_libraries(yolo ${OpenCV_LIBS})
+
+add_definitions(-O2 -pthread)