yolov7 trt files with multiprocessing

yolov7/CMakeLists.txt

+cmake_minimum_required(VERSION 2.6)
+
+project(yolov7)
+
+add_definitions(-std=c++11)
+add_definitions(-DAPI_EXPORTS)
+option(CUDA_USE_STATIC_CUDA_RUNTIME OFF)
+set(CMAKE_CXX_STANDARD 11)
+set(CMAKE_BUILD_TYPE Debug)
+
+find_package(CUDA REQUIRED)
+
+if(WIN32)
+enable_language(CUDA)
+endif(WIN32)
+
+include_directories(${PROJECT_SOURCE_DIR}/include)
+# include and link dirs of cuda and tensorrt, you need adapt them if yours are different
+
+
+if (CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64")
+    message("embed_platform on")
+    include_directories(/usr/local/cuda/targets/aarch64-linux/include)
+    link_directories(/usr/local/cuda/targets/aarch64-linux/lib)
+else()
+    message("embed_platform off")
+    # cuda
+    include_directories(/usr/local/cuda/include)
+    link_directories(/usr/local/cuda/lib64)
+
+    # tensorrt
+    include_directories(/home/na/TensorRT-7.2.2.3/include)
+    link_directories(/home/na/TensorRT-7.2.2.3/lib)
+endif()
+
+
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11 -Wall -Ofast -g -Wfatal-errors -D_MWAITXINTRIN_H_INCLUDED")
+cuda_add_library(myplugins SHARED yololayer.cu)
+target_link_libraries(myplugins nvinfer cudart)
+
+find_package(OpenCV)
+include_directories(${OpenCV_INCLUDE_DIRS})
+
+cuda_add_executable(yolov7 calibrator.cpp yolov7.cpp preprocess.cu)
+
+target_link_libraries(yolov7 nvinfer)
+target_link_libraries(yolov7 cudart)
+target_link_libraries(yolov7 myplugins)
+target_link_libraries(yolov7 ${OpenCV_LIBS})
+
+if(UNIX)
+add_definitions(-O2 -pthread)
+endif(UNIX)
+
+

yolov7/Dockerfile

+FROM nvcr.io/nvidia/l4t-pytorch:r32.5.0-pth1.7-py3
+
+RUN apt-get update
+RUN apt install tzdata ffmpeg libsm6 libxext6 -y
+
+RUN python3 -m pip install --upgrade pip
+RUN python3 -m pip install scipy==1.5.4
+ADD . /app
+WORKDIR /app
+RUN COPY /home/ilens/tensorrtx/yolov7/traffic1.mp4 .
+RUN COPY /home/ilens/tensorrtx/yolov7/traffic2.mp4 .
+RUN python3 -m pip install -r requirements.txt
+
+CMD ["python3","yolov7_multiprocessing_videos.py"]
+

yolov7/Dockerfile.save

+	FROM nvcr.io/nvidia/l4t-pytorch:r32.5.0-pth1.7-py3 RUN apt-get update RUN apt install tzdata ffmpeg libsm6 libxext6 -y RUN python3 -m pip 
+install --upgrade pip RUN python3 -m pip install scipy==1.5.4 ADD . /app WORKDIR /app RUN python3 -m pip install -r requirements.txt CMD 
+["python3","app.py"]

yolov7/README.md

+# yolov7
+
+The Pytorch implementation is [WongKinYiu/yolov7](https://github.com/WongKinYiu/yolov7).
+
+The tensorrt code is derived from [QIANXUNZDL123/tensorrtx-yolov7](https://github.com/QIANXUNZDL123/tensorrtx-yolov7)
+
+## Different versions of yolov7
+
+Currently, we support yolov7 v0.1
+
+- For yolov7 v0.1, download .pt from [yolov7 release v0.1](https://github.com/WongKinYiu/yolov7/releases/tag/v0.10), then follow how-to-run in current page.
+
+
+## Config
+
+- Choose the model tiny/v7/x/d6/w6/e6/e6e from command line arguments.
+- Input shape defined in yololayer.h
+- Number of classes defined in yololayer.h, **DO NOT FORGET TO ADAPT THIS, If using your own model**
+- INT8/FP16/FP32 can be selected by the macro in yolov7.cpp, **INT8 need more steps, pls follow `How to Run` first and then go the `INT8 Quantization` below**
+- GPU id can be selected by the macro in yolov7.cpp
+- NMS thresh in yolov7.cpp
+- BBox confidence thresh in yolov7.cpp
+- Batch size in yolov7.cpp
+
+## How to Run, yolov7-tiny as example
+
+1. generate .wts from pytorch with .pt, or download .wts from model zoo
+
+```
+// download https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
+cp {tensorrtx}/yolov7/gen_wts.py {WongKinYiu}/yolov7
+cd {WongKinYiu}/yolov7
+python gen_wts.py
+// a file 'yolov7.wts' will be generated.
+```
+
+2. build tensorrtx/yolov7 and run
+
+```
+cd {tensorrtx}/yolov7/
+// update CLASS_NUM in yololayer.h if your model is trained on custom dataset
+mkdir build
+cd build
+cp {WongKinYiu}/yolov7/yolov7.wts {tensorrtx}/yolov7/build
+cmake ..
+make
+sudo ./yolov7 -s [.wts] [.engine] [t/v7/x/w6/e6/d6/e6e gd gw]  // serialize model to plan file
+sudo ./yolov7 -d [.engine] [image folder]  // deserialize and run inference, the images in [image folder] will be processed.
+// For example yolov7
+sudo ./yolov7 -s yolov7.wts yolov7.engine v7
+sudo ./yolov7 -d yolov7.engine ../samples
+```
+
+3. check the images generated, as follows. _zidane.jpg and _bus.jpg
+
+4. optional, load and run the tensorrt model in python
+
+```
+// install python-tensorrt, pycuda, etc.
+// ensure the yolov7.engine and libmyplugins.so have been built
+python yolov7_trt.py
+```
+
+# INT8 Quantization
+
+1. Prepare calibration images, you can randomly select 1000s images from your train set. For coco, you can also download my calibration images `coco_calib` from [GoogleDrive](https://drive.google.com/drive/folders/1s7jE9DtOngZMzJC1uL307J2MiaGwdRSI?usp=sharing) or [BaiduPan](https://pan.baidu.com/s/1GOm_-JobpyLMAqZWCDUhKg) pwd: a9wh
+
+2. unzip it in yolov7/build
+
+3. set the macro `USE_INT8` in yolov7.cpp and make
+
+4. serialize the model and test
+
+<p align="center">
+<img src="https://user-images.githubusercontent.com/15235574/78247927-4d9fac00-751e-11ea-8b1b-704a0aeb3fcf.jpg">
+</p>
+
+<p align="center">
+<img src="https://user-images.githubusercontent.com/15235574/78247970-60b27c00-751e-11ea-88df-41473fed4823.jpg">
+</p>
+
+## More Information
+
+See the readme in [home page.](https://github.com/wang-xinyu/tensorrtx)