[YOLO] - YoloV4 개발환경 셋팅

*Ubuntu : 18.04

*CUDA : 10.2.89

*CUDNN : 8.2.1

 

기존 OpenCV 제거

sudo apt-get remove libopencv*
sudo apt-get autoremove
sudo find /usr/local/ -name "*opencv*" -exec rm {} \;

 

Update & Upgrade

sudo apt-get update
sudo apt-get upgrade

 

개발자 도구 설치

sudo apt-get install build-essential cmake unzip pkg-config

 

libraries 설치

sudo apt-get install libjpeg-dev libpng-dev libtiff-dev
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev v4l-utils libxvidcore-dev libx264-dev libxine2-dev
sudo apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev
sudo apt-get install libgtk-3-dev
sudo apt-get install mesa-utils libgl1-mesa-dri libgtkgl2.0-dev libgtkglext1-dev
sudo apt-get install libatlas-base-dev gfortran libeigen3-dev

 

Python 설치

sudo apt-get install python2.7-dev python3-dev python-numpy python3-numpy

 

---

 

OpenCV 3.4.0 설치

mkdir opencv
cd opencv
wget -O opencv.zip https://github.com/opencv/opencv/archive/3.4.0.zip
wget -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/3.4.0.zip

unzip opencv.zip
unzip opencv_contrib.zip

 

cd opencv-3.4.0
mkdir build
cd build

cmake -D CMAKE_BUILD_TYPE=RELEASE \ 
-D BUILD_opencv_cudacodec=OFF \ 
-D CMAKE_INSTALL_PREFIX=/usr/local \ 
-D WITH_TBB=OFF \ -D WITH_IPP=OFF \ 
-D WITH_1394=OFF \ 
-D BUILD_WITH_DEBUG_INFO=OFF \ 
-D BUILD_DOCS=OFF \ 
-D INSTALL_C_EXAMPLES=ON \ 
-D INSTALL_PYTHON_EXAMPLES=ON \ 
-D BUILD_EXAMPLES=OFF \ 
-D BUILD_TESTS=OFF \ 
-D BUILD_PERF_TESTS=OFF \ 
-D WITH_QT=OFF \ 
-D WITH_GTK=ON \ 
-D WITH_OPENGL=ON \ 
-D OPENCV_EXTRA_MODULES_PATH=../../opencv_contrib-3.4.0/modules \ 
-D WITH_V4L=ON \ 
-D WITH_FFMPEG=ON \ 
-D WITH_XINE=ON \ 
-D BUILD_NEW_PYTHON_SUPPORT=ON \ 
-D PYTHON2_INCLUDE_DIR=/usr/include/python2.7 \ 
-D PYTHON2_NUMPY_INCLUDE_DIRS=/usr/lib/python2.7/dist-packages/numpy/core/include/ \ 
-D PYTHON2_PACKAGES_PATH=/usr/lib/python2.7/dist-packages \ 
-D PYTHON2_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython2.7.so \ 
-D PYTHON3_INCLUDE_DIR=/usr/include/python3.6m \ 
-D PYTHON3_NUMPY_INCLUDE_DIRS=/usr/lib/python3/dist-packages/numpy/core/include/ \ 
-D PYTHON3_PACKAGES_PATH=/usr/lib/python3/dist-packages \ 
-D PYTHON3_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython3.6m.so \ 
../

(libprotobuf 오류시에 "-DBUILD_opencv_cudacodec=OFF" 추가)

 

make -j16

(cpu 코어 수 체크 : cat /proc/cpuinfo | grep processor | wc -l)

 

sudo make install
sudo sh -c echo '/usr/local/lib/' > sudo /etc/ld.so.conf.d/opencv.conf
sudo ldconfig

 

---

 

YoloV4 설치

git clone https://github.com/AlexeyAB/darknet.git

 

Makefile 수정

GPU=1 
CUDNN=1 
CUDNN_HALF=1 
OPENCV=1 
AVX=0 
OPENMP=0 
LIBSO=1

 

darknet make 실행

make

 

weights 파일 다운

yolov4.weights :

https://drive.google.com/file/d/1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT/view

yolov4.weights

 

Test

./darknet detect cfg/yolov4.cfg yolov4.weights data/dog.jpg

 

 

 

*참조

https://keyog.tistory.com/21

Ubuntu 18.04 에서 Yolo v4 설치하기