150服务器上配置refinedet环境。相关操作参照
安装虚拟环境命令;https://blog.csdn.net/a493823882/article/details/87888509
首先使用命令:
命令:进入<bash>环境
bash
进入conpy36的虚拟环境:
source activate conpy36
查看本机的cuda和cudnn是
cat /usr/local/cuda/version.txt
- 1. 装python3的依赖项：
sudo apt-get install python3-pip
sudo apt-get install python3-scipy
sudo apt-get install python3-matplotlib
sudo apt-get install python3-skimage
sudo apt-get install python3-dev
sudo apt-get install python3-numpy
sudo apt-get install git cmake build-essential
sudo apt-get install build-essential libgtk2.0-dev libavcodec-dev libavformat-dev libjpeg.dev libtiff4.dev libswscale-dev libjasper-dev
- 2. 编译opencv
1.cd opencv-3.4.3
2.mkdir build
3.cd build
4.cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ..
运行完注意观察是否找到python3
5.make -j4
6.sudo make install
7. sudo vim /etc/ld.so.conf.d/opencv.conf(执行此命令后打开的可能是一个空白的文件，不用管，只需要在文件开始添加/usr/local/lib)
8.保存后执行sudo ldconfig（执行如下命令使得刚才的配置路径生效）
9.测试：终端输入python3, import cv2不报错则说明opencv安装成功
3. 编译Refinedet
1.编译依赖项
1.sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler
2. sudo apt-get install --no-install-recommends libboost-all-dev
3. sudo apt-get install libopenblas-dev liblapack-dev libatlas-base-dev
4. sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
5. sudo apt-get install git cmake build-essential
6. sudo pip3 install protobuf
2.编译caffe
1.cd RefineDet
2.make all -j4
3.make py
3.测试：
1. cd RefineDet/python
2. 终端输入python3，import caffe
4.报错和解决
1. import caffe如果出现类似于 ld libboost_python3.so找不到错误，则采用以下方式解决
1.1cd /usr/lib/aarch64-linux-gnu/
1.2
4.cd Pelee-TensorRT
cmake .
make
cp build/lib/libperson.so ../ actionDemo/so_library_dir/
完成！！！