Reference:
Pre-requisites: Make sure you already installed CUDA 8, cuDNN v5.1, OpenCV 3.1, Python 3.4. Don’t forget to use python virtualenv.
Installation:
- Use python virtual environment ‘opencv_caffe’
1234567891011teddy@teddy-K43SJ:~$ mkvirtualenv opencv_caffeUsing base prefix '/usr'New python executable in /home/teddy/.virtualenvs/opencv_caffe/bin/python3Also creating executable in /home/teddy/.virtualenvs/opencv_caffe/bin/pythonInstalling setuptools, pip, wheel...done.virtualenvwrapper.user_scripts creating /home/teddy/.virtualenvs/opencv_caffe/bin/predeactivatevirtualenvwrapper.user_scripts creating /home/teddy/.virtualenvs/opencv_caffe/bin/postdeactivatevirtualenvwrapper.user_scripts creating /home/teddy/.virtualenvs/opencv_caffe/bin/preactivatevirtualenvwrapper.user_scripts creating /home/teddy/.virtualenvs/opencv_caffe/bin/postactivatevirtualenvwrapper.user_scripts creating /home/teddy/.virtualenvs/opencv_caffe/bin/get_env_details(opencv_caffe) teddy@teddy-K43SJ:~$
Check python version:
12345(opencv_caffe) teddy@teddy-K43SJ:~$ pythonPython 3.4.3 (default, Nov 17 2016, 01:08:31)[GCC 4.8.4] on linuxType "help", "copyright", "credits" or "license" for more information.>>>