{"id":462,"date":"2020-07-25T20:19:21","date_gmt":"2020-07-25T10:19:21","guid":{"rendered":"https:\/\/www.samontab.com\/web\/?p=462"},"modified":"2020-07-25T20:19:21","modified_gmt":"2020-07-25T10:19:21","slug":"minimal-install-of-openvino-2020-4-in-kubuntu-20-04-lts-for-c-inference-on-cpu","status":"publish","type":"post","link":"https:\/\/www.samontab.com\/web\/2020\/07\/minimal-install-of-openvino-2020-4-in-kubuntu-20-04-lts-for-c-inference-on-cpu\/","title":{"rendered":"Minimal install of OpenVINO 2020.4 in Kubuntu 20.04 LTS for C++ inference on CPU"},"content":{"rendered":"\n
\n

The official installer of OpenVINO 2020.4 requires Ubuntu 18.04 LTS<\/a>, but since Kubuntu 20.04 LTS is already out I wanted to use that instead. Here’s what you need to do to get a minimal install for C++ inference on the CPU.<\/p>\n\n\n\n

First make sure you have everything up to date:<\/p>\n<\/div><\/div>\n\n\n

\nsudo apt-get update\nsudo apt-get upgrade\n<\/pre><\/div>\n\n\n
You’ll need git installed to get the source code. Also, python3 comes already pre-installed with 20.04 but not python, so we’re going to assign any python calls to python3.<\/p>\n\n\n
\nsudo apt-get install git python-is-python3\n<\/pre><\/div>\n\n\n
Now get the OpenVINO source code into your home directory (or wherever you prefer). Don’t download the zip file directly from github as there are some 3rd party dependencies that need to get downloaded as well. That’s the –recursive<\/strong> part of the following command. The specific –branch<\/strong> we’re using is the same as the official installer uses, releases\/2020\/4<\/strong>.<\/p>\n\n\n
\ncd ~\ngit clone --recursive --branch releases\/2020\/4 https:\/\/github.com\/openvinotoolkit\/openvino.git\n<\/pre><\/div>\n\n\n
Install the dependencies by running the included script:<\/p>\n\n\n
\n~\/openvino\/install_dependencies.sh\n<\/pre><\/div>\n\n\n
Before continuing you need to change some of the files you just downloaded. I’m using xdg-open<\/em> which will invoke your preferred application but you can use whatever you prefer instead like vi, nano, etc.<\/p>\n\n\n\n
First open up the gna_helper.cpp<\/strong> file. <\/p>\n\n\n
\nxdg-open ~\/openvino\/inference-engine\/src\/gna_plugin\/gna_helper.cpp\n<\/pre><\/div>\n\n\n
Update the code for these functions as follows:<\/p>\n\n\n
\nvoid profilerRtcStart(intel_gna_profiler_rtc *p) {\n    if (nullptr == p) return;\n    clearTimeB(p->passed);\n    clearTimeB(p->stop);\n    \/\/ftime(&amp;p->start);\n    timespec start;\n    clock_gettime(CLOCK_REALTIME, &amp;start);\n    p->start.time = start.tv_sec;\n    p->start.millitm = start.tv_nsec\/1000000;\n}\n\nvoid profilerRtcStop(intel_gna_profiler_rtc *p) {\n    if (nullptr == p) return;\n    \/\/ftime(&amp;p->stop);\n    timespec stop;\n    clock_gettime(CLOCK_REALTIME, &amp;stop);\n    p->stop.time = stop.tv_sec;\n    p->stop.millitm = stop.tv_nsec\/1000000;\n}\n\n<\/pre><\/div>\n\n\n
Now open the execution_engine.cpp<\/strong> file:<\/p>\n\n\n
\nxdg-open ~\/openvino\/inference-engine\/thirdparty\/ade\/sources\/ade\/source\/execution_engine.cpp\n<\/pre><\/div>\n\n\n
In line 141, simply update this:<\/p>\n\n\n
\n\/\/return std::move(ret);\nreturn ret;\n<\/pre><\/div>\n\n\n
Now you’re ready to build it.  And this will take a long time.<\/p>\n\n\n\n