Closed hazard-10 closed 4 years ago
Please make sure libinference_engine_c_api and libjson_c are installed correctly.
Hi Linxie, Thank you for your reply.
The build-ffmpeg script inside FFVA enables both libinference_engine_c_api and libjson_c options when running ffmpeg's configure script, and the building process has no error. Is that a sign of valid installation of these two libraries , or do I need to install them manually ?
P.S I have libjson.so under multiple directories in /usr/ and libinference_engine_c_api.so under default openvino directory.
please check the ffbuild/config.log to see if there's anything wrong
It turns out to be a missing libjson_c.so. The patch works now. Thanks for the tip !
FYI, In section 4 of getting started guide , when using FFVA on a host machine, the user has to run setup_env.sh under FFmepg-patch/scripts/ in order to try env | grep MODELS_PATH & env | grep VIDEO_EXAMPLES_DIR, which is not mentioned in the guide.
Hello again,
I switched to Ubuntu 16.04 and tried to apply the patches to ffmpeg and the patches don't seem to be applied.
The system is clean as I just installed it over the weekend.
Following Guidance 3.2 Build on a host machine : ALL the required dependencies are successfully installed through apt-get install. I used OpenVino_p20.2.120 version. Excluded Intel-media-sdk. Did not see OpenVX in the optionally-excluded list.
libdrm, libva, & media-sdk, etc are properly installed Clinfo & Vainfo run just fine. Patching process runs without a hitch.
In the final building stage, I used build-ffmpeg-dynamic and disabled librkafka as there is always an error when building its file.
At last, when I checked the installation with ffmepg -filters | grep Inference command, the output only showed ffmpeg default filters without "detect" & "classify".
Any suggestions ?