This section will guide you through the FindFace Server step-by-step installation process. Follow the instructions below minding the sequence.
In this section:
FindFace Enterprise Server SDK can be installed from a local repository. You can receive the FindFace Enterprise Server SDK distributable packages from your NTechLab manager. To prepare the packages for installation, do the following:
Unpack the package with components on each designated host.
sudo dpkg -i <findface-repo>.deb
Add a signature key on each designated host.
sudo apt-key add /var/findface-repo/public.key sudo apt-get update
Unpack the packages with models (face, gender, age, and emotions). In the cluster environment, models are installed only on the
sudo dpkg -i findface-data*
FindFace Enterprise Server is licensed by the following criteria:
- The number of biometric samples extracted from faces detected in static images and videos.
- The number of cameras in use.
- The number of
findface-extraction-apimodel instances in use.
- Face features recognition: gender/age/emotions/glasses/beard.
- Face liveness detection.
- Fast index.
You can choose between the online and on-premise (aka offline) licensing:
- Online licensing requires a stable internet connection. Upon being disconnected from the internet, the system will continue working off-grid for about 1 hour.
- On-premise (offline) licensing requires a USB port on the physical server with the
findface-ntlscomponent, that will be used to plug in a provided USB dongle.
To provide the system functioning, one
findface-ntls instance should be enough. If for some reason, your system requires more license servers, contact your Ntech Lab manager beforehand to prevent your system from being blocked.
After you install the FindFace Server components, configure their interaction with each other. Do the following:
sudo vi /etc/findface-facenapi.ini
Uncomment and/or edit the settings to align with your network specifications, substituting the suggested values with actual location:
ffupload_url = 'http://127.0.0.1:3333' mongo_host = '127.0.0.1' extraction_api_url = 'http://127.0.0.1:18088' tntapi_servers_file = '/etc/tntapi.json'
findface-facenapi.inicontent must be correct Python code.
Do not specify
findface-uploadcomponent is not installed.
By default, if one or several tntapi shards are out of service during face identification, findface-facenapi returns an error. If necessary, uncomment the
tntapi_ignore_search_errorparameter and assign it
True. In this case
findface-facenapiwill use available
tntapishards to obtain face identification results, indicating the number of available servers vs the total number of servers in the response:
tntapi_ignore_search_errors = True
Restart all the FindFace Enterprise Server SDK services and nginx (for
findface-upload) on the relevant host(s).
sudo service 'findface*' restart sudo service nginx restart
Check the services status. The command will return the services description, status (should be Active), path and running time.
sudo service 'findface*' status sudo service nginx status