Deploy FindFace Server
Docker platform
FindFace Server is distributed using Docker images and is intended to be run using Docker-compatible execution environment (i.e. Docker, Podman, Docker Swarm or Kubernetes). You must install and start a set of Docker products before proceeding with the FindFace Server deployment. For your convenience, this chapter contains the Ubuntu Server Preparation section covering the intricacies of installing Docker on Ubuntu. For other platforms, please refer to the Docker documentation. On modern RedHat systems, you can substitute Docker with Podman, but you will need to refer to official NVIDIA docs if you intend to use GPU-acceleration with Podman.
NVIDIA driver and NVIDIA Container Runtime (GPU only)
If you intend to deploy FindFace Server with GPU-acceleration, you need to install the NVIDIA driver and NVIDIA Container Runtime. Again, you will find the relevant information in the Ubuntu Server Preparation section.
Deployment
After you are finished with the server preparation, you are all set for the FindFace Server deployment. Each FindFace Server component is deployed step-by-step using the docker platform. It requires fundamental understanding of the product architecture. Specify environment variables. If needed, make changes to the configuration file of the required component and restart the container.
Deploying FindFace Server standalone. See Deploy Components for guidance.
Deploying FindFace Server in a multi-host environment. It requires a bit of technical expertise and knowledge of the product architecture.
Note
Keep in mind to install necessary neural network models along with the video-worker-cpu / video-worker-gpu and extraction-api-cpu / extraction-api-gpu components and enable them in corresponding configuration file.
Post-deployment procedures and how-to’s
Browse through the Post-deployment Procedures and How-to’s section to learn how to license your instance, and configure logging. This section will also provide you with few basic commands that will help you to kick-start your work with FindFace Server containers, in case you are a newbie with Docker.
Important
Starting the GPU-accelerated services extraction-api-gpu and video-worker-gpu for the first time after deployment may take a considerable amount of time due to the caching process (up to 45 minutes).
Important
FindFace Server does not include any means of access control and completely relies on surrounding network and cluster infrastructure to provide access control and authentication. You should avoid uncontrollably exposing FindFace Server components ports to untrusted networks without reverse proxies implementing some form of authorization or strict firewall policies.
Instance removal
To remove your instance, you must run a set of commands. See the Remove FindFace Server Instance section.