Skip to content

System Requirements#

Windows OS installations#

We support 64-bit versions of the following operating systems:

Desktop/workstation environment:

  • Windows 7 or newer is required. Older versions are not supported.

Server environment:

  • Windows Server 2008r2 or newer is required. Older versions are not supported.

Supported compiler:

  • Visual Studio 2015 update 4. Other compilers may work but were not tested.

Note 1: 32-bit version of Windows is also supported, but with restricted capabilities.

Note 2: FaceEngine requires a 64-bit version of Visual C++ Redistributable for Visual Studio 2015 to operate. The redistributable installer may be obtained from Microsoft via this link: [https://www.microsoft.com/en-us/download/details.aspx?id=48145]{.underline}

Linux OS installations#

We support the following operating systems:

  • CentOS 7.2 64-bit;
  • Ubuntu 1804 LTS 64-bit.

Supported compilers:

  • GCC4.x. Minimum version: 4.8.4. Versions 4.9.x are also supported. Version 5 and newer are not supported. Other compilers may work but were not tested.

Note 1: 32-bit OS on x86_64 CPU are not supported.

Note 2: your OS should run glibc version 2.17 (CentOS) or 2.19 (Ubuntu), or newer.

Note 3: system locale must be US English. Specifically LC_NUMERIC=en_US.UTF-8.

NVIDIA Jetson installations#

FaceEngine requires:

  • Ubuntu 16.04.6 LTS (Xenial Xerus)

For development:

  • L4T 28.2.1 [ JetPack 3.3 | 3.2.1 ]

Requirements for GPU acceleration#

Recomended versions of CUDA

The most current version of these release notes can be found online at http://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html.

Cuda version on Linux can be found using command below:

$nvidia-smi

Cuda version on Windows can be found in Control Panel\Programs\Programs and Features as in fugure below

CUDA version on Win
CUDA version on Win

Note: We recommend to use suggested version of CUDA for your operating system. But if your version is older than required, we can't give guaranties, that it will work successfuly. More detials about CUDA Compatibility, can be found online at https://docs.nvidia.com/deploy/cuda- compatibility/index.html.

Web-based installations#

A decent browser with ASM.js support is required. The following browsers are supported:

  • Chrome 54+;
  • Firefox 48+;
  • Microsoft Edge (Windows 10 build 14393+).

Note: Internet Explorer is not supported.

Hardware requirements#

Server / PC installations#

CPU requirements#

CPU should support at least the SSE4.2 instruction set. For the best performance, AVX2 instruction set support is highly recommended. Note, that only 64-bit CPUs are supported.

If in doubt, consider checking your CPU specifications at the following websites:

FaceEngine was primarily tested on 5th gen. Intel(R) Xeon(R) CPUs (ex. "Broadwell").

GPU requirements#

For GPU acceleration an NVIDIA GPU is required. The following architectures are supported:

  • Pascal or newer.

A minimum of 6GB or dedicated video RAM is required. 8 GB or more VRAM recommended.

The number of actually created threads while using a GPU#

The total number of threads can be calculated by such expression: 

totalNumberOfThreads = numThreads + 2*numGpuDevices + 1 (and 1 optional),

where

  • numThreads is the value of setting <param name="numThreads" type="Value::Int1" x="12" />. Description can be found in "Configuration Guide - Runtime settings";
  • numGpuDevices is the number of GPU devices;
  • One of threads for CUDA in runtime;
  • And besides 1 optional thread depending on internal settings LUNA-SDK API;

Example: if numThreads==4 and there are 2 GPU devices in system the total number of threads will be 9 where 4 - are numThreads, 2 + 2 for every GPU and 1 thread for CUDA.

For decreasing of threads number can be set the environment variable CUDA_VISIBLE_DEVICES=-1.

RAM requirements#

System memory consumption differs depending on a usage scenario and is proportional to the number of worker threads. This is true for both CPU (think system RAM) and GPU (think VRAM) execution modes.

For example, in CPU execution mode 1GB RAM is enough for a typical pipeline, which consists of a face detector and a face descriptor extractor running on a single core (one worker thread) and processing 1080p input images with 10-12 faces on average. If this setup is scaled up to 8 worker threads, overall memory consumption grows up to 8GB.

It is recommended to assume at least 1GB of free RAM per worker thread.

Storage requirements#

FaceEngine requires 1GB of free space to install. This includes model data for both CPU and GPU execution modes that should be redistributed with your application. If only one execution mode is planned, reduce space requirements by half.

Embedded installations#

CPU requirements#

Supported CPU architectures:

  • ARMv7-A;
  • ARMv8-A (ARM64).
Back to top