System requirements

Supported operating systems

Operating system	Architecture	Recommended version
Windows	x86-64	10
Linux	x86-64	Ubuntu 18.04
	arm-32	Ubuntu 18.04
	arm-64	jetpack 4.4
Android	arm-32	api 21 - 34
	arm-64	api 23 - 34
iOS	arm-64	12 - 17.1

Available APIs

• C++ API (for Windows, Linux, Android, iOS)
• Java wrapper (for Windows, Linux, Android)
• C# wrapper (for Windows, Linux)
• Python wrapper (for Windows, Linux)
• Swift API (for iOS)
• Kotlin wrapper (for Android)
• Flutter plugin (for iOS, Android)
• Javascript

note

See more details here

Hardware recommendations

The following hardware configuration recommended to achieve best performance*.

Desktop PCs (x86 64-bit CPU):

• CPU Intel Core i7-7700K @ 4.20GHz (4 Cores);
• 8 GB RAM;

* Based on the result of test on the FullHD (1920x1080) video stream with no more than 5 faces in the frame using method12v100_recognizer.xml recognition method.

Android (ARM 64-bit CPU):

• CPU Qualcomm Snapdragon 821 @ 2.15 GHz (4 Cores);
• 4 GB RAM;

* Based on the result of test on the VGA (640x480) video stream with 1 face in the frame using method12v30_recognizer.xml recognition methods.

Required dependencies

For Windows:

• sense4.dll. This library is located in the bin folder of
  distribution package. If you change the default location, the library must be placed next to facerec.dll.
• (64-bit): Microsoft Visual C++ Redistributable for Visual Studio 2019

For Linux:

• libusb-0.1.so.4

GPU acceleration

CUDA

Supported platforms:

• Windows x86 64-bit
• Linux x86 64-bit
• Linux aarch64

System requirements:

• CUDA Toolkit 11.0 ≤ vs < 12
• cuDNN v8.8.0 for CUDA 11.x

• Windows

  • Nvidia GPU Driver >= 512.15
  • Microsoft Visual C++ Redistributable for Visual Studio 2019

• Linux

  • Nvidia GPU Driver >= 510.39.01

Hardware requirements:

• GPU with CUDA support (NVIDIA GTX 1050 Ti or better)

TensorRT

Supported platforms:

• Windows x86 64-bit
• Linux x86 64-bit

System requirements:

• CUDA Toolkit 11.0 ≤ vs < 12
• cuDNN v8.8.0 for CUDA 11.x
• TensorRT 10.2

• Windows
  • Nvidia GPU Driver >= 536.67
  • Microsoft Visual C++ Redistributable for Visual Studio 2019
• Linux
  • Nvidia GPU Driver >= 535.54.03

Hardware requirements:

• GPU with CUDA support (NVIDIA GTX 1650 Ti or better)

CPU acceleration

OpenVINO

To accelerate model execution on CPUs, Face SDK now supports integration with OpenVINO — a high-performance toolkit from Intel optimized for neural network inference on Intel processors.

Supported platforms

• Windows: windows-x86-64
• Linux: linux-x86-64

CPU requirements

• 64-bit architecture (x86_64)
• AVX2 instruction set support (required for basic functionality)
• VNNI — optional, for additional acceleration

API Requirements

C#

• .Net 8 ≤ version

Python

• 3.6 ≤ version ≤ 3.12

Flutter

• Flutter 3.27.0 ≤ version ≤ 3.27.3
• Dart 3.6.0 ≤ version ≤ 3.6.1

Go

• 1.22 ≤ version