BitRefine Heads platform requires GPU-enabled HW for the most of the recognition tasks. Currently we support NVIDIA GPU with the driver >r460 and CUDA compute capability 3.5 or higher. You can check the list of CUDA-enabled GPU cards here: https://developer.nvidia.com/cuda-gpus

Due to high flexibility of the recognition platform, and a broad range of tasks it solves, the exact hardware requirements should be reviewed for each particular project.

Reference configuration

Here are examples of system requirement definitions for the typical use cases, which can be used as a basic reference.

2-8 cameras with standard people or vehicle recognition module:

CPU: Intel Core i3
RAM: 8Gb
GPU: NVIDIA GTX 750
OS: Ubuntu 18.04

16-32 cameras with advanced people or vehicle recognition module.

CPU: Intel Core i7
RAM: 16Gb
GPU: NVIDIA RTX 2080
OS: Ubuntu 18.04

Embedded System-on-Module (SoM)

BitRefine Heads can run on small low-power AI systems based on NVIDIA Jetson compute units.

The smallest unit in the Jetson family is Jetson Nano (min 4Gb version). Nvidia Jetson Nano

An industrial computer based on the advanced platform NVIDIA Jetson Xavier NX Nvidia Jetson Nano

This type of HW is ideal, if the task requires centralized collection of structured data from multiple locations with few cameras at each location. Embedded compute units take the role of the Heads, and a regular server or a cloud compute engine takes the role of the Manager.