Page History

Hardware The hardware requirements for the neural analytics (see see General information on neural analytics) are the following:

Some

1. Because of specific features of NVIDIA SDK

specific features allow the

2. , neural analytics

to

3. can work

only on Windows Server 2019 or Windows 10. For neural analytics operation, you may use CPU, GPU NVIDIA, VPU (Intel NCS, Intel HDDL).

4. on GPU only in the operating systems specified in Operating system requirements. 

   Note
   title Attention!
   To connect Intel NCS, insert the device into a USB port and make sure that it is recognized by Windows OS as a USB device with one of the following names: Movidius, Myriad X, or VSC Loopback Device. You can use Intel NCS

may be used with any PC

5. on any computer that meets Axxon One hardware requirements (see Hardware requirements).

6. We

do not

7. don't recommend using more than one Intel NCS device per Server.

You can use several Intel HDDL devices on the Server if they have the same revisions.
8. For Intel HDDL to work correctly with AMD processors, pre-install the OpenVINO™ toolkit version 2019.3.379 (see docs.openvino.ai).

9. Neural analytics can work on the following devices: CPU, Nvidia GPU, VPU (Intel NCS).

10. If CPU or Intel GPU is used to run analytics, the following requirements must

If the detection tool uses CPU or Intel GPU resources, the following requirements should

11. be met:

    1. Supported CPUs:

       1. 6th Generation Intel® Core™ processors and higher

;

12. 1. 1. .

          Note
          title Attention!
          When using a CPU lower than 6th Generation Intel® Core™ processors, the operation of the

detection tool is not

13. 1. 1. detectors isn't guaranteed.

       2. Intel® Xeon® v5 family
;
14. 1. 1. and Intel® Xeon® v6 family
;
15. 1. 1. .
       2. Intel® Movidius™ Neural Compute Stick
;
16. 1. 1. .
       2. Intel® Neural Compute Stick 2
;
17. 1. 1. .
       2. Intel® Vision Accelerator Design with Intel® Movidius™ VPUs.
    2. OpenVino
should
18. 1. must support the Intel CPU
in
19. 1. that you use (see
https://
20. 1. software.intel.com
/content/www/us/en/develop/tools/openvino-toolkit/system-requirements.html
21. 1. ).
    2. CPU
should
22. 1. must support the AVX2 or AVX512 instruction set (
see https://
23. 1. see ark.intel.com
/content/www/us/en/ark/search/featurefilter.html?productType=873&1_Filter-InstructionSetExtensions=3533&1_Filter-Family=595
24. 1. ).
Video card:
25. NVIDIA GeForce 1050
Ti or
26. Ti graphics card or higher. Requirements:
    1. At least 2 GB of memory;
    2. CUDA 11.
1—11.4
27. 1. 1 or higher;

    2. Compute Capability 3.

5—8.6

28. 1. 5 or higher.

       Note
       title Attention!
       CUDA is compatible with generations of computers with the following architectures: Kepler (partially), Maxwell, Pascal, Volta, Turing, Ampere, Ada Lovelace (partially) (

see 

29. 1. see CUDA). You can check Compute Capability GPU version on the manufacturer's website. If you use NVIDIA graphics cards, make sure to download the latest drivers from the manufacturer's website.

We recommend using AxxonSoft Platform Calculator (see AxxonSoft Platform Calculator documentation) to calculate the required video memory for detectors that use neural networks (see General information on neural analytics).

You can use multiple graphics When using a video card, a single neural network requires 500 MB of video memory, except for the neural network for face detection (see Hardware requirements for face detection) and license plate recognition (RR) (see Hardware requirements for License plate recognition (RR)). For example: a neural fire detection tool and a neural smoke detection tool, both with unlimited number of channels, require a 1 GB graphics card or higher. You can use multiple video cards in your system.