Hardware requirements for neural analytics operation

The hardware requirements for the neural network-based analytics are:

1. Some NVIDIA SDK specific features allow the neural analytics to work only under Windows Server 2019 or Windows 10. 

2. For neural analytics operation, you may use CPUs, GPUs (NVIDIA discrete or Intel embedded), or VPUs (Intel NCS or Intel HDDL). 

   Note

   To connect an Intel NCS, insert the device into a USB port and make sure that it is recognized by Windows OS as one of the following: Movidius, Myriad X, or VSC Loopback Device. 

   Intel NCS may be used with any PC that conforms to Axxon One hardware requirements (see Hardware requirements).

   Attention!

   We do not 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 revision.

   Attention!

   For Intel HDDL to work correctly with AMD processors, pre-install the OpenVINO ™ toolkit version 2019.3.379 (see Installing openvino windows).

3. If a detection tool uses CPU or Intel GPU resources, make note of the following requirements:  

   1. supported CPUs:
      1. 6th-10th Generation Intel® Core™ processors;
      2. Intel® Xeon® v5 family;
      3. Intel® Xeon® v6 family;
      4. Intel® Movidius™ Neural Compute Stick;
      5. Intel® Neural Compute Stick 2;
      6. Intel® Vision Accelerator Design with Intel® Movidius™ VPUs;
   2. OpenVino should support the Intel CPU in use (see https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit/system-requirements.html).
4. Video card: NVIDIA GeForce 1050 Ti or higher. Requirements:
   1. at least 2 GB of memory;

   2. Compute Capability 3.5 − 8.6.

      Note

      You can check the GPU's Compute Capability version on the manufacturer's website.

      Attention!

      If you use NVIDIA graphics cards, make sure to download the latest drivers from the manufacturer's website.

When using a video card, a single neural network requires 500MB of video memory. 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.