Hardware requirements for neural analytics operation

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

1. Some NVIDIA SDK specific features allow neural analytics to work only on Windows Server 2019 and Windows 10. 

2. Neural analytics can work on CPU, Nvidia GPU, VPU (Intel NCS, Intel HDDL).

   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 on any computer that meets Axxon One hardware requirements (see Hardware requirements). We do not recommend using more than one Intel NCS device per Server.
   • You can use several Intel HDDL devices on one Server if they have the same revisions.
   • For Intel HDDL to work correctly with AMD processors, pre-install the OpenVINO™ toolkit version 2019.3.379 (see docs.openvino.ai).

3. If CPU or Intel GPU is used to run analytics, the following requirements must be met:

   1. Supported CPUs:

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

         Attention!

         When using a CPU lower than 6th Generation Intel® Core™ processors, the operation of the detection tools isn't guaranteed.

      2. Intel® Xeon® v5 family and Intel® Xeon® v6 family.
      3. Intel® Movidius™ Neural Compute Stick.
      4. Intel® Neural Compute Stick 2.
      5. Intel® Vision Accelerator Design with Intel® Movidius™ VPUs.
   2. OpenVino must support the Intel CPU that you use (see software.intel.com).
   3. CPU must support the AVX2 or AVX512 instruction set (see ark.intel.com).
4. NVIDIA GeForce 1050 Ti graphics card or higher. Requirements:
   1. At least 2 GB of memory;
   2. CUDA 11.1–11.4;

   3. Compute Capability 3.5–8.6.

      Attention!

      • CUDA is compatible with generations of computers with the following architectures: Kepler (partially), Maxwell, Pascal, Volta, Turing, Ampere (partially) (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.

When you use a graphics card, a single neural network requires 500 MB of video memory, except for the neural network for Face Detection (see Hardware requirements for the Face Detection TV and its sub-tools) and License Plate Recognition RR (see Hardware requirements for License Plate Recognition RR and Vehicle 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 graphics cards in your system.