Documentation for Axxon One 2.0. Documentation for other versions of Axxon One is available too.

Previous page General information on neural analytics  Data collection requirements for neural network training Next page

Hardware requirements

Processors used for detectors operation

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

  1. Because of specific features of NVIDIA SDK, neural analytics can work on GPU only in the operating systems specified in Operating system requirements. 

    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 don't recommend using more than one Intel NCS device per Server.
    • Neural analytics can work on the following devices: CPU, Nvidia GPU, VPU (Intel NCS).

  2. 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 detectors 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).
  3. NVIDIA GeForce 1050 Ti graphics card or higher. Requirements:
    1. At least 2 GB of memory;
    2. CUDA 11.1 or higher;

    3. Compute Capability 3.5 or higher.

      Attention!

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

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 cards in your system.

Attention!

For the correct operation of each detector, a set of requirements must be met for:

  • hardware platform for detector operation,
  • video stream and scene,
  • images.

The requirements for each detector are specific and listed in the corresponding sections (see Detectors).

  • No labels