Hardware requirements for When you use neural analytics (see General information on neural analytics), the hardware requirements are the following:
Because of specific features of - Take into account NVIDIA SDK
, - limitations. The neural analytics can
work - operate on the GPU only in the operating systems specified
in - in the Operating system requirements page.
| Note |
|---|
|
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: - VPU requirements (Intel NCS):
- Connect a device to the computer USB port.
- Make sure that the Windows system determines a device as 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 - Use it on the computers that meet the Hardware requirements.
- Apply no more than one Intel NCS device
per - on the server.
- Neural analytics can work on the following devices: CPU, Nvidia GPU, VPU (Intel NCS).
If CPU or Intel GPU is used to run analytics, the following requirements must be met:
Supported CPUs:6th Generation Intel® Core™ processors and higher.
| Note |
|---|
|
When using a CPU lower than 6th Generation Intel® Core™ processors, the operation of the detectors isn't guaranteed. |
- Intel® Xeon® v5 family and Intel® Xeon® v6 family.
- Intel® Movidius™ Neural Compute Stick.
- Intel® Neural Compute Stick 2.
Intel® - Supported CPUs and requirements:
| CPU type | Supported generations/models | Key requirements and conditions |
|---|
| Intel® Core™ | 6th generation (Skylake) and higher | - Support the AVX2 or AVX512 instruction set (see ark.intel.com)
- We don't guarantee the detector operation on CPUs lower than 6th generation
|
| Intel® Xeon® | v5 family (Broadwell) and v6 (Skylake) | |
| Intel VPU devices | Movidius™ Neural Compute Stick, Neural Compute Stick 2, |
| Vision Accelerator Design with Intel® Movidius™ VPUs |
.OpenVino must support the Intel CPU that you use .- CPU must support the AVX2 or AVX512 instruction set (see ark.intel.com).
- NVIDIA GeForce 1050 Ti graphics card or higher. Requirements:
- At least 2 GB of memory;
- CUDA 11.1 or higher;
Compute Capability 3.5 or higher.
| Note |
|---|
|
- 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.
...
- Requirements for NVIDIA GPU:
| Parameter | Minimal/recommended requirements |
|---|
| GPU model | NVIDIA GeForce GTX 1650 and higher |
| Memory space | At least 2 GB. For the accurate calculation, we recommend using AxxonSoft Platform Calculator (see AxxonSoft Platform Calculator documentation) |
| CUDA version | 12.8.1 |
| Compute Capability | Not lower than 7.5. You can check a version on the page or on the manufacturer's website. |
| Supported architectures | - Turing, Ampere, Ada Lovelace (partially)
- In Windows OS, starting from the Detector Pack 3.15.2 version, the Hopper and Blackwell support is added for the following detectors:
- Starting from the Detector Pack 3.15.2 version, Kepler (late), Maxwell, Pascal, Volta are no longer supported
|
| Drivers | We recommend installing the latest driver version from the official website |
| Configuration | You can use several GPUs in one system |
For proper operation, each detector must meet individualspecificrequirements (see Detectors) to:- Hardware,
- Video stream and scene,
- Image settings
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.
...