Page History
Section | ||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
General requirements for base computers and operating system
The requirements for the base computers and operating system for the modules included in the Intellect Detector pack correspond to the same requirements for the Intellect (see Intellect Administrator's Guide).
Each software module automatically determines which computing resources it can use — a central processing unit (CPU) or a graphics processing unit (GPU).
For the modules that use neuroanalysis neural analysis (see General information on Neural analytics), the operation device can be set manually.
Hardware and software requirements for neural analytics
The following requirements are imposed on the software and Requirements for the hardware platform when the neuroanalysis neural network analytics is used:
- Due to the NVIDIA SDK specific features, the neural analytics can operate only on Windows Server 2019 OS and Windows 10 OS.
The neural network analytics supports the following devices: CPU, GPU (NVidia discrete GPUs, integrated Intel GPUs), NVIDIA, VPU (Intel NCS, Intel HDDL).
Info title Note. In order to connect the Intel NCS, plug in the device to the USB port and make sure that Windows shows it with one of the following names: Movidius, Myriad X, VSC Loopback Device.
Intel NCS can be utilized with any computer compliant to the Intellect hardware requirements (see Requirements for base PCs).
Note title Attention! It is not recommended to use more than one Intel NCS device on the same Server.
Note title Attention! Several Intel HDDL devices can be used on one Server if their revisions match.
For Intel HDDL to work on a computer with AMD CPU, it is required that the OpenVino toolkit be installed according to the instructions on the siteThe neural network analytics functions are not available for AArch64 (ARM) architecture processors.
- If CPU or Intel GPU is used for the neural network analytics operation, keep in mind that the following processors are supported: Intel Core generation 6 and later, Intel Xeon and Intel Pentium® processors N4200/5, N3350/5 or N3450/5 with Intel® HD Graphics then the following requirements should be taken into account:
- support for the following CPUs:
- 6th-10th Generation Intel® Core™ processors;
- Intel® Xeon® v5 family;
- Intel® Xeon® v6 family;
- Intel® Movidius™ Neural Compute Stick;
- Intel® Neural Compute Stick 2;
- Intel® Vision Accelerator Design with Intel® Movidius™ VPUs;
- the OpenVino toolkit should support the Intel CPU being used (for more information see https://software.intel.com/content/www/us/en
- support for the following CPUs:
- NVIDIA GeForce 1050 Ti GPU or newer. GPU requirements:
- at least 2 GB of memory;
Compute Capability 3.0 or higher.5 - 8.6.
Info title Note. Please check the GPU's Compute Capability version on the manufacturer's web site.
Info title Attention! When using NVidia NVIDIA graphics cards, it is recommended to install the latest driver from the NVidia official NVIDIA official web site.
A single neural network consumes 500 MB of video memory. Each neural network is distributed between several object trackers within the GPU. For example: to apply the neural fire detector and the neural smoke detector to any number of channels, you should use a 1 GB graphics card or higher. You can use multiple video cards in your system.
...