Page History
...
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 (see General information on Neural analytics), the operation device can be set manually.
Requirements for the hardware platform when the neuroanalysis is used:
The neural network analytics supports the following devices: CPU, GPU (NVidia discrete GPUs, integrated Intel GPUs), VPU (Intel NCS, Intel HDDL).
Info title Note. In
...
The computer and operating system requirements for the modules that are part the Intellect Detector pack correspond to the same requirements for that of Intellect (see Intellect Administrator's Guide). However, some software modules have different requirements, which are listed below.
Info | ||
---|---|---|
| ||
Each software module automatically determines, which computing resources it can use: either the central processing unit (CPU) or the graphic processing unit (GPU). For the Neurotracker and the Person location tracker software modules, you can manually select the CPU or GPU, or use the automatic mode. |
The Neurotracker and the Person location tracker software modules
Requirements for the hardware platform when the Neurotracker and the Person location tracker are used:
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! The 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 https://software.intel.com/en-us/openvino-toolkit/hardware.
- NVIDIA GeForce 1050 Ti GPU or newer. GPU requirementsOnly NVidia GPUs are supported. Video cards from other manufacturers are not supported.
NVidia GeForce 1050 Ti or newer video card. Requirements:- at least 2 GB of memory;
Compute Capability 3.0 and upor higher.
Info title Note. You can Please check the version of GPU's Compute Capability video card version on the manufacturer's pageweb site.
Noteinfo title Attention! Each object of the Neurotracker/Person location tracker uses about 400 Mbytes of the video RAM. When several such objects are used, which collectively consume the video RAM more than it is available on the system, the error will appear. In case of lack of the video RAM, it is recommended to use several video RAMs in one system.
When using NVidia graphics cards, it is recommended to install the latest driver from the 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.
Note | ||
---|---|---|
| ||
Make sure that video image requirements are met in order for each detection module to operate correctly. The requirements are specific for each detection module and are given in the corresponding sections (see Configuring detection modules). |