We were consulted about introducing a workstation for the purpose of acquiring multi-view images using industrial cameras and performing inference using deep learning.
The client is considering a configuration in which eight cameras will be connected via a PoE hub and the synchronized footage will be analyzed, and they would like to implement an Intel X550-T2 NIC.
The budget is around 50 to 60 yen.
| CPU | Intel Core Ultra 7 265 2.40GHz(8C/8T) +1.80GHz(12C/12T) |
| memory | Total 64GB DDR5 6400 32GB x 2 |
| Storage 1 | 2TB SSD M.2 NVMe Gen4 |
| Video | NVIDIA GeForce RTX5070Ti 16GB |
| network | on board(2.5GBase-T x1) Wi-Fi 6E, Bluetooth |
| Housing + power supply | Mid-tower chassis + 1000W 80PLUS PLATINUM |
| OS | Microsoft Windows 11 Professional 64bit |
| Expansion card | Intel X550-T2 10GBase-T 2Port |
| Others | TEGARA Young Researcher Support Campaign Benefit A (5% OFF) |
This structure is subject to the current "Young Researchers Support Campaign (5% OFF)"This is an example of a design that was done within a budget of 60 yen.
Click here for details on the "Young Researchers Support Campaign" to help you get started with your research.
CPU and Storage
To process images from multiple cameras simultaneously, we selected the Intel Core Ultra 7 265 (8 cores + 12 cores) CPU, which has high parallel processing performance.
It provides stability in video capture processing.
In addition, high-resolution video from eight cameras can be simultaneously imported into the storage.Choose a 2TB M.2 NVMe SSD for superior write speedsdoing.
About GPU
To make inference of deep learning models more efficient, GPUs haveEquipped with GeForce RTX 5070Ti (16GB) for maximum performance within your budget
Considering the VRAM capacity, the system memory exceeds this by 64GB.
Network configuration and I/O performance
The NIC (X550-T2) specified by the customer is a standard 10GbE NIC that does not have PoE power supply functionality.
Therefore, in this configuration,Intel X550-T2 – PoE Hub – CameraThe connection path is ", and power is supplied to the camera and communication is carried out via the PoE hub.
※※Points to note when connecting a camera※※
Depending on the number of cameras connected and the data volume, there is a possibility that a bottleneck may occur between the X550-T2 and the PoE hub, preventing the video from being sent correctly to the PC.
When connecting one camera to one PoE port, we have a proven track record of providing ADLINK PCIe-GIE74P
We can propose the optimal configuration depending on your application and the number of devices you want to connect, so please contact us with your needs.
For those who are active in these fields
|
Tegara's custom-made PC production service not only caters to initial use, but also supports system expansion in anticipation of future expansion of research scale.
We not only propose configurations that meet various software requirements, but also accept consultations regarding the construction of an entire research environment.
Please feel free to contact us and we will provide the best solution to suit your needs.
|
■ Click here for details and inquiries about this PC case
* Please enter the name of the case or your desired conditions. |
