系统要求
操作系统 |
Windows 10/11, Linux Ubuntu 20.04/22.04/24.04/26.04 [1] or Jetson Linux 36/39 |
独立 GPU |
A dedicated GPU gives the best performance with Zivid. It is also the best choice if the GPU will be used for more than Zivid's computations. A medium to high-end NVIDIA GPU with at least 3 GB of memory is required for optimal performance. This is the preferred solution for Zivid. 建议:
|
带有集成 GPU 的 CPU |
This is the most cost-efficient solution for Zivid. The benefit of an integrated GPU is that the data transfer from GPU to CPU is fast. It is also beneficial for applications that require low power consumption, e.g., battery-powered mobile platforms. A high-end integrated GPU with at least 3 GB of memory available is required for optimal performance. 建议:
|
以太网 |
最高性能:
降低性能:
建议:
|
GPU 计算后端
Zivid SDK runs on one of two GPU compute backends, chosen when you install the SDK. Which backend to pick depends on your GPU vendor:
Architecture |
CUDA |
OpenCL |
|---|---|---|
Intel AMD64 |
No |
Yes |
NVIDIA AMD64 |
Optimal [2] |
Yes [3] |
NVIDIA ARM64 (Jetson) |
Yes |
No |
Requires an NVIDIA driver that supports CUDA 12 or newer.
If you install the OpenCL version of the SDK on an NVIDIA GPU, the SDK treats it as an unsupported compute device and will not run until you edit the Config.yml file to explicitly allow it. See 选择计算设备 for details. Zivid recommends installing the CUDA version instead, so no extra configuration is needed.
有关驱动程序安装以及如何选择计算设备,请参阅 关于GPU 。
如果您需要计算设备的建议,请查看 推荐的工业 PC 。
版本历史
SDK |
变更 |
|---|---|
2.18.0 |
Added support for Ubuntu 26.04. Updated the supported Jetson Linux versions from 35/36 to 36/39. |
2.17.0 |
增加了对 Zivid 3 XL250 的支持。 |
2.14.0 |
增加了对 Zivid 2+ MR130、LR110 和 MR60 的支持。 |
2.12.0 |
Zivid One+ 已达到其生命周期的终点并且不再受支持。 |