Scribd
Upload
99 views2 pages

Cognex Deep Learning PC Requirement

Uploaded by

gokul.advantech
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
99 views2 pages

Cognex Deep Learning PC Requirement

Uploaded by

gokul.advantech
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

System Requirements

System Requirements
The following subsections describe the software and hardware requirements to use VisionPro Deep Learning.

PC Requirements
Both PCs for training and PCs for deployment purposes require a fast multi-core CPU, large system memory (RAM), and a
strong NVIDIA® GPU. Training PCs require larger GPU and system memory, and a large amount of free SSD space.

Requirement Description
CPU Intel Core i7 or higher.

l The Blue Locate tool is sensitive to clock speed rates, particularly with complex model matching
applications.
l If a single core performs multiple tasks, processing time can increase. Therefore, use a sufficient
amount of resources or allocate only one task to a single core.
GPU Cognex recommends using a GPU for higher performance and for access to High Detail tools. You can use
Focused mode tools without a GPU, but you cannot process High Detail and High Detail tools.
VisionPro Deep Learning has the following GPU requirements:
l VisionPro Deep Learning 3.3.2 supports all NVIDIA® CUDA®-enabled GPUs with compute
capability of 6.1 and higher. For more information about GPU compute capability, see the NVIDIA
website.
l 10 GB or larger GPU RAM is required for a training PC.
l 8 GB or larger GPU RAM is required for a deployment PC.

Note: For training and processing High Detail tools, Cognex recommends more than 10 GB.

l Cognex recommends using a GPU driver version from 528.02 to 532.03, with the following
considerations:
l The tested driver version is 528.02.
l Driver versions from 532.03 to 546.01 are not recommended.
l You can use a driver version higher than 546.01 if necessary. When using a version higher
than 546.01, you must disable Shared GPU memory usage in the NVIDIA Control Panel.
For more information, see Disable Shared GPU Memory.

Note: Using driver versions beyond 532.03 can result in slower training and
processing times in High Detail mode.

Visit the NVIDIA Driver Downloads website to find the right driver version for your GPU.

For more information about selecting GPUs for your application, see Guidelines for GPU Selection on
page 50.
System VisionPro Deep Learning has the following minimum system memory requirements:
memory
l 64 GB RAM or larger is required for a training PC.
(RAM)
l 32 GB RAM or larger is required for a deployment PC.
System SSD with 200 GB or more free space is required for a training PC.
storage

49
System Requirements

PCIe lanes Minimum x8 PCIe lanes. A x16 PCIe lane can reduce cycle time by approximately 10 ms, relative to a PCIe
x8 (based on a 5 MP image).
Power supply 1.25 times larger than the system and GPU power requirements.
USB 2.0 USB port for a permanent Security Key connection via USB 2.0.

Guidelines for GPU Selection


VisionPro Deep Learning3.3.2 supports all NVIDIA® CUDA®-enabled GPUs with compute capability of 6.1 and higher. For
more information about GPU compute capability, see the NVIDIA website.
Cognex recommends selecting an NVIDIA® GPU model with a higher core clock frequency, higher memory, and a higher
number of CUDA cores and Tensor cores because these models provide faster computational speeds.

Note: To use GPU driver versions higher than 546.01, you need to disable the Sysmem Fallback setting in the NVIDIA
Control Center. See Disable Shared GPU.

Tested GPU Models


The following list includes the GPU models that Cognex has tested. Cognex aims to support most common GPU families, but
we do not test every model. If the GPU model meets the compute capability requirements, you can use it. Cognex customers
use most common GPUs other than very new models, even if the GPUs have not been tested by Cognex.
l NVIDIA® GeForce® GTX 1060 6GB
l NVIDIA® GeForce® GTX 1080
l NVIDIA® GeForce® GTX 1080 Ti
l NVIDIA® GeForce® RTX 2080 Ti
l NVIDIA® GeForce® RTX 3080
l NVIDIA® GeForce® RTX 3080 Ti
l NVIDIA® GeForce® RTX 3090
l NVIDIA® GeForce® RTX 4080
l NVIDIA® GeForce® RTX 4090
l NVIDIA® Quadro® P4000

Not Recommended GPU Models


Cognex does not recommend the following GPU models because they provide low performance and slow training time for
unknown reasons:
l NVIDIA® GeForce® GTX 1650
l NVIDIA® GeForce® GTX 1660

Supported Operating Systems


Microsoft® Windows® Operating System English Chinese Japanese Korean French German Spanish
Windows 11 Professional (64-bit) ✓ ✓ ✓ ✓ ✓ ✓ ✓
Windows 10 Professional (64-bit) ✓ ✓ ✓ ✓ ✓ ✓ ✓
Windows Server 2019 ✓ ✓ ✓ ✓ ✓ ✓ ✓
Windows Server 2022 ✓ ✓ ✓ ✓ ✓ ✓ ✓

50

You might also like