PC Requirements

Intel Core i7 or higher.

• The Blue Locate tool is sensitive to clock speed rates, particularly with complex model matching applications.

• 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.

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:

• VisionPro Deep Learning 3.3 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.

• 10 GB or larger GPU RAM is required for a training PC.

• 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.
  

• Cognex recommends using a GPU driver version from 528.02 to 532.03, with the following considerations:

  • The tested driver version is 528.02.

  • Driver versions from 532.03 to 546.01 are not recommended.

  • 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.

VisionPro Deep Learning has the following minimum system memory requirements:

• 64 GB RAM or larger is required for a training PC.

• 32 GB RAM or larger is required for a deployment PC.