Hardware and Software Requirements

Requirements differ based on how you plan to use the application.

  • If you use or train modules of Anomaly of Surface or Surface Detection you may be able to use a PC without GPU.
  • If you use modules for Images Preprocessing, Measurement or Code you can safely use PC without GPU.
  • If you are going to use modules for Classification of Object Detection we strongly recommend to use GPU for training. It is possible to use PC without GPU for image recognition (inference), however the inference times would be significantly higher.

Runtime

For typical requirements - fast processing and convenient usage we recommend to use NVIDIA GPU with enough memory. A rough estimation is 3GB per deep-learning module. To be on the safe side we recommend to use NVIDIA GeForce® RTX 2080 Ti.

For price-sensitive use-cases it is possible to use cheaper NVIDIA GPU card or to use a computer without GPU card at all. However, this results in longer recognition times.

For embedded use-cases we support embedded hardware too - e.g. ARM based devices like NVIDIA TX2 or Xavier or some types of FPGA. Contact us for more information.

Training

For training of deep-learning modules we recommend to use fast NVIDIA GPU with a lot of memory. We recommend to use NVIDIA GeForce® RTX 2080 Ti in a PC with at least 16 GB of RAM. (Training of deep-learning modules without GPU can technically work but we strongly discourage from this as the training times can take hours or even days).

Hardware Requirements

  • NVIDIA GPU with CUDA (capability 4.0 or higher)

Software Requirements

  • CUDA library 10.0
  • cuDNN library 7.5

General

Operating System Support

  • Windows 7 or higher
  • Linux – supported distributions: Ubuntu 16.04, Ubuntu 18.04

In case you are using LabVIEW

LabVIEW 2019 (and above), VIPM 2019 (and above), Win 10

results matching ""

    No results matching ""