You are here: Start » Appendices » Deep Learning Service Configuration

Deep Learning Service Configuration

Contents

1. Installation guide
2. GPU installation prerequisites
3. Using Adaptive Vision Deep Learning Service
4. References

Installation guide

To to use Deep Learning technique with Adaptive Vision Studio or Adaptive Vision Library an additional Deep Learning Service must be installed. Before installing Adaptive Vision Deep Learning Service please check your hardware configuration.

Deep Learning Service is available in two versions:

• GPU version - version optimized for working with GPU acceleration. It is recommended for performing DeepModel training.
• CPU version - all computations are done using only CPU; no additional GPU hardware is needed.

Requirements

• Graphics card compatible with CUDA toolkit. List of compatible devices can be found on this website (all CUDA devices with "Compute Capability" greater or equal 3.5 and less than 7.0). For best performance minimal 2 GB memory is required.
• At least 1.5 GB disk space for program files.
• At least 8 GB RAM memory.
• 64-bit processor Intel i7, i5 or better.
• Windows 7, 8 or 10.

Using Adaptive Vision Deep Learning service

After starting the service, a new icon should be displayed in system tray.

The service icon can be displayed in three colors, indicating the service status:

• Red - service is starting or an error has occurred;
• Yellow - service is ready to accept clients;
• Green - client is connected.

Please note: to open the Deep Learning Editor, place a relevant Deep Learning filter (Detect Features, Detect Anomalies or Classify Object) in the Program Editor, go to its Properties and click on the icon next to inDeepModel parameter.

See also:

• Machine Vision Guide: Deep Learning - Deep Learning technique overview,
• Creating Deep Learning Model - how to use Deep Learning Editor.

Previous: Quick Start Guide for C/C++ Programmers