Article ID: 000059581 Content Type: Maintenance & Performance Last Reviewed: 05/20/2022

Why Is the Frame per Second (FPS) in Deep Learning (DL) Workbench Higher than OpenVINO™ Demo Inference Script?

BUILT IN - ARTICLE INTRO SECOND COMPONENT
Summary

Factors that affect inference performance

Description
  1. Ran YOLOv4 Object Detection model with Microsoft Common Object in Context (MS COCO) dataset on DL Workbench and get 50 - 60 FPS.
  2. Ran OpenVINO™ Demo Inference Script and got higher FPS.
Resolution

Inference Results may vary depending on many factors:

  • Load of local machine
  • Usage of OpenVINO™ Toolkit API
  • Tools used

Related Products

This article applies to 2 products