Support Knowledge Base

Why Inferencing Using YOLOv3 on Ubuntu* 20.04 Is Faster than Inferencing on Yocto* OS?

Content Type: Compatibility | Article ID: 000089046 | Last Reviewed: 05/20/2022

Description Resolution

Environment

Ubuntu 20.04 Yocto (IOTG Yocto BSP, Tag: release-74_tgl_u_mr3) Yocto (IOTG Yocto BSP, Tag: release-81_tgl_u_mr4) OpenVINO 2021.4 OpenVINO 2021.4.2

Description

Ran Object Detection C++ Demo with YOLOv3 model using GPU plugin in OpenVINO™ 2021.4.
Obtained similar performances in Ubuntu 20.04 and Yocto (IOTG Yocto BSP, Tag: release-74_tgl_u_mr3) when using Intel® Core™ i5-1145G7E, Intel® Core™ i3-1115G4E, and Intel® Celeron® 6305E processors.
Obtained 58 frames per second (FPS) in Ubuntu 20.04 and 47.3 FPS in Yocto (IOTG Yocto BSP, Tag: release-74_tgl_u_mr3) when using Intel® Core™ i7-1185G7E processor.

Resolution

Use IOTG Yocto BSP (Tag: release-81_tgl_u_mr4) image for Yocto.
Run Object Detection C++ Demo with YOLOv3 model using GPU plugin in OpenVINO™ 2021.4.2.

Related Products

This article applies to 4 products.

Intel® Xeon Phi™ Processor Software OpenVINO™ toolkit Performance Libraries

Discontinued Products

Intel® Developer Cloud for the Edge

Need more help?

Contact support

Contact support