Raspberry pi Object Detection Async vs Sync Intel OpenVINO Comparision
more info
http://raspberrypi4u.blogspot.com/202...
Hardware
• Raspberry pi 4B 4G + SDCard 32 GB
• Intel Neural Compute Stick 2
Software
• Raspberry pi Legacy OS ( Raspbian 10 , 32 bit version )
• OpenVINO toolkit 2019 R3
• OpenCV 4.0
• Python 3.7.3
Machine Learning Model : SSD Mobilenet V2 ( FP16 )
Video MP4 960x540 pixels
Install OpenVINO™ toolkit for Raspbian* OS
https://docs.openvino.ai/latest/openv...
Object Detection Python* Demo
https://docs.openvino.ai/latest/omz_d...
Async API usage can improve overall frame-rate of the application, because rather than wait for inference to complete, the app can continue doing things on the host, while accelerator is busy.
This and other performance implications and tips for the Async API are covered in the Optimization Guide.
Other demo objectives are:
Video as input support via OpenCV*
Visualization of the resulting bounding boxes and text labels (from the .labels file) or class number (if no file is provided)
สอบถาม เพิ่มเติม :
อดุลย์ นันทะแก้ว 081-6452400
LINE : adunnan
Page : / softpowergroup
FaceBook : / adun.nantakaew
email : [email protected]