DeGirum Demonstration of Efficient Pipelining of Multiple Models Using DeGirum PySDK

Shashi Chilappagari, Co-Founder and Chief Architect of DeGirum, demonstrates the company’s latest edge AI and vision technologies and products at the 2023 Embedded Vision Summit. Specifically, Chilappagari demonstrates DeGirum’s hardware (ORCA) and software (PySDK).

Chilappagari demonstrates PYSDK’s ability to pipeline multiple machine learning models by showcasing a use case in which the output of one machine learning model is used to determine the input to the second machine learning model. The first model is a YOLOv5s-based person detection model which identifies all the people in each frame. The bounding boxes of people are then cropped and sent to a pose detection model which identifies multiple key points. DeGirum’s PySDK then combines all the information and renders the output.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.



1646 N. California Blvd.,
Suite 360
Walnut Creek, CA 94596 USA

Phone: +1 (925) 954-1411
Scroll to Top