Session
Rocket your Machine Learning models to the edge with C#
In this talk we will see how to optimize the cascade execution of various Machine Learning models with ML Net using the latest Microsoft video analytics platform: "Project Rocket" https://github.com/microsoft/Microsoft-Rocket-Video-Analytics-Platform .
We'll see how to build our own Machine Learning pipeline to optimize its execution at the edge (in this particular case we will use the jetson nano).
To see the use of this Pipeline, several models (lightweight and heavy from Tensorflow and Darknet) have been used for pedestrian detection. In addition, these models will be able to recognize when certain pedestrians cross certain dangerous areas, sending all this information to the cloud.
Once the pipeline has been built, we will simulate the streaming video in real time to our edge device and send all the generated telemetry to the IoT Hub.
Rodrigo Cabello
Principal AI Research Engineer at Plain Concepts and Microsoft MVP in Artificial Intelligence
Granada, Spain
Links
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top