Toly Kotlarsky, Distinguished Member of the Technical Staff in R&D at Zebra Technologies, presents the “Practical Guide to Implementing Deep Neural Network Inferencing at the Edge” tutorial at the September 2020 Embedded Vision Summit.
In this presentation, Kotlarsky explores practical aspects of implementing a pre-trained deep neural network (DNN) inference on typical edge processors. First, he briefly touches on how we evaluate the accuracy of DNNs for use in real-world applications. Next, he explains the process for converting a trained model in TensorFlow into formats suitable for deployment at the edge and examines a simple, generic C++ real-time inference application that can be deployed on a variety of hardware platforms
Kotlarsky then outlines a method for evaluating the performance of edge DNN implementations and shows the results of utilizing this method to benchmark the performance of three popular edge computing platforms: The Google Coral (based on the Edge TPU), NVIDIA Jetson Nano and Raspberry Pi 3.
See here for a PDF of the slides.