Grove Vision AI V2 is based on the Arm Cortex-M55 and Ethos-U55 embedded vision module.The Ethos-U55 has 64 to 512 GOP/s of arithmetic power to meet the growing demand for downloading machine learning
Last updated
This chapter is divided into three subsections. The first subsection is model training, which explains how to train the model on the local computer or in the cloud and how to produce the dataset. In addition, we have implemented a DIY training function for the COCO dataset, which allows you to select any number of labels of interest for model training.
The second subsection is model quantization, which reduces the computational complexity of the model and makes it easier to deploy in embedded systems. Similarly, we consider the difference between local and cloud training models, which can be subjected to model quantization.
The third section is the model deployment. It explains how to download the model to Grove Vision AI V2 and implement the communication between it and the robot dog so that we have completed the learning of the whole process from model training to model deployment. We believe that through the detailed explanation in this chapter, you can learn how to deploy your favorite model on our robot dog and be amazed by its powerful functions.
If you encounter problems using the AI vision module applied to Petoi robotic dogs, you can email sunkaiwei13791222268@gmail.com for a solution. We will reply to you ASAP!
