# Advanced development and application of AI vision modules 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 Grove Vision AI V2 module applied to Petoi robotic dogs, you can email ****** for a solution. We will reply to you ASAP! --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.petoi.com/extensible-modules/advanced-development-and-application-of-ai-vision-modules.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.