When using a computer vision model, some characteristics are crucial. Optimizing a model for speed may allow it to run in real time, opening up many new uses. Improving a model's accuracy by even a few percent may make the difference between a toy model and a real-life application.
Another important characteristic is size, which impacts how much storage the model will use and how long it will take to download it. For some platforms, such as mobile phones or web browsers, the size of the model matters to the end user.
In this section, we will describe techniques to improve the model inference speed and how to reduce its size.
