xact VS AI-basketball-analysis

https://github.com/wtpayne/xact - Model Based Systems/Software Engineering tool with support for machine learning and synthetic data.

MBSE is a vastly underappreciated technique, and one that deserves much more exposure in the mainstream tech community.

Sadly, I have found myself exceedingly disappointed at the tooling available to support MBSE, having mainly used Simulink, and also experimented with a few others like Rhapsody, Capella and EA.

Constant mouse usage with Simulink gave me really bad RSI, and merging models was a pain, due to the way that layout and structural information were mixed together in the xml-based .mdl file format.

So (naturally) I made a text-based alternative. It's a bit like TensorFlow in that you create a compute graph (computational model), and then run it.

The model itself can be generated dynamically in a script, using JQuery-like syntax to add or change nodes, or alternatively it can be stored and version controlled in one or more text files, using YAML, XML, JSON or TOML (or some mixture of those) to serialise the structure in an easy-to-diff-and-merge form.

https://github.com/wtpayne/xact

Source code: https://github.com/chonyy/AI-basketball-analysis

I built an app to visualize and analyze basketball shots and shooting pose with machine learning.

https://github.com/chonyy/AI-basketball-analysis

The result is pretty nice. However, the only problem is the slow inference speed. I'm now refactoring the project structure and changing the model to a much faster YOLO model.

Thanks for asking! This is not a noob question.

I would say that the similar workflow could be applied to any ball-related sports. The object detection and the tracking algorithm is basically the same. Then, you could add any sport-specific feature!

For example, I have used a similar method to build AI Basketball Analysis.

https://github.com/chonyy/AI-basketball-analysis