Playing Mortal Kombat with TensorFlow.js. Transfer learning and data augmentation
Read OriginalThis technical article details the process of creating a posture classification algorithm to control a JavaScript Mortal Kombat game. It explores using TensorFlow.js and Convolutional Neural Networks (CNNs), applying transfer learning with MobileNet to improve upon a previous basic posture detection method. The post covers data collection, model training, and the technical challenges of real-time classification in the browser.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
1
Introducing GPT-5.1 for developers
Simon Willison
•
4 votes
2
Using A Hidden Submit Button To Ensure Unnamed Submissions
Ben Nadel
•
3 votes
3
uv+just for testing multiple Python versions
Daniel Feldroy
•
3 votes
4
ServiceNow and Microsoft Copilot
Marius Sandbu
•
2 votes
5
🧠 Build an Agent Chat that Remembers — Persisting Conversations with Microsoft Agent Framework
Bruno Capuano
•
2 votes
6
Agentic AI and Security
Martin Fowler
•
2 votes
7
Springs and Bounces in Native CSS
Josh Comeau
•
2 votes
8
Importing vs fetching JSON
Jake Archibald
•
2 votes
9
Hire Me in Japan
Dan Abramov
•
1 votes
10
In the economy of user effort, be a bargain, not a scam
Lea Verou
•
1 votes