TensorFlow.js is an open-source hardware-accelerated JavaScript library for training and deploying machine learning models.
Develop ML in the Browser
Use flexible and intuitive APIs to build models from scratch using the low-level
JavaScript linear algebra library or the high-level layers API.
Run Existing models
Use TensorFlow.js model converters to run pre-existing TensorFlow models right
in the browser.
Retrain Existing models
Retrain pre-existing ML models using sensor data connected to the browser, or
other client-side data.
Check out their examples repository and their tutorials.
History of Pong
Pong was the first commercially successful computer game and widely accepted as the birthplace of gaming as we know it. From humble beginnings it created an industry that is now worth $108.9 billion globally, driven by over 1 billion worldwide gamers.
A retro atari cabinet with pong running on it.
Pre trainred Model
- Pong playing model is trained in Keras.
- Then it is saved and converted to tfjs format.
- The converted model is then loaded using Tensorflow.js
Try Now ! on Heroku ....
