• Home
  • Blog
  • C# / Unity
  • C++ / Unreal Engine
  • Python strategy games
  • Python arcade games
  • Python other
  • Machine Learning
  • C
  • Scratch
  • Coding and electronics
  • How I learnt to code
  • Project Euler
  • Feedback
  James L.'s coding

Machine Learning

TensorFlow in Practice

I've passed the TensorFlow in Practice course on Coursera that is taught by Andrew Ng and Laurence Moroney.  It covers: Convolutional Neural Networks, Natural Language Processing and Sequences, Time Series and Predictions.

Picture

Digit Recogniser

Digit Recognition was my first machine learning project. It uses the MNIST database of labelled handwritten digits (about 70,000 of them) to find an algorithm to work out your digit.  The digits are stored in single dimensional arrays of opacity.  The biggest difficulty with the project was exporting the trained model from a Jupyter Notebook to Unity.  The predictions aren't as good as I wanted because I couldn't export my Convnet model (which looks at shapes wherever they are in the image) and so I had to use a Dense network (which looks at pixels).  
The first six digits in the MNIST data base.
You click and drag to draw a digit. You can draw anywhere in the second blue box but I recommend you draw in the darkest box. When you are done press recognise.
An .exe of the unity code
Proudly powered by Weebly
  • Home
  • Blog
  • C# / Unity
  • C++ / Unreal Engine
  • Python strategy games
  • Python arcade games
  • Python other
  • Machine Learning
  • C
  • Scratch
  • Coding and electronics
  • How I learnt to code
  • Project Euler
  • Feedback