A selection of example projects I've worked on can be found below.

Interactive examples from the DeepLearning.AI TensforFlow Developer Professional Certiicate course, including my own investigations to gain a deeper understanding of the course content.

Please note: It might take ~ 30 seconds for the app to load - I’m using the free tier of Heroku, and so the app goes to sleep after 30 minutes of inactivity.

GitHub

From September 2019 until April 2020 I completed a 12 week data science bootcamp with Cambridge Spark. This culminated in a capstone project, which I completed with agriculture AI firm SmartBell.

The aim of the project was to train object detection models on video footage of calves within an enclosed, undercover rearing area. It was demonstrated that by performing transfer learning with TensorFlow using a relatively small selection of manually tagged frames, models able to detect calves, their heads and shelter entrances could be developed. The trained models detected around 90 % of objects in a frame on average, and were used to generate metrics detailing: the number of calves in view over a given period of time; the number of these that were within a shelter; and the number with their heads low to the ground – a potential indicator of illness.

The full capstone project report can be downloaded here.

Some intuitions about neural networks - based on notes from Andrew Ng’s Machine Learning Coursera course.

Please note: It might take ~ 30 seconds for the app to load - I’m using the free tier of Heroku, and so the app goes to sleep after 30 minutes of inactivity.

GitHub

A super simple, starter for 10 Streamlit app with the purpose of demoing functionality, and documenting how to do some cool stuff. Includes a guide to deploying a Streamlit app to Heroku via a CI/CD pipeline implemented using GitHub Actions.

Please note: It might take ~ 30 seconds for the app to load - I’m using the free tier of Heroku, and so the app goes to sleep after 30 minutes of inactivity.

GitHub

This website - hosted on GitHub pages using the Jekyll framework and Liquid templating language.

I created a bespoke version of the Cayman theme, and setup the custom domain to make the website available at https://thatscotdatasci.com via HTTPS.

GitHub