Deep Learning Projects: Leveraging fastai v1

This repository contains different deep learning project notebooks that were run using the fastai framework.

Structure

Here is a list of the projects contained in this repository, classified according to the domain they belong to.

Vision:

• mask-wear: The goal of this project was to build an image classifier that identifies whether a person is wearing their mask properly or imporperly. Data was collected using Google Images.

• osmose-birds: The goal of this project was to build an image classifier that identifies different endangered waterbird species present throughout the Prek Toal Reserve in Cambodia. This classifier has the potential to bring support to NGOs such as Osmose which ensure the protection of waterbird colonies throughout the reproductive cycle. Data was collected using Google Images.

NLP:

• nlp-tweets: The goal of this project was to build a machine learning model that predicts which Tweets are about real disasters and which ones aren’t. I had access to a dataset of 10,000 tweets that were hand classified. This project was part of a Kaggle competition where I scored a 79.5% accuracy.

Contributing

Contributions are what make the open source community a great place to learn, inspire, and create. Any contributions you make are really helpful!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingContribution)
3. Commit your Changes (git commit -m 'Add some AmazingContribution')
4. Push to the Branch (git push origin feature/AmazingContribution)
5. Open a Pull Request

Reporting Issues

Does something seem off? Make sure to report it.