Exercises for fastai's course Practical Deep Learning
As the title suggests, this repository contains my homework for the course Practical Deep Learning.
I aimed to distinguish between Magic: The Gathering, Yugioh!, and Pokémon TCG cards. I got the idea for this notebook from an old project where I and a friend of mine tried to develop a physical classifier of Magic Cards.
You can find the notebook here on GitHub or on kaggle.
As a lesson 2 homework, I trained an artistic style classifier based on the best-artworks-of-all-time dataset. The main problem left is due to the non-uniform representation of artistic style for each artist. You can find the notebook on this repository or on kaggle. A basic webapp is available too on huggingface.