UC-046 Cat Classification of 20 Distinct Breeds

Cat breed classification algorithms have been made time and time before due to cats being such a popular and beloved animal. As such, classification algorithms aim to identify their breeds for veterinary pursuits and wildlife tracking which necessitates accurate classification. Our classification algorithm identifies 20 different CFA-recognized pedigreed cat breeds utilizing TensorFlow with the MobileNetV3 Large model as the base for training. Our preliminary results over 25 initial epochs and 25 fine tuning epochs resulted in a model with a test accuracy of 65%. In the future, we plan to add more techniques to prevent overfitting and experimenting with a more robust dataset which we hope will allow us to achieve our target accuracy of 80%.