Pet Classifier Model

Overview

Early computer-vision project — a CNN that classifies pets from photographs. Originally built during my high-school AI elective at Delhi Public School, R. K. Puram on a private school-provided dataset, then rebuilt as a public, reproducible repo on the Oxford-IIIT Pet Dataset (37 breeds, ~7,400 images). Uses MobileNetV2 transfer learning with a two-stage schedule — head training then fine-tuning the last ~30 base layers — targeting ~92% test accuracy. Ships with training, evaluation, and a single-image breed-prediction CLI.