AWS Dog Breed Classifier – Computer Vision Project

This project is part of my work in the Future AWS AI Scientist program with Udacity.

The goal was to build a dog breed classifier that can identify the breed of a dog from an input image using a pre-trained deep learning model.

What I did

  • Used a pre-trained CNN model and fine-tuned it for dog-breed recognition.
  • Processed image data and organized it into training, validation, and test sets.
  • Deployed and ran the model using AWS tooling and a reproducible notebook workflow.

Why it matters

This project strengthened my understanding of transfer learning, model evaluation, and how to take a computer vision workflow from experimentation to a more production-ready structure on AWS.