This capstone project aims to build a machine-learning tool capable of precisely and accurately classifying cars by their make, model and year from images acquired from the Stanford car dataset using deep learning.
The data for this project was sourced from the Stanford car dataset. The files present in the CSV files folder were provided alongside the all the car images which can be downloaded from the kaggle link below, these CSV files remain unmodified and the clean test and train CSV files were obtained through running the clean_data_files.py.
The following order of notebooks represent the project flow from data visualiztion to data modelling.
- Capstone 2 Exploratory Data Analysis.ipynb
- Capstone 2 Modelling.ipynb
The following order of documents match the project flow from proposal to final report.
- Capstone 2 Project Proposal.pdf
- Capstone 2 Milestone Report.pdf
- Capstone 2 Consolidated Report.pdf
The slide deck below gives a brief overview of the entire project.
- Stanford Car Classification.pptx
https://www.kaggle.com/jutrera/stanford-car-dataset-by-classes-folder