Francis Burnet – AI Engineering Portfolio

Capstone portfolio spanning AI engineering, applied data science, machine learning, and deep learning.

Francis Burnet headshot

Automating Port Operations Evidence Map

Automating Port Operations vessel infographic
Capstone Summary

Vessel classifier page with the notebook, outputs, and saved metrics laid out in a clean project template.

Project at a glance

This page presents the vessel classifier, the notebook that produced it, and the saved outputs that support the published result.

Run in Colab View Notebook Open Metrics JSON

Objective

The goal is to classify vessels from images using the published notebook workflow and the saved model comparison outputs.

The final result favors transfer learning, and the page keeps the notebook, evidence, and metrics easy to open from one place.

Notebook and Evidence

Requirements

Verbatim task map

The requirement list that drives the notebook sections.
Evidence manifest

Run outputs and artifacts

Saved notebooks, plots, metrics, and supporting notes.
Custom CNN plot

Training curves

Baseline loss and accuracy history.
Custom CNN plot

Confusion matrix

Class-by-class review heatmap for the baseline lane.
Transfer learning plot

Training curves

MobileNetV2 training history for the winning lane.
Comparison summary

Metrics JSON

Saved model comparison and held-out accuracy values.
Comparison notes

Final observation

The notebook note that records why transfer learning is preferred.
Notebook access

Source notebook

Open the notebook source or launch it in Colab to rerun the workflow.

Run in Colab View Notebook

Outputs

Transfer learning is the published recommendation.

Model result

The comparison summary records 86.32% held-out accuracy for transfer learning versus 44.30% for the custom CNN.

Final note

The observation text records why transfer learning is preferred and keeps the project decision explicit.

Open comparison notes Open notebook source