This repository documents my hands-on learning process in computer vision, focusing on:

• YOLOv8 — object detection workflows, parameter exploration, and result analysis
• OpenCV — fundamental image processing techniques and experiments

It combines code, notes, datasets, and generated artifacts to form a reproducible learning pipeline.

.
├── src/ # Source code
│ ├── Yolo/ # YOLOv8 experiments and scripts
│ └── OpenCV/ # Image processing notebooks
│
├── notebook/ # Structured learning notes (Markdown)
│ ├── Yolo/
│ └── OpenCV/
│
├── data/ # Input datasets (images / videos)
│
├── artifacts/ # Generated outputs from experiments
│ ├── OpenCV/ # Processed images
│ └── Yolo/ # Detection results
│
├── models/ # Model weights (e.g., yolov8n.pt)
│
├── runs/ # Ultralytics default output directory
│
├── pyproject.toml # Dependency management (uv)
└── README.md

• Reproducible YOLOv8 inference workflows
• Parameter sensitivity experiments
• OpenCV preprocessing demonstrations
• Organized Markdown notes for theory + practice
• Clean separation of data → code → artifacts

• Python >= 3.12
• torch, torchvision
• ultralytics (YOLOv8)
• OpenCV
• matplotlib
• jupyterlab

Install dependencies:

uv sync

Run a YOLO demo

uv run src/Yolo/01demo/main.py

Explore OpenCV Jupyter experiments

jupyter notebook src/OpenCV/