🚀 MLOps & Computer Vision Pipeline

A comprehensive machine learning engineering project demonstrating automated CI/CD workflows alongside real-time Computer Vision & Object Tracking applications.

---

📌 Project Overview

This repository integrates modern MLOps best practices with end-to-end computer vision applications:

• MLOps Integration: Automated code linting, unit testing, and Docker containerization using GitHub Actions.
• Computer Vision Application: Real-time object detection and video tracking powered by YOLOv8 and OpenCV.

---

🛠️ Tech Stack & Tools

• Programming Language: Python 3.11
• Computer Vision: YOLOv8 (Ultralytics), OpenCV, Pillow
• Web Framework: Streamlit
• MLOps & DevOps: Docker, GitHub Actions
• Testing & Quality: Pytest, Flake8

---

🌟 Key Features

1. Object Detection & Tracking: Detects items in images and performs real-time ID-based object tracking in uploaded videos.
2. Automated CI/CD: GitHub Actions triggers automated workflows on every push or pull request to the main branch.
3. Containerization: Fully containerized setup via Dockerfile for seamless deployment across environments.

---

🚀 Getting Started Locally

Prerequisites

Make sure you have Python installed along with Git.

1. Clone the Repository

git clone [https://github.com/dan99ger/tests.git](https://github.com/dan99ger/tests.git)
cd tests