Computer Vision Project ( Lung X-ray Classification )

I developed a complete end-to-end Deep Learning pipeline for automated Lung X-ray image classification. The project focuses on building a production-ready system rather than just training a model.

? Project Overview

The system classifies chest X-ray images using Convolutional Neural Networks (CNNs) to assist in detecting lung-related conditions.

Unlike basic notebook-based projects, this implementation follows a structured, modular, and production-oriented architecture.

? What I Implemented

Built a modular ML pipeline including:

Data ingestion

Data validation

Data transformation

Model training

Model evaluation

Structured the project using clean architecture principles:

components

pipeline

config_entity

artifact_entity

Logging & custom exception handling

Containerized the application using Docker.

Integrated CI/CD workflows using GitHub Actions.

Used BentoML for model serving and deployment readiness.

Configured AWS CLI for cloud integration and deployment setup.

Implemented testing using tox and separate dev requirements.

? Tech Stack

Python

TensorFlow / Deep Learning

Docker

BentoML

AWS

GitHub Actions (CI/CD)

Modular MLOps structure

? Key Highlights

Production-ready structure (not just a training notebook)

Clean codebase with logging and error handling

Deployment-ready setup

Scalable architecture for future extension

Reproducible environment setup

? Outcome

This project demonstrates my ability to move beyond experimentation and build a structured, deployable Deep Learning system following MLOps best practices.