Hello, I'm Mahdi! I'm a Machine Learning, Computer Vision, and Cloud Computing enthusiast, currently working at CNRS (Centre National de la Recherche Scientifique) in France.
With a solid foundation acquired from CentraleSupélec (France), holding a Master's degree in Control, Signal, and Image Processing, complemented by an Engineering Degree from Ecole Nationale Polytechnique (Algeria) in Control and Signal Processing, I've developed a profound understanding of the multifaceted aspects of machine learning and computer vision.
- Machine Learning
- Deep Learning
- Computer Vision
- Generative AI
- Natural Language Processing
- Cloud Computing
This repository is to act like a high level overview of the data science projects I've worked on. Each project's README.md
should act as a full description of the project, but I'll provide a short description here for convenience. All of these projects are in Python. Links are provided to projects whose code can be made public.
This project involves developing, training, and evaluating machine learning models (SVM, KNN, Random Forests, XGBoost) to predict BMI categories based on individual data, integrating the best model into a Flask API, and deploying it using Docker on AWS EC2, with the application accessible for interaction and predictions at a specified URL.
This project leverages a pre-trained VGGFace CNN model with transfer learning for binary facial classification, utilizing image augmentation and a weighted sampling strategy to handle class imbalance, and fine-tunes the model with specific training parameters for the detection of facial accessories and hair.
This project develops an automated pipeline using PyTorch and a pre-trained YOLOv7 model for detecting, cropping, and resizing faces in images to create standardized profile pictures, with a recommendation to download and view the potentially large files locally for optimal performance.
This project implements a UNet Convolutional Neural Network for the semantic segmentation of aerial satellite imagery, specifically targeting the ISPRS Potsdam dataset, to differentiate and classify distinct land cover types in urban landscapes.
Thank you for visiting my GitHub page. I hope you find the projects insightful and inspiring!
Mahdi.