I’m Mostafa Bahaa — a Machine Learning Engineer and Computer Engineering student passionate about building intelligent systems, experimenting with deep learning models, and solving real-world problems using AI.
My main focus areas are Computer Vision (CV) and Natural Language Processing (NLP). I work with PyTorch, TensorFlow, PyTorch Lightning, and I enjoy exploring fine-tuning techniques, efficient training workflows, and model optimization.
I’ve worked on projects including depth estimation, image classification, group activity recognition, video understanding, and building clean, scalable ML pipelines. I’m also interested in research and open-source contributions, especially in ecosystems like NumFOCUS and annotation tools like CVAT.
I aim to create ML systems that are accurate, efficient, reproducible, and ready for real-world deployment.
- Fayoum- Egypt
Highlights
- Pro
Pinned Loading
-
hdtm-group-activity-recognition
hdtm-group-activity-recognition PublicRe-implementation and extension of the CVPR 2016 paper, “A Hierarchical Deep Temporal Model for Group Activity Recognition.” This project reproduces the original two-stage LSTM architecture in PyTo…
Python
-
-
depth_map_prediction_from_single_image
depth_map_prediction_from_single_image PublicThis project is a reimplementation of the paper “Depth Map Prediction from a Single Image using a Multi-Scale Deep Network” by Eigen et al., . The work explores how deep convolutional neural networ…
Python 1
-
multi-modal_language_model_pali-gemma
multi-modal_language_model_pali-gemma PublicThis project is my PyTorch reproduction of PaliGemma, a compact 3B vision–language model that integrates SigLIP vision features with a Gemma decoder. I implemented the full multimodal pipeline from…
Python
-
mediguide_MVP
mediguide_MVP PublicAI-powered accessibility app that helps blind and low-vision users manage medications safely. It uses image recognition, voice interaction, and AWS-based cloud verification to identify and confirm …
TypeScript
-
If the problem persists, check the GitHub status page or contact support.