Skip to content
View ahmedshafiq12's full-sized avatar

Block or report ahmedshafiq12

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ahmedshafiq12/README.md

👋 Hi, I’m Ahmed Shafiq

Hi

💫 About Me:

🎯 Computer Vision Engineer | AI Enthusiast | Deep Learning Specialist I'm a Computer Vision Engineer with over two years of experience in AI and deep learning. My work primarily focuses on building and optimizing computer vision models for real-world applications, specializing in tasks such as object detection, real-time video analysis, and edge deployment. I have hands-on experience with various AI frameworks and enjoy tackling complex challenges to create impactful solutions.

📂 Projects:

Watch Demo Watch Demo

A computer vision-based tennis and MMA smart coach that extracts statistics and provides recommendations from match videos, using advanced techniques like TrackNet, custom-built CNNs, YOLO, image processing, and homography.

Watch Demo

Built a multi-modal assistant integrating computer vision, speech recognition, and NLP. Fine-tuned models for Egyptian dialect recognition and utilized Ccomputer Vision for emotion detection, enhancing user interaction through personalized responses.

VisionStats (Graduation Project):

Watch Demo

A tool to extract detailed game statistics, utilizing YOLOv3 for high-precision detection of players, ball, and goal, along with key statistics like distance covered, possession, shots, and passes.

Watch Demo

Detects and reads license plates in video streams, associating detected plates with vehicles using a custom-trained model and PaddleOCR for content recognition.

Results

This project implements a Pix2Pix GAN using PyTorch to generate maps from satellite images.

Watch Demo

Implemented a YOLOv8-based system to monitor crowd behavior in real-time, measuring social distancing violations with customizable visualization settings.

📫 Connect with Me Email: ahmed.mshafiq77@gmail.com

🌐 Socials:

LinkedIn Medium Upwork Kaggle

💻 Tech Stack:

Python C++ C# Java Keras NumPy Pandas Plotly PyTorch scikit-learn SciPy TensorFlow GIT LINUX

Pinned Loading

  1. Egyptian-Arabic-Virtual-Assistant Egyptian-Arabic-Virtual-Assistant Public

    Welcome to Hakeem, your new Egyptian-Arabic Virtual Assistant! Hakeem is designed to simplify your life. With advanced features and natural language processing, it helps manage tasks, provides reco…

    Python 8 4

  2. License-Plate-Recognition-System License-Plate-Recognition-System Public

    The License Plate Recognition (LPR) System is a computer vision project designed to detect and recognize license plates in images or video streams.

    Python 6

  3. Social-Distancing-Detector Social-Distancing-Detector Public

    This project implements a real-time Social Distancing Detector that can identify the distance between individuals in a crowd. It utilizes the YOLOv8 model for person detection and scipy for distanc…

    Python

  4. Color-Identification Color-Identification Public

    Implementing an image color detector which identifies all the colors in an image

    Python 1

  5. Building-Neural-Network-From-scratch Building-Neural-Network-From-scratch Public

    Jupyter Notebook

  6. MNIST-digit-reconstruction-GAN MNIST-digit-reconstruction-GAN Public

    Python