Skip to content
View mohamedkhayat's full-sized avatar

Highlights

  • Pro

Block or report mohamedkhayat

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse

Pinned Loading

  1. transformers-for-fruit-object-detection-internship transformers-for-fruit-object-detection-internship Public

    This internship project centers on training Vision Transformer models (RT-DETRv2) for fruit object detection using YOLO-format data. The pipeline is fully modular, supports mixed precision and W&B …

    Python 3

  2. DIYNeuralNet DIYNeuralNet Public

    A lightweight deep learning framework implemented from scratch using NumPy/CuPy. supports customizable architectures, forward and back propagation, dropout, He/Glorot init, and mini-batch training.…

    Jupyter Notebook 6

  3. Reinforcement-Learning-Trees Reinforcement-Learning-Trees Public

    A Python implementation of Reinforcement Learning Trees (Zhu et al., 2015). RLT leverages "look-ahead" reinforcement learning to master high-dimensional, sparse data where standard Random Forests f…

    Jupyter Notebook 7 2

  4. Multimodal-Technical-RAG-Agent Multimodal-Technical-RAG-Agent Public

    Multimodal agentic assistant for technical workflows — analyze circuit diagrams, extract components, and chat with context. Built with LangGraph · FastAPI · Next.js.

    TypeScript

  5. modern-training-pipeline modern-training-pipeline Public

    This project is a modern, modular, and production-ready deep learning training pipeline built with PyTorch. It’s designed for image classification tasks and supports advanced tools like Hydra for c…

    Python 3

  6. face-auth-pipeline face-auth-pipeline Public

    A real-time face verification system built with PyTorch and FastAPI, featuring a custom Hybrid Triplet Loss with margin scheduling, ResNet-50 backbone, MTCNN detection, and W&B integration for trai…

    Python 4