swe/ml engineer

github

Muratcan Laloglu  • Peerlist

Moondream VLM-powered labeler one-click YOLO export

MoonLabel

This project aims to develop an efficient and accurate system for brain tumor segmentation using deep learning techniques. Leveraging the powerful U-Net architecture, we build a model capable of precisely identifying and segmenting brain tumors from MRI images. To make this technology accessible and user-friendly, we integrate the segmentation model into a web application using FastAPI, allowing users to interact with the model through a simple and intuitive interface.

Brain Tumor Segmentation with U-Net Architecture

This project involves training a deep learning model to detect whether a person is wearing a mask or not in real-time using a live video stream. The model is trained using the TensorFlow framework and utilizes the MobileNetV2 architecture for feature extraction. The face detection is performed using a pre-trained face detection model.

Face Mask Detection

This project leverages LangChain, OpenAI, ChromaDB, and Gradio to create a question-answering system for any YouTube videos. By inputting questions related to the content of the provided videos, users receive answers along with a corresponding YouTube video.