Featured Projects

AI-powered assistant to help you with your daily tasks, powered by Llama 3.2 and different HuggingFace models.

While others focus on Cloud AI, We bring you an offline, privacy-respecting AI building tools

Learn vocabulary, practice pronunciation, and role-play with AI.

Build your resume, and mock interviews with AI, and get personalized feedback on your performance.

Effortless data labeling with AI support from YOLO, Segment Anything 1/2, MobileSAM, and more. Try it now!

Chat to your offline LLMs on CPU Only. 100% private, no data leaves your execution environment at any point.

P8Hub is a Docker Desktop Extension for hosting private AI services, making AI technologies accessible and secure for individuals and small teams.

Daisykit is an open source AI toolkit, aiming to provide an easy way to use AI in software projects on multiple platforms. Now we have C++, Python, and Android demos.

Push-up Counter using camera (MoveNet pretrained model) or proximity sensor. Tracking workout by day.

VIA Project is an open-source platform for self-driving cars, including source code and tutorials for learning image processing and computer vision by building autonomous vehicles, VIA Simulation - a highly customizable simulation for self-driving car testing, and VIA Makerbot - PCB for your mini self-driving car.

VN AIDr project is an open-source medical image processing solution for AI learners and hobbyists. On this platform, we design, train, and evaluate machine learning models and algorithms for medical image analysis and medical report autocompletion.

This project uses BlazePose - a SOTA model for real-time human pose detection, a single-frame action recognition model, and some signal processing algorithms to count push-ups from a video stream or webcam. I reimplemented BlazePose using Keras (source).

A driver assistant system that uses Jetson Nano as the hardware with four main functions: forward collision warning, lane departure warning, traffic sign recognition, and overspeed warning. I won The NVIDIA Jetson Project Of the Month Prize with this project and received a Jetson AGX Xavier Developer Kit.

This project helped my group achieve The First Prize in FPT Self-driving Car Challenge 2020 - University round at Hanoi University of Science and Technology. We built a ROS node with deep neural networks to control an autonomous car in a simulation environment.

I led a 4-member team to build a paper streaming solution for remote education. Our project got Second Place in SoICT - IBM Hackathon 2020 at HUST. I was responsible for algorithms to capture drawing strokes and handwritten text from a phone camera, filter, and create video streaming.

A modified Deep Head Pose model by adding new backbones (ShuffleNetV2, EfficientNet), and face landmark estimation.

A camera desktop application with funny face decorations and filters. In this project, I also integrated LBP Cascade and Haar Cascade models trained by myself to detect faces. This project supports both Linux and Windows.

This is a group project for FPT self-driving car challenge 2018. We used Watershed and Floodfill algorithms for lane segmentation, a color-based method for traffic sign detection, and HOG + SVM for sign classification.

We built a complete store management solution with a lot of features such as billing, management UI for bills, warehouse, suppliers, customers, finance, and employees. I worked on the desktop application.

My funny IoT project for our environment. This trash bin can classify bottles and other kinds of garbage into different compartments. I finished this project in only 1 day. I integrated and ran a pre-trained SSD-MobileNet V2 model on a Raspberry Pi to detect bottles.

Online BattleShip game using ReactJS for frontend, Flask for backend, and WebSocket for realtime communication. We also implemented a chatting system and friend list. I worked mostly on the frontend part (ReactJS).