Hùng Việt

Artificial Intelligence Engineer at VNPT IT

Hanoi, Vietnam
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Hùng Việt is an Artificial Intelligence Engineer based in Hanoi with 10 years of experience building and optimizing computer vision models for production. Having worked at Bkav and now VNPT IT, he blends practical industry experience with a master's-level CS background from Hanoi University of Science and Technology. He has hands-on expertise refining YOLO implementations—contributing backbone, loss function, and architecture improvements to a popular TensorFlow YOLOv4 repository aimed at deployment to TensorRT and TFLite. Known for a pleasant collaborative style, he focuses on model performance and deployment, bridging research-grade improvements with real-world constraints in embedded and cloud environments.
code10 years of coding experience
job5 years of employment as a software developer
bookBachelor's degree, Computer Software Engineering, Bachelor's degree, Computer Software Engineering at Hanoi University of Science and Technology
stackoverflow-logo

Stackoverflow

Stats
1reputation
2kreached
0answers
1question
github-logo-circle

Github Skills (10)

object-detection10
computer-vision10
tensorflow10
python10
yolov410
neural-network9
convolutional-neural-networks9
tflite8
tensorrt8
flutter6

Programming languages (1)

Python

Github contributions (5)

github-logo-circle
YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
Role in this project:
userML Engineer
Contributions:114 commits, 15 PRs, 97 pushes in 3 months
Contributions summary:Hùng primarily contributed to updating the YOLOv4 object detection model within the repository. Their commits focused on modifying the backbone architecture and loss functions, indicating an effort to improve the model's performance. The changes involved adjusting convolutional layers, residual blocks, and upsampling layers, as well as implementing a new CIoU loss function. These modifications suggest the user was focused on model optimization and refinement for the YOLOv4 implementation.
tensorflow-2tensorflow-2-0tinyweightsyolov4-tiny
hunglc007/yolov5

Nov 2020 - Feb 2021

YOLOv5 in PyTorch > ONNX > CoreML > TFLite
Contributions:2 PRs, 7 pushes in 3 months
pytorchdeep-learningobject-detectiononnxpytorch-onnx
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Hùng Việt - Artificial Intelligence Engineer at VNPT IT