Potter Hsu
Senior AI Engineer at Delta Electronics
Taoyuan City, Taiwan
Summary
👤
Senior🎓
Top SchoolPotter Hsu is a Senior AI Engineer with nine years of hands-on experience in computer vision, deep learning, and edge AI, currently driving AI initiatives at Delta Electronics. He has led government-funded research, built an endoscopic diagnostic system adopted by a major hospital, and created defect-detection platforms used by listed manufacturers. Potter is strong in productionizing models for constrained devices—quantizing to INT8/FP16, customizing CUDA operators, and deploying WebRTC/GStreamer streaming solutions with millisecond-scale latency and minimal CPU usage. His contributions to PyTorch object detection were accepted upstream, his GitHub projects have attracted hundreds of stars and forks, and he earned a Kaggle gold (top 0.5%) in a global detection challenge. Comfortable across C/C++, Python, embedded Linux, and cloud (AWS), he blends academic rigor with product-focused engineering and a track record of turning research prototypes into deployed systems.
9 years of coding experience
8 years of employment as a software developer
Master's degree, Computer Science and Information Engineering, Master's degree, Computer Science and Information Engineering at 中原大學
Github Skills (33)
convolutional-neural-networks10
digit10
pdf10
datasets10
number-recognition10
computer-vision10
backbone10
efficientnet10
arxiv10
pytorch9
python9
machine-learning9
torchvision9
tensorflow9
imagery9
Programming languages (4)
Github contributions (5)
potterhsu/easy-faster-rcnn.pytorch
Sep 2018 - Jul 2019
An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.
Contributions:7 releases, 97 commits, 71 pushes in 10 months
pytorcharxivpdfefficientnetdeep-learning
potterhsu/SVHNClassifier-PyTorch
Apr 2017 - Mar 2019
A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
Contributions:7 commits, 15 pushes, 1 branch in 1 year 11 months
visual-recognitionarxivpdfdigitconvolutional-neural-network
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.