Shaohui Ruan
Machine Learning Engineer
Shanghai, China
Summary
🤩
RockstarShaohui Ruan is a Machine Learning Engineer based in Shanghai with nine years of hands-on experience focused on computer vision and practical ML solutions. He contributes to open-source projects like a TensorFlow-based CTPN text-detection repo, where he improved data pipelines, fixed loss-function bugs, and optimized inference with CUDA NMS and bi-LSTM integration. Comfortable across data preparation, model debugging, and performance tuning, he bridges research techniques and production needs to deliver reliable vision models. Known for meticulous training-data engineering, he brings a pragmatic eye for converting messy datasets into VOC-format pipelines that scale.
9 years of coding experience
Github Skills (7)
data-preprocessing10
computer-vision10
tensorflow10
text-detection10
python10
image-processing10
numpy10
Programming languages (2)
Github contributions (5)
eragonruan/text-detection-ctpn
Sep 2017 - Feb 2019
text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network
Role in this project:
ML Engineer
ML EngineerContributions:3 releases, 67 commits, 24 PRs in 1 year 5 months
Contributions summary:Shaohui primarily focused on preparing and refining training data for text detection, as evidenced by the "prepare training data" commit messages and modifications to data processing scripts. They implemented code to convert and build data into the VOC format, which is a standard for object detection. Furthermore, the user fixed bugs within the loss function and optimized the model by incorporating CUDA nms and bi-lstm.
id-cardctpnocrdetectrobust-reading
eragonruan/eragonruan.github.io
May 2017 - Jun 2022
Contributions:52 pushes, 1 branch, 90 comments in 5 years 2 months
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.