Lin Jian
PhD Candidate
Xi'an, Shaanxi, China
Summary
🤩
Rockstar🎓
Top SchoolLin Jian is a PhD candidate and machine learning engineer based in Xi'an with six years of hands-on experience optimizing deep learning models for production. He specializes in accelerating object detection pipelines, notably integrating TensorRT across multiple YOLO versions and adding INT8 precision and NMS plugin support to boost inference performance. His open-source work on a multi-version YOLO TensorRT repo demonstrates practical expertise in model conversion, video detection, and performance engineering. Trained at Northwestern Polytechnical University, he blends academic rigor with pragmatic engineering to close the gap between research prototypes and deployable systems. Colleagues describe him as detail-oriented in low-level optimization while comfortable navigating cross-version compatibility challenges.
6 years of coding experience
Northwestern Polytechnical University
Github Skills (9)
tensorrt10
computer-vision10
yolov510
onnx10
yolov710
python9
object-detection9
machine-learning8
pycuda7
Programming languages (10)
Github contributions (5)
Linaom1214/TensorRT-For-YOLO-Series
Nov 2021 - Jan 2023
tensorrt for yolo series (YOLOv11,YOLOv10,YOLOv9,YOLOv8,YOLOv7,YOLOv6,YOLOX,YOLOv5), nms plugin support
Role in this project:
ML Engineer
ML EngineerContributions:7 releases, 1 review, 67 commits in 1 year 1 month
Contributions summary:Lin primarily focused on integrating TensorRT for accelerating YOLO models. Their contributions involved modifying existing code to support various YOLO versions (v5, v6, v7, and others listed in the repository description), converting models to TensorRT engines, and incorporating NMS plugins for object detection. They also implemented video detection capabilities and added support for INT8 precision, indicating a focus on optimizing model performance.
tensorrtyolov5yolov7yolov6yolox
Linaom1214/Infrared-detect-by-segmentation
Jan 2022 - Jun 2022
红外弱小目标检测算法 Infrared Target Detection by Segmentation (Deeplearing Method)
Contributions:2 releases, 15 commits, 20 pushes in 5 months
segmentationunet-image-segmentationfcninfrared
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.