Zhenhuan Wei
 |
Undergraduate |
About me
I am now an undergraduate in Xidian University, majoring in software engineering. I'm now learning Computer Vision, ML/DL Systems, CUDA programming and Deep Learning framework development.
Education
Xi'an Jiaotong University, Master in Software Engineering, Sep. 2023 - Now
Xidian University, Bachelor in Software Engineering, Sep. 2019 - June 2023
Research
My research interests include
Computer Vision
Machine Learning / Deep Learning Systems
High Performance Computation
Awards
Oct. 2022, The National Scholarship(top 0.7%)
May 2022, Robomaster University AI Challenge(RMUA), International Third Prize
Dec. 2021, The Chinese Mathematical Competitions(CMC), Second Prize
Aug. 2021, Robomaster University Series, First Prize in University League, Second Prize in University Championship
Oct. 2020, The Contemporary Undergraduate Mathematical Contest in Modeling(CUMCM), Provincial First Prize
Projects
MindCV Component Development [details]
MindCV is an open-source toolbox for computer vision research and development based on MindSpore. It collects a series of classic and SoTA vision models, such as ResNet and SwinTransformer, along with their pre-trained weights and training strategies. SoTA methods such as auto augmentation are also provided for performance improvement.
Robot Self-aiming System Based On OpenCV
This project is a robot self-aiming system developed by me and my team during the preparation of Robomaster competition. Based on OpenCV visual library, this project realizes a system integrating target search, coordinate calculation, automatic aiming, target tracking and other functions by analyzing the images obtained by the camera carried by the robot.
In this project, I'm responsible for the development of EdgeNeXt. I rewrite the code using Mindspore, then train the model, and finally provide the model script, training recipe and training weights.