Wu Maojia's Projects
基于LLM实现CHIP2021-Task3中文临床术语标准化任务,准确率约70%。
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.
This project reproduces the book Dive Into Deep Learning (https://d2l.ai/), adapting the code from MXNet into PyTorch.
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。
微信小程序《恒计划》,利用艾宾浩斯遗忘曲线智能帮助用户进行需要大量记忆的学科的学习、记忆、背诵、复习等的小程序。使用了微信云开发。
瓜大计组实验课微指令程序简单翻译工具
Motion planning algorithms commonly used on autonomous vehicles. (path planning + path tracking)
ROS Navigation stack. Code for finding where the robot is and how it can get somewhere else.
Motion planning and Navigation of AGV/AMR:ROS planner plugin implementation of GBFS, Dijkstra, A*, JPS, LPA*, D* (Lite), (Lazy) (S-) Theta*, (Informed) RRT (*) (-Connect), ACO, Voronoi, PID, DWA, APF, RPP, LQR, MPC, DDPG, Polynomia, Bezier, (Cubic) (B) Spline, Dubins, Reeds-Shepp, Fem-Pos etc.
Python sample codes for robotics algorithms.
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
用QT实现的桌面端聊天室软件,含服务端和客户端,使用经过SSL加密的TCP通信和SQLite数据库管理系统。
Motion planning and Navigation of AGV/AMR:ROS planner plugin implementation of A*(A Star), JPS(Jump Point Search), D*(D Star), LPA*, D* Lite, RRT, RRT*, RRT-Connect, Informed RRT*, PID, DWA etc.
A Rviz Plugin used in path visualization and curve generation, which is helpful for qualitative experiments on path planning and curve optimization.
Multiple approaches for completing RVSC (Right Ventricle Segmentation Challenge), including PyTorch implementations of UNet with attention, UNet++, U2Net.
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Webots Robot Simulator
Yolov5 deepsort inference,使用YOLOv5+Deepsort实现车辆行人追踪和计数,代码封装成一个Detector类,更容易嵌入到自己的项目中
🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 930+kb (int8) and 1.7M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~