An open-source RAG-based tool for chatting with your documents.

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

MOT(multi object tracking ) by detection, follows ABMOT and SimpleTrack

(IROS 2020, ECCVW 2020) Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics"

LLM training in simple, raw C/CUDA

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

这是一个blip-pytorch简化的代码，适用于了解Attention与Transformer的结构。

A collection of pre-trained, state-of-the-art models in the ONNX format

Implementation of popular deep learning networks with TensorRT network definition API

🙃 A delightful community-driven (with 2,400+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

OpenPCDet代码分析与注释

yolov8 tensorrt 加速

基于地面假设的单目测距，核心代码文件

🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

Interactive Map Correction for 3D Graph SLAM

LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Visualizing Yolov5's layers using GradCam

Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

Android Contacts

该工作由电子科技大学陈昂、刘俊凯、夏子寒同学完成。我们提出可以使用深度学习的方案对中国车牌进行检测和识别。我们提出使用YOLOv3网络进行车牌检测，然后创新性地对检测后的车牌使用空间变换网络STN加以校正，最后使用LPRNet网络进行车牌的字符与数字识别。目前实测结果，在老师提供的45张数据集上，我们的YOLOv3网络检测准确率（IOU）达到98.2%，深度学习级联网络识别准确率为95.6%…