Pinned Repositories
DynaSLAM
基于ORB-SLAM2修改 动态环境建模 dynamic environments for monocular, stereo and RGB-D setups
living
自我进化，个人、家庭、工作三位一体 爱 健康 财富 是人生值得追求的东西！人生不过是一段体验。我们都是时间的囚徒，活在当下。有趣！有料！
Mathematics
数学知识点滴积累 矩阵 数值优化 神经网络反向传播 图优化 概率论 随机过程 卡尔曼滤波 粒子滤波 数学函数拟合
MVision
机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶
ORB_SLAM2_SSD_Semantic
动态语义SLAM 目标检测+VSLAM+光流/多视角几何动态物体检测+octomap地图+目标数据库
pwc
有代码的论文 Papers with code. Sorted by stars. Updated weekly.
Ros
机器人操作系统ROS 语音识别 语义理解 视觉控制 gazebo仿真 雷达建图导航
ROS-Academy-for-Beginners
**大学MOOC《机器人操作系统入门》课程代码示例
semantic_slam
CNN (PSPNet) + ORB_SLAM2 语义SLAM Real time semantic slam in ROS with a hand held RGB-D camera
ShiYanLou
学习C & C++ & python&汇编语言 LLVM编译器 数据结构 算法 操作系统 单片机 linux 面试
Ewenwan's Repositories
Ewenwan/ShiYanLou
学习C & C++ & python&汇编语言 LLVM编译器 数据结构 算法 操作系统 单片机 linux 面试
Ewenwan/aipath
AI学习之路
Ewenwan/onnc
Open Neural Network Compiler
Ewenwan/AscendCContest
参加华为AscendC算子编程比赛的代码
Ewenwan/AscendCL_GEMM
Ewenwan/BXC_VideoAnalyzer_v4
基于C++开发的视频行为分析系统v4系统，可以在不用考虑音视频开发，编解码开发，界面开发等情况下， 只需要训练自己的模型，开发自己的算法插件，就可以轻松实现出任何想要的视频行为检测，比如周界入侵，烟火检测，打架，斗殴，跌倒，人群聚集，电动车，垃圾箱，抽烟，攀爬，离岗睡岗，安全帽，充电桩，工作服， 疲劳检测，交通拥堵等等。
Ewenwan/chatchat-knowledgebase
属于每个人的公众号”查特查特“上线啦！新问题、新方法、新发现，欢迎提PR！
Ewenwan/DeepLearningSystem
Deep Learning System core principles introduction.
Ewenwan/EPro-PnP
[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
Ewenwan/ESJZone-novel-mirror
ESJZone 的小說備份
Ewenwan/fmath
fast log and exp functions for x86/x64 SSE
Ewenwan/gpt-tokens
What are learned in tiktoken?
Ewenwan/GroundingDINO
Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Ewenwan/How_to_optimize_in_GPU
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.
Ewenwan/isp
camera pipeline
Ewenwan/llama
Inference code for LLaMA models
Ewenwan/ml_toolset
Ewenwan/MLIR-AscendC
Ewenwan/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Ewenwan/movenet
Google's Next Gen Pose Estimation in PyTorch
Ewenwan/nolebase
A place to record memories, knowledge and ideas | 记录回忆，知识和畅想的地方
Ewenwan/onnx-tool
A parser, editor and profiler tool for ONNX models.
Ewenwan/opencv-mobile
opencv-mobile 通过调整编译参数，删减部分opencv源码，来最小化编译的 opencv 库提供了 opencv 常用的功能，如读写图片，处理，矩阵操作等等 版本与上游同步，无第三方依赖在绝大多数情况下，以 1/10 的体积无痛替换官方 opencv，尤其适合对体积有特殊要求的移动端和嵌入式环境
Ewenwan/openISP
Image Signal Processor
Ewenwan/playground
code for fun
Ewenwan/PyDSL
A Python subset for a better MLIR programming experience
Ewenwan/TheRoadOfSO
学习安全运营的记录 | The knowledge base of security operation
Ewenwan/tiny-gpu
A minimal GPU design in Verilog to learn how GPUs work from the ground up
Ewenwan/True_Artificial_Intelligence
真AI人工智能
Ewenwan/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.