|
1 | | -<p align="center"> |
2 | | - <img src="https://cdn.nlark.com/yuque/0/2020/png/726405/1578322228096-7dba507c-67f2-463b-a280-791bebed0418.png?x-oss-process=image%2Fresize%2Cw_1492" width="900"> |
3 | | - <br> |
4 | | - Linux, AI, Python, GUI: 4-in-1 Environments Running on Android. [中文版] <a href='README.md'>[English]</a> |
5 | | -</p> |
6 | | -<p align="center"> |
7 | | - <a href="https://travis-ci.org/lc-soft/LCUI"><img src="https://travis-ci.org/lc-soft/LCUI.png?branch=master" alt="Build Status"></a> |
8 | | - <img src="https://img.shields.io/badge/coverage-100%25-brightgreen" alt="Coverage Status"> |
9 | | - <a href="http://opensource.org/licenses/MIT"><img src="https://img.shields.io/github/license/lc-soft/LCUI.svg" alt="License"></a> |
10 | | - <a href="https://github.com/aidlearning/AidLearning-FrameWork/releases"> |
11 | | - <img src="https://img.shields.io/github/v/tag/aidlearning/AidLearning-FrameWork" > </a> |
12 | | -<img src="https://img.shields.io/github/forks/aidlearning/AidLearning-FrameWork?style=flat" alt="Fork"> |
13 | | -<img src="https://img.shields.io/github/stars/aidlearning/AidLearning-FrameWork?style=flat" alt="star"> |
14 | | -<img src="https://img.shields.io/github/last-commit/aidlearning/AidLearning-FrameWork?style=plastic" alt="commit"> |
15 | | -</p> |
16 | | - |
17 | | -[AidLearning](http://www.aidlearning.net)是一个移动端的AI开发平台，支持所有主流深度学习神经网络的开发框架和工具。 |
18 | | - |
19 | | -它采用了独特的cpu+gpu加速技术，内置的tflite_gpu模块能够赋予深度学习算法性能上的大幅度提升。同时，AidLearning为开发者提供了VSCode、Jupiter Notebook等开发工具。 |
20 | | - |
21 | | -目前，AidLearning已在各大App应用中心上线，下载启动次数超过200万。 |
22 | | - |
23 | | -<img src="http://www.aidlearning.net/showdoc/server/index.php?s=/api/attachment/visitFile/sign/4a72d62cec051582170e99b3584da67c&showdoc=.jpg" width="960" /> |
24 | | - |
25 | | -<img src="http://www.aidlearning.net/showdoc/server/index.php?s=/api/attachment/visitFile/sign/846b7bfbf009ef144372943dc251c848&showdoc=.jpg" width="960" /> |
26 | | - |
27 | | -## 开始使用 |
28 | | -点击以下链接即可下载最新的安装包（约20M）： |
29 | | - |
30 | | -[【AidLearning v0.87F3】](https://github.com/aidlearning/AidLearning-FrameWork/releases/download/v0.87F3/aidv0.87F3.apk) [【国内镜像】](https://download.s21i.faiusr.com/23668748/0/0/ABUIABBKGAAgsdH_gQYo-PrV4wU?f=aidv0.87F3.apk&v=1614784689) |
31 | | - |
32 | | -- [安装配置](https://www.aidlearning.net/showdoc/web/#/5?page_id=26) |
33 | | -- [开发文档](https://www.aidlearning.net/showdoc/web/#/5?page_id=23) |
34 | | -- [示例代码](https://www.aidlearning.net/showdoc/web/#/5?page_id=40) |
35 | | - |
36 | | -## 架构设计 |
37 | | - |
38 | | -AidLearning FrameWork可以分为Linux环境和AI编程平台两部分。 |
39 | | - |
40 | | -Linux环境由Terminal和Desktop构成。前者基于Android底层Linux kernel和busybox命令包构建了完整Linux的环境。和原生Linux系统类似，用户可以通过apt命令安装任何依赖包；后者基于web构建了图形化操作桌面，用户可以直接通过触摸屏进行操作。 |
41 | | - |
42 | | -AidLearning同时提供了云桌面功能，桌面端可以通过局域网访问手机内容。 |
43 | | - |
44 | | -AI编程平台由深度学习框架和Python可视化编程框架构成。前者包含了所有目前的主流深度学习框架，负责模型的加载、计算图的调度，各计算的内存分配、Op实现。后者构建了Python可视化快速开发平台，不仅可以实时运行、调试Python代码。 |
45 | | - |
46 | | -用户可以通过AidLearning内置的[apk开发工具](https://www.aidlearning.net/showdoc/web/#/5?page_id=31)设计应用界面、一键编译打包，快速开发人工智能应用。 |
47 | | - |
48 | | -## 内置工具 |
49 | | -- [AidCode](https://www.aidlearning.net/showdoc/web/#/5?page_id=28) |
50 | | -- [文件管理器](https://www.aidlearning.net/showdoc/web/#/5?page_id=27) |
51 | | -- [云桌面icloud](https://www.aidlearning.net/showdoc/web/#/5?page_id=29) |
52 | | -- [Blocky积木编程](https://www.aidlearning.net/showdoc/web/#/5?page_id=34) |
53 | | -- [Service-依赖包、系统服务](https://www.aidlearning.net/showdoc/web/#/5?page_id=33) |
54 | | -- [Apkbuild](https://www.aidlearning.net/showdoc/web/#/5?page_id=31) |
55 | | -- [Jupyter notebook](https://www.aidlearning.net/showdoc/web/#/5?page_id=30) |
56 | | -- [X模式--兼容开发模式](https://www.aidlearning.net/showdoc/web/#/5?page_id=36) |
57 | | -- [VSCode](https://www.aidlearning.net/showdoc/web/#/5?page_id=32) |
58 | | -- [XFce4-Linux原生桌面](https://www.aidlearning.net/showdoc/web/#/5?page_id=35) |
59 | | - |
60 | | -## 贡献与参与 |
61 | | -- [贡献代码](https://www.aidlearning.net/showdoc/web/#/5?page_id=39) |
62 | | -- [系统扩展](https://www.aidlearning.net/showdoc/web/#/5?page_id=38) |
63 | | -- [更新日志](https://www.aidlearning.net/showdoc/web/#/5?page_id=24) |
64 | | - |
65 | | -## 交流与反馈 |
66 | | - |
67 | | -- [AidLearning官网](http://www.aidlearning.net) |
68 | | -- [AidLearning官方论坛](http://new.aidlearning.net/) |
69 | | - |
70 | | -<details> |
71 | | -<summary>QQ交流群</summary> |
72 | | -<img src="https://i.loli.net/2020/04/11/TtfxFj2rnkB7ZVM.png" height="256"/> |
73 | | -</details> |
74 | | - |
75 | | -## License |
76 | | -- [GPL 3.0](license.md) |
77 | | - |
78 | | -## 致谢 |
79 | | -AidLearning参与人员：bill、flay、gondon、willam、gugu、yoline777、qidiso、yuge等。 |
80 | | - |
81 | | -下列项目： |
82 | | - |
83 | | -* VTE (libvte): Terminal emulator widget for GTK+, mainly used in gnome-terminal. [Source](https://github.com/GNOME/vte), [Open Issues](https://bugzilla.gnome.org/buglist.cgi?quicksearch=product%3A%22vte%22+), and [All (including closed) issues](https://bugzilla.gnome.org/buglist.cgi?bug_status=RESOLVED&bug_status=VERIFIED&chfield=resolution&chfieldfrom=-2000d&chfieldvalue=FIXED&product=vte&resolution=FIXED). |
84 | | -* iTerm 2: OS X terminal application. [Source](https://github.com/gnachman/iTerm2), [Issues](https://gitlab.com/gnachman/iterm2/issues) and [Documentation](http://www.iterm2.com/documentation.html) (which includes [iTerm2 proprietary escape codes](http://www.iterm2.com/documentation-escape-codes.html)). |
85 | | -* Konsole: KDE terminal application. [Source](https://projects.kde.org/projects/kde/applications/konsole/repository), in particular [tests](https://projects.kde.org/projects/kde/applications/konsole/repository/revisions/master/show/tests), [Bugs](https://bugs.kde.org/buglist.cgi?bug_severity=critical&bug_severity=grave&bug_severity=major&bug_severity=crash&bug_severity=normal&bug_severity=minor&bug_status=UNCONFIRMED&bug_status=NEW&bug_status=ASSIGNED&bug_status=REOPENED&product=konsole) and [Wishes](https://bugs.kde.org/buglist.cgi?bug_severity=wishlist&bug_status=UNCONFIRMED&bug_status=NEW&bug_status=ASSIGNED&bug_status=REOPENED&product=konsole). |
86 | | -* hterm: JavaScript terminal implementation from Chromium. [Source](https://github.com/chromium/hterm), including [tests](https://github.com/chromium/hterm/blob/master/js/hterm_vt_tests.js), and [Google group](https://groups.google.com/a/chromium.org/forum/#!forum/chromium-hterm). |
87 | | -* xterm: The grandfather of terminal emulators. [Source](http://invisible-island.net/datafiles/release/xterm.tar.gz). |
88 | | -* Connectbot: Android SSH client. [Source](https://github.com/connectbot/connectbot) |
89 | | -* Android Terminal Emulator: Android terminal app which Termux terminal handling is based on. Inactive. [Source](https://github.com/jackpal/Android-Terminal-Emulator). |
90 | | -* Termux: Android terminal and Linux environment - app repository. [Source](https://github.com/termux/termux-app). |
91 | | -* remi:Python REMote Interface library. Platform independent. In about 100 Kbytes, perfect for your diet.[Source](https://github.com/dddomodossola/remi). |
92 | | -* [Caffe](https://github.com/BVLC/caffe) |
93 | | -* [Tensorflow](https://github.com/tensorflow/tensorflow) |
94 | | -* [Mxnet](https://github.com/apache/incubator-mxnet) |
95 | | -* [Keras](https://github.com/keras-team/keras) |
96 | | -* [ncnn](https://github.com/Tencent/ncnn) |
97 | | -* [pytorch](https://github.com/pytorch/pytorch) |
98 | | -* [opencv](https://github.com/opencv/opencv) |
| 1 | +# AidLux - ARM架构跨生态AIoT开发与部署平台 |
| 2 | + |
| 3 | +[ |
| 4 | + |
| 5 | + |
| 6 | + |
| 7 | +](LICENSE) |
| 8 | +[ |
| 9 | + |
| 10 | + |
| 11 | + |
| 12 | +](https://www.aidlux.com) |
| 13 | + |
| 14 | +**AidLux** 是一个创新的融合操作系统，旨在解决Android与Linux生态割裂问题，为开发者提供在ARM设备（如高通芯片）上同时运行Android应用和LinuxAI算法的原生环境。 |
| 15 | + |
| 16 | +## 🚀 核心优势 |
| 17 | + |
| 18 | +### 1. 独创融合架构 |
| 19 | + |
| 20 | +- **原生体验**：在一台设备上同时获得Android和Linux的原生开发体验，无需虚拟机或双系统切换 |
| 21 | +- **生态互补**：打通Android丰富的应用生态（摄像头、传感器、UI框架）与Linux强大的AI生态（Python, OpenCV, ROS） |
| 22 | + |
| 23 | +### 2. 极致性能调度 |
| 24 | + |
| 25 | +- **异构计算**：通过极致性能AI工具链，一键释放SoC的AI算力 |
| 26 | +- **全栈调度**：综合调度CPU + GPU + NPU，支持高通等ARM架构芯片，实现高性能低功耗的端侧推理 |
| 27 | + |
| 28 | +### 3. 开箱即用 |
| 29 | + |
| 30 | +- **软硬一体**：提供从操作系统到底层驱动的完整解决方案，支持"开箱即用"的工业级部署 |
| 31 | +- **模型支持**：支持多种主流框架模型的优化和转换，解决芯片及算法异构问题 |
| 32 | + |
| 33 | +## 🛠️ 工具链介绍 |
| 34 | + |
| 35 | +### AidLux OS |
| 36 | + |
| 37 | +融合操作系统，集成极致性能AI工具链，作为基础运行环境，释放SoC算力 |
| 38 | + |
| 39 | +### AI Model Optimizer |
| 40 | + |
| 41 | +**模型优化平台** |
| 42 | + |
| 43 | +- 支持多种主流框架模型优化与转换 |
| 44 | +- 菜单式一键操作，零代码实现模型迁移 |
| 45 | +- 精度损失小 |
| 46 | + |
| 47 | +### AI Creator |
| 48 | + |
| 49 | +**可视化训练平台** |
| 50 | + |
| 51 | +- 集标注、训练、部署于一体 |
| 52 | +- 基于行业领先正样本算法 |
| 53 | +- 快速完成模型训练与更新 |
| 54 | + |
| 55 | +### 端侧AI生态门户 |
| 56 | + |
| 57 | +全球首个高通物联网平台端侧AI生态门户，包含解决方案中心 + 模型广场 |
| 58 | + |
| 59 | +## 💡 适用领域 |
| 60 | + |
| 61 | +- 🤖 **智能机器人**：具身智能、服务机器人 |
| 62 | +- 🏭 **工业AI检测**：缺陷检测、自动化质检 |
| 63 | +- 🏙️ **智慧城市**：安防、停车管理 |
| 64 | +- 📱 **边缘计算与AI教育** |
| 65 | + |
| 66 | +## 📦 安装与使用 |
| 67 | + |
| 68 | +### 系统要求 |
| 69 | + |
| 70 | +- Android 7.0及以上版本 |
| 71 | +- ARM架构处理器（推荐高通芯片） |
| 72 | +- 至少2GB RAM |
| 73 | + |
| 74 | +### 安装步骤 |
| 75 | + |
| 76 | +1. **下载AidLux APK** |
| 77 | + |
| 78 | +``` |
| 79 | +# 从官网下载最新版本 |
| 80 | +wget https://www.aidlux.com/download/aidlux-latest.apk |
| 81 | +``` |
| 82 | + |
| 83 | +2. **安装应用** |
| 84 | + |
| 85 | +``` |
| 86 | +adb install aidlux-latest.apk |
| 87 | +``` |
| 88 | + |
| 89 | +3. **启动服务** |
| 90 | + |
| 91 | +``` |
| 92 | +# 通过Android Intent启动 |
| 93 | +am start -n com.aplux.aidlux/.MainActivity |
| 94 | +``` |
| 95 | + |
| 96 | +4. **访问Linux环境** |
| 97 | + - 本地访问：直接在手机上使用 |
| 98 | + - 远程访问：通过浏览器访问 `http://<device-ip>:8080` |
| 99 | + |
| 100 | +### 基本使用 |
| 101 | + |
| 102 | +``` |
| 103 | +# 进入Linux终端 |
| 104 | +aidlux terminal |
| 105 | +
|
| 106 | +# 安装AI框架 |
| 107 | +sudo apt update |
| 108 | +sudo apt install python3-pip |
| 109 | +pip3 install tensorflow pytorch |
| 110 | +
|
| 111 | +# 运行Python程序 |
| 112 | +python3 your_ai_app.py |
| 113 | +``` |
| 114 | + |
| 115 | +## 🧪 开发示例 |
| 116 | + |
| 117 | +### 运行AI模型 |
| 118 | + |
| 119 | +``` |
| 120 | +import cv2 |
| 121 | +import tensorflow as tf |
| 122 | +
|
| 123 | +# 直接调用手机硬件资源 |
| 124 | +cap = cv2.VideoCapture(0) # 使用手机摄像头 |
| 125 | +model = tf.keras.models.load_model('your_model.h5') |
| 126 | +
|
| 127 | +while True: |
| 128 | + ret, frame = cap.read() |
| 129 | + prediction = model.predict(frame) |
| 130 | + # 处理预测结果 |
| 131 | +``` |
| 132 | + |
| 133 | +### 多语言开发支持 |
| 134 | + |
| 135 | +- **Python**：`python3`, `pip3` |
| 136 | +- **C/C++**：`gcc`, `g++`, `make` |
| 137 | +- **Java**：`openjdk-11-jdk` |
| 138 | +- **Go**：`golang` |
| 139 | +- **Shell**：`bash`, `zsh` |
| 140 | + |
| 141 | +## 🧰 开发工具 |
| 142 | + |
| 143 | +- **VSCode**：集成开发环境 |
| 144 | +- **Jupyter Notebook**：交互式编程 |
| 145 | +- **Terminal**：完整的Linux命令行 |
| 146 | +- **File Manager**：图形化文件管理 |
| 147 | + |
| 148 | +## 📚 学习资源 |
| 149 | + |
| 150 | +- **官方文档**：https://www.aidlux.com/docs |
| 151 | +- **开发者社区**：https://forum.aidlux.com |
| 152 | +- **示例项目**：https://github.com/aidlux/examples |
| 153 | + |
| 154 | +## 🤝 贡献指南 |
| 155 | + |
| 156 | +欢迎开发者贡献代码和文档！ |
| 157 | + |
| 158 | +1. Fork本仓库 |
| 159 | +2. 创建你的特性分支 (`git checkout -b feature/AmazingFeature`) |
| 160 | +3. 提交你的更改 (`git commit -m 'Add some amazing feature'`) |
| 161 | +4. 推送到分支 (`git push origin feature/AmazingFeature`) |
| 162 | +5. 打开Pull Request |
| 163 | + |
| 164 | +## 📄 许可证 |
| 165 | + |
| 166 | +本项目采用Apache License 2.0，详情请查看LICENSE文件。 |
| 167 | + |
| 168 | +## 📬 联系方式 |
| 169 | + |
| 170 | +- **官网**：https://www.aidlux.com |
| 171 | +- **邮箱**：support@aidlux.com |
| 172 | +- **GitHub**：https://github.com/aidlux |
| 173 | + |
| 174 | +--- |
| 175 | + |
| 176 | +**AidLux** - 让AI开发更简单，让边缘计算更强大！ |
| 177 | + |
0 commit comments