Toolkit for software engineers to Deploy AI Systems Yourself (DAISY). DaisyKit SDK is the core of models and algorithms, which can be used to develop wrappers and applications for different platforms: mobile, embedded or web browsers.

VNOpenAI

Last update: Dec 26, 2022

Overview

Daisykit SDK

DaisyKit SDK is the core of models and algorithms, which can be used to develop wrappers and applications for different platforms: mobile, embedded or web browsers.

Website: https://daisykit.org/.

Environment Setup

Install OpenCV. In Ubuntu:

sudo apt install libopencv-dev

Install Vulkan dev. In Ubuntu:

sudo apt-get install -y libvulkan-dev

Download precompiled NCNN, extract it (version for your development computer).

Build and Run on PC

Initialize / Update submodules

git submodule update --init

Build

mkdir build
cd build
cmake .. -Dncnn_FIND_PATH="<path to ncnn lib>"
make

Run face detection example

./demo_face_detector_graph

Coding convention

Read coding convention and contribution guidelines here.

Build documentation

Step 1: Install doxygen first.
Step 2: Build the documentation:

cd docs
doxygen Doxyfile.in

Step 3: Deploy html documentation from docs/_build/html.
Step 4: Our lastest documentation is deployed at https://docs.daisykit.org.

References

This toolkit is developed on top of other source code. Including

Toolchains setup from ncnn.
QR Scanner from ZXing-CPP.
JSON support from nlohmann/json.
Pretrained AI models from different sources: https://docs.daisykit.org/md_models.html.

You might also like...

Real time eye tracking for embedded and mobile devices.

drishti Real time eye tracking for embedded and mobile devices in C++11. NEWS (2018/08/10) Native iOS, Android, and "desktop" variants of the real-tim

356 Dec 14, 2022

The PULP Ara is a 64-bit Vector Unit, compatible with the RISC-V Vector Extension Version 0.9, working as a coprocessor to CORE-V's CVA6 core

Ara Ara is a vector unit working as a coprocessor for the CVA6 core. It supports the RISC-V Vector Extension, version 0.9. Dependencies Check DEPENDEN

185 Dec 24, 2022

Spying on Microcontrollers using Current Sensing and embedded TinyML models

Welcome to CurrentSense-TinyML CurrentSense-TinyML is all about detecting microcontroller behaviour with current sensing and TinyML. Basically we are

71 Sep 17, 2022

Insight Toolkit (ITK) is an open-source, cross-platform toolkit for N-dimensional scientific image processing, segmentation, and registration

ITK: The Insight Toolkit C++ Python Linux macOS Windows Linux (Code coverage) Links Homepage Download Discussion Software Guide Help Examples Issue tr

1.1k Dec 26, 2022

Comments

Several vulnerabilities in the shared libraries which daisykit depends on. Could you help upgrade to patch versions?

Hi, @vietanhdev , @tranminhduc4796 , I'd like to report a vulnerability issue in daisykit_0.1.20211123.

Dependency Graph between Python and Shared Libraries

Issue Description

As shown in the above dependency graph(here shows part of the dependency graph, which depends on vulnerable shared libraries), daisykit_0.1.20211123 directly or transitively depends on 53 C libraries (.so). However, I noticed that some C libraries are vulnerable, containing the following CVEs: libcrypto-2879dacc.so.1.1 libssl-6082116c.so.1.1from C project openssl(version:1.1.1f) exposed 5 vulnerabilities: CVE-2021-3711, CVE-2021-3712, CVE-2020-7043, CVE-2020-7042, CVE-2020-7041,

Suggested Vulnerability Patch Versions

openssl has fixed the vulnerabilities in versions >=1.1.1l

Python build tools cannot report vulnerable C libraries, which may induce potential security issues to many downstream Python projects. As a popular python package (daisykit has 7,176 downloads per month), could you please upgrade the above shared libraries to their patch versions?

Thanks for your help~ Best regards, Andy

opened by andy201709 1

Toolkit for software engineers to Deploy AI Systems Yourself (DAISY). DaisyKit SDK is the core of models and algorithms, which can be used to develop wrappers and applications for different platforms: mobile, embedded or web browsers.

Related tags

Overview

Daisykit SDK

Environment Setup

Build and Run on PC

Coding convention

Build documentation

References

You might also like...

Real time eye tracking for embedded and mobile devices.

The PULP Ara is a 64-bit Vector Unit, compatible with the RISC-V Vector Extension Version 0.9, working as a coprocessor to CORE-V's CVA6 core

Spying on Microcontrollers using Current Sensing and embedded TinyML models

Insight Toolkit (ITK) is an open-source, cross-platform toolkit for N-dimensional scientific image processing, segmentation, and registration

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Fox-toolkit - Unofficial Zenotech specific mirror of fox-toolkit; please refer to upstream site for latest version

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

Wt, C++ Web Toolkit

shufflev2-yolov5: lighter, faster and easier to deploy

Comments

Several vulnerabilities in the shared libraries which daisykit depends on. Could you help upgrade to patch versions?

Dependency Graph between Python and Shared Libraries

Issue Description

Suggested Vulnerability Patch Versions

Owner

VNOpenAI

Mobile Robot Programming Toolkit (MRPT) provides C++ libraries aimed at researchers in mobile robotics and computer vision

Lite.AI.ToolKit 🚀🚀🌟: A lite C++ toolkit of awesome AI models such as RobustVideoMatting🔥, YOLOX🔥, YOLOP🔥 etc.

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Deploy SCRFD, an efficient high accuracy face detection approach, in your web browser with ncnn and webassembly

Deploy OcrLite in your web browser with ncnn and webassembly

A lightweight 2D Pose model can be deployed on Linux/Window/Android, supports CPU/GPU inference acceleration, and can be detected in real time on ordinary mobile phones.

🐸 Coqui STT is an open source Speech-to-Text toolkit which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers

Want a faster ML processor? Do it yourself! -- A framework for playing with custom opcodes to accelerate TensorFlow Lite for Microcontrollers (TFLM).

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.