IA - DESENVOLVEDOR (MAKER)
Hands on: ferramentas, tutoriais, práticas, e aplicações
O rol de sites aqui apresentado com ferramentas, projetos e práticas tem caráter informativo. Os projetos, ferramentas e práticas não foram necessariamente testados. APLICATIVOS, FERRAMENTAS e PLATAFORMAS
Linguagem - Python é uma linguagem de programação amigável, de fácil aprendizagem e aberta.
Library - OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library. OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in the commercial products. Being a BSD-licensed product, OpenCV makes it easy for businesses to utilize and modify the code. .
Plataforma de desenvolvimento - Edge Impulse é uma plataforma de desenvolvimento para machine learning on edge devices, gratuita para desenvolvedores.
Biblioteca de código aberto - Tensor Flow é uma plataforma completa de código aberto para machine learning.
Repositório - Tensor Flow no Github.
Biblioteca de código aberto - Fast Ai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library.
Modelo de Desenvolvimento - TinyML Modelo de ecossistema (comunidade, algoritmos, dispositivos...) de Machine Learning para implementação em sistemas de baixo consumo de energia, como sensores ou microcontroladores, capazes de executar tarefas automatizadas demandando menos energia e menos infraestrutura (não há necessidade de enviar informações para a nuvem).
Meetup - TinyMLMembros da área espalhados vários países organizam e publicam eventos sobre TinyML .
Linkedin - tinyML Community.
Youtube - tinyML - Canal.
Magenta - Geração de arte e música com inteligência de máquina.
Magenta - Repositório no Github (Getting Started, Magenta Repo, Installation, Using Magenta, Development Environment).
Jupyter - Project Jupyter exists to develop open-source software, open-standards, and services for interactive computing across dozens of programming languages).
JupyterLab: Jupyter’s Next-Generation Notebook Interface
JupyterLab is a web-based interactive development environment for Jupyter notebooks, code, and data. JupyterLab is flexible: configure and arrange the user interface to support a wide range of workflows in data science, scientific computing, and machine learning. JupyterLab is extensible and modular: write plugins that add new components and integrate with existing ones.
The Jupyter Notebook
The Jupyter Notebook is an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and narrative text. Uses include: data cleaning and transformation, numerical simulation, statistical modeling, data visualization, machine learning, and much more.
CoLab - Google Colaboratory (CoLab)
O Google Colaboratory é um ambiente gratuito de notebooks Jupyter (ambiente com ferramentas de desenvolvimento - development tool) que não requer configuração e é executado na nuvem. Permite escrever e executar códigos em Python, salvar e compartilhar análises e acessar poderosos recursos de computação científica, tudo direto no navegador.
CoLab - Exemplos de machine learning.
Para ver exemplos completos das análises interativas de machine learning possibilitadas pelo Colaboratory (Colab - ambiente de notebooks Jupyter da Google), confira estes tutoriais que usam modelos do TensorFlow Hub.
PyTorch
An open source machine learning framework that accelerates the path from research prototyping to production deployment (from research to production) ).
Teaching Kits - NVIDIA DLI TEACHING KITS FOR EDUCATORS.
Universities are at the forefront of nurturing the next generation in the emerging technologies of accelerated computing, data science, and AI. NVIDIA Deep Learning Institute (DLI) Teaching Kits lower the barrier of incorporating AI and GPU computing in coursework with downloadable teaching materials and online courses that provide the foundation for understanding and building hands-on expertise in these critical areas.
Biblioteca de código aberto - PyCaret
PyCaret is an open source, low-code machine learning library in Python (by Moez Ali, July 2020) that aims to reduce cycle time from hypothesis to insights. PyCaret automates machine learning workflows. It is an end-to-end machine learning and model management tool that speeds up the experiment cycle exponentially and makes you more productive.
Biblioteca de código aberto - PyCaret - Documentação
Release Notes, Example Notebooks, Blog Posts, LinkedIn, YouTube, Contribute and More about PyCaret.
Guide - PyCaret
Getting started , functions, pre-processing, modules and tutorial.
Git - PyCaret - Github
Biblioteca de código aberto - SciKit Learn
Tools for predictive data analysis, accessible to everybody, and reusable in various contexts. Built on NumPy, SciPy, and matplotlib. Open source, commercially usable - BSD license
Boosting Framework - LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. It is designed to be distributed and efficient with the following advantages: faster training speed and higher efficiency; lower memory usage; better accuracy; support of parallel, distributed, and GPU learning; capable of handling large-scale data.
Biblioteca de código aberto - Numpy
NumPy forms the basis of powerful machine learning libraries like scikit-learn and SciPy. As machine learning grows, so does the list of libraries built on NumPy. TensorFlow’s deep learning capabilities have broad applications — among them speech and image recognition, text-based applications, time-series analysis, and video detection. PyTorch, another deep learning library, is popular among researchers in computer vision and natural language processing. MXNet is another AI package, providing blueprints and templates for deep learning.
Biblioteca de código aberto - XGBoost
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. The same code runs on major distributed environment (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.
Biblioteca de código aberto - spaCy
Industrial-strength NLP (Natural Language Processing).
spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products.
End-to-end workflows from prototype to production: spaCy's new project system gives you a smooth path from prototype to production. It lets you keep track of all those data transformation, preprocessing and training steps, so you can make sure your project is always ready to hand over for automation. It features source asset download, command execution, checksum verification, and caching with a variety of backends and integrations.
spaCy comes with pretrained pipelines and currently supports tokenization and training for 60+ languages. It features state-of-the-art speed and neural network models for tagging, parsing, named entity recognition, text classification and more, multi-task learning with pretrained transformers like BERT, as well as a production-ready training system and easy model packaging, deployment and workflow management. spaCy is commercial open-source software, released under the MIT license.
Plataform and Tools - Qualcomm developer network
(Developer Resources, Software Development Tools, Hardware Development Tools and QUALCOMM AI research)
AI is changing everything. Combined with powerful, energy efficient processors and ubiquitous connectivity to the wireless edge, intelligence is moving to more devices, changing industries, and inventing new experiences.
On-device AI allows for real-time responsiveness, improved privacy, and enhanced reliability along with better overall performance and with or without a network connection.
The Qualcomm Artificial Intelligence (AI) Engine along with our AI Software and Hardware tools (including our Qualcomm® Neural Processing SDK for AI) as outlined below, are designed to accelerate your on-device AI-enabled applications and experiences.The Qualcomm Artificial Intelligence (AI) Engine is available on supported Snapdragon® 888, 865, 855, 845, 835, 821, 820 and 660 mobile platforms, and with cutting-edge on-device AI processing found in the Snapdragon 888.
AIfES - Artificial Intelligence for Embedded Systems
Embedded AI – Artificial Intelligence for microcontrollers and embedded systems
(Developer Resources, Software Development Tools, Hardware Development Tools and QUALCOMM AI research)
Fraunhofer IMS has developed AIfES, a open source platform-independent and constantly growing machine learning library developed using the C programming language, which implies a fully configurable Feedforward Neural Network (FNN). AIfES uses standard libraries based on the GNU Compiler Collection (GCC). The program source code is reduced to a minimum, thus even the integration on a microcontroller including learning algorithms is possible. AIfES runs on almost any hardware from 8-bit microcontrollers to smartphones and PCs.
Main page: www.aifes.ai
AIfES Youtube Channel
AIfES for Arduino Git Hub
Arduino - Project Hub - hackster.io
Plataform and Tools - bigML
BigML provides a selection of robustly-engineered Machine Learning algorithms proven to solve real world problems by applying a single, standardized framework across your company. Avoid dependencies on many disparate libraries that increase complexity, maintenance costs, and technical debt in your projects. BigML facilitates unlimited predictive applications across industries including aerospace, automotive, energy, entertainment, financial services, food, healthcare, IoT, pharmaceutical, transportation, telecommunications, and more.
Plataform and Tools - D3.js
D3.js is a JavaScript library for manipulating documents based on data. D3 helps you bring data to life using HTML, SVG, and CSS. D3’s emphasis on web standards gives you the full capabilities of modern browsers without tying yourself to a proprietary framework, combining powerful visualization components and a data-driven approach to DOM manipulation.
JupyterLab: Jupyter’s Next-Generation Notebook Interface
JupyterLab is a web-based interactive development environment for Jupyter notebooks, code, and data. JupyterLab is flexible: configure and arrange the user interface to support a wide range of workflows in data science, scientific computing, and machine learning. JupyterLab is extensible and modular: write plugins that add new components and integrate with existing ones.
The Jupyter Notebook
The Jupyter Notebook is an open-source web application that allows you to create and share documents that contain live code, equations, visualizations and narrative text. Uses include: data cleaning and transformation, numerical simulation, statistical modeling, data visualization, machine learning, and much more.
O Google Colaboratory é um ambiente gratuito de notebooks Jupyter (ambiente com ferramentas de desenvolvimento - development tool) que não requer configuração e é executado na nuvem. Permite escrever e executar códigos em Python, salvar e compartilhar análises e acessar poderosos recursos de computação científica, tudo direto no navegador.
Para ver exemplos completos das análises interativas de machine learning possibilitadas pelo Colaboratory (Colab - ambiente de notebooks Jupyter da Google), confira estes tutoriais que usam modelos do TensorFlow Hub.
An open source machine learning framework that accelerates the path from research prototyping to production deployment (from research to production) ).
Universities are at the forefront of nurturing the next generation in the emerging technologies of accelerated computing, data science, and AI. NVIDIA Deep Learning Institute (DLI) Teaching Kits lower the barrier of incorporating AI and GPU computing in coursework with downloadable teaching materials and online courses that provide the foundation for understanding and building hands-on expertise in these critical areas.
PyCaret is an open source, low-code machine learning library in Python (by Moez Ali, July 2020) that aims to reduce cycle time from hypothesis to insights. PyCaret automates machine learning workflows. It is an end-to-end machine learning and model management tool that speeds up the experiment cycle exponentially and makes you more productive.
Release Notes, Example Notebooks, Blog Posts, LinkedIn, YouTube, Contribute and More about PyCaret.
Getting started , functions, pre-processing, modules and tutorial.
Tools for predictive data analysis, accessible to everybody, and reusable in various contexts. Built on NumPy, SciPy, and matplotlib. Open source, commercially usable - BSD license
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks. It is designed to be distributed and efficient with the following advantages: faster training speed and higher efficiency; lower memory usage; better accuracy; support of parallel, distributed, and GPU learning; capable of handling large-scale data.
NumPy forms the basis of powerful machine learning libraries like scikit-learn and SciPy. As machine learning grows, so does the list of libraries built on NumPy. TensorFlow’s deep learning capabilities have broad applications — among them speech and image recognition, text-based applications, time-series analysis, and video detection. PyTorch, another deep learning library, is popular among researchers in computer vision and natural language processing. MXNet is another AI package, providing blueprints and templates for deep learning.
XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. The same code runs on major distributed environment (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.
Industrial-strength NLP (Natural Language Processing).
spaCy is a library for advanced Natural Language Processing in Python and Cython. It's built on the very latest research, and was designed from day one to be used in real products.
End-to-end workflows from prototype to production: spaCy's new project system gives you a smooth path from prototype to production. It lets you keep track of all those data transformation, preprocessing and training steps, so you can make sure your project is always ready to hand over for automation. It features source asset download, command execution, checksum verification, and caching with a variety of backends and integrations.
spaCy comes with pretrained pipelines and currently supports tokenization and training for 60+ languages. It features state-of-the-art speed and neural network models for tagging, parsing, named entity recognition, text classification and more, multi-task learning with pretrained transformers like BERT, as well as a production-ready training system and easy model packaging, deployment and workflow management. spaCy is commercial open-source software, released under the MIT license.
(Developer Resources, Software Development Tools, Hardware Development Tools and QUALCOMM AI research)
AI is changing everything. Combined with powerful, energy efficient processors and ubiquitous connectivity to the wireless edge, intelligence is moving to more devices, changing industries, and inventing new experiences. On-device AI allows for real-time responsiveness, improved privacy, and enhanced reliability along with better overall performance and with or without a network connection. The Qualcomm Artificial Intelligence (AI) Engine along with our AI Software and Hardware tools (including our Qualcomm® Neural Processing SDK for AI) as outlined below, are designed to accelerate your on-device AI-enabled applications and experiences.The Qualcomm Artificial Intelligence (AI) Engine is available on supported Snapdragon® 888, 865, 855, 845, 835, 821, 820 and 660 mobile platforms, and with cutting-edge on-device AI processing found in the Snapdragon 888.
Embedded AI – Artificial Intelligence for microcontrollers and embedded systems
(Developer Resources, Software Development Tools, Hardware Development Tools and QUALCOMM AI research)
Fraunhofer IMS has developed AIfES, a open source platform-independent and constantly growing machine learning library developed using the C programming language, which implies a fully configurable Feedforward Neural Network (FNN). AIfES uses standard libraries based on the GNU Compiler Collection (GCC). The program source code is reduced to a minimum, thus even the integration on a microcontroller including learning algorithms is possible. AIfES runs on almost any hardware from 8-bit microcontrollers to smartphones and PCs.
BigML provides a selection of robustly-engineered Machine Learning algorithms proven to solve real world problems by applying a single, standardized framework across your company. Avoid dependencies on many disparate libraries that increase complexity, maintenance costs, and technical debt in your projects. BigML facilitates unlimited predictive applications across industries including aerospace, automotive, energy, entertainment, financial services, food, healthcare, IoT, pharmaceutical, transportation, telecommunications, and more.
D3.js is a JavaScript library for manipulating documents based on data. D3 helps you bring data to life using HTML, SVG, and CSS. D3’s emphasis on web standards gives you the full capabilities of modern browsers without tying yourself to a proprietary framework, combining powerful visualization components and a data-driven approach to DOM manipulation.
TUTORIAIS E GUIAS
AIfES - AIfES - Inference Tutorial © GPL3+.
This tutorial shows how to import an already trained ANN from a framework like TensorFlow/Keras into Fraunhofer-Institut für Mikroelektronische Schaltungen und Systeme IMS' AIfES and perform an inference.
TinyML - Identificação de fruta usando Arduíno e Tensor Flow.
TinyML - Arduino Machine Learning com Tensor Flow Lite: carro robô controlado por voz.
TinyML - Raspberry Pi Machine Learning com Impulse.
TinyML - TinyML: Machine learning para microcontroladores. (14/04/2021)
OpenCV Tutorials, Resources, and Guides.
Accessing the Raspberry Pi Camera with OpenCV and Python by Adrian Rosebrock on March 30, 2015
Start Here with Computer Vision, Deep Learning, and OpenCV - Your step-by-step guide to getting started, getting good, and mastering Computer Vision, Deep Learning, and OpenCV.
Edge Impulse no Raspberry Pi 4
DIY Deep Learning for Vision: a Hands-On Tutorial with Caffe
Guia - More Deep Learning. Less crying -> A guide
This is a guide to make deep learning less messy and hopefully give you a way to use less tissues next time you code.
by Subhaditya Mukherjee
Guia - Keras Developer guides
Guia - Google Colab - Quick Guide
This tutorial shows how to import an already trained ANN from a framework like TensorFlow/Keras into Fraunhofer-Institut für Mikroelektronische Schaltungen und Systeme IMS' AIfES and perform an inference.
This is a guide to make deep learning less messy and hopefully give you a way to use less tissues next time you code.
by Subhaditya Mukherjee
PORTAL DE PROJETOS: mjrobot.org
Blog do Professor Marcelo José Rovai com projetos, práticas e tutoriais.
* - Compartilhamento de idéias e experiências no mundo da Eletrônica. Ênfase no uso de plataformas de desenvolvimento baseadas em microcontroladores, como Arduino e computadores completos do tamanho de cartões de crédito como o Raspberry-Pi.
PLATAFORMAS DE HARDWARE (BOARDS)
Cheat Sheet Raspberry Pi: A cheat sheet. (September 3, 2020, 1:30 AM PST)
Board - Sony Spresense
Spresense SDK Getting Started Guide via Command Line Interface (CLI)
Spresense tutorials
Onion Omega2: low-cost, production-ready Linux modules for connected devices and sensors
The Onion Omega2 is a Wi-Fi enabled, Linux-based development module, designed specifically for IoT applications. It provides a drop-in, low-power solution ideal for prototyping and building IoT hubs and devices.
Onion Omega2 Documentation
Onion Omega2 Getting Started
Onion Omega2 Hardware Overview
OnionIoT/source at github
ESP32-CAM camera development board
ESP32-CAM is the latest small size camera module released by Essence. The module can work independently as the smallest system, with a size of only 27*40.5*4.5mm, and a deep sleep current as low as 6mA. ESP32-CAM can be widely used in various IoT applications, suitable for home smart devices, industrial wireless control, wireless monitoring, QR wireless identification, wireless positioning system signals and other IoT applications. It is an ideal solution for IoT applications.
O módulo ESP32-CAM com Câmera OV2640 2MP tem como principais características: Bluetooth BLE 4.2, suporte para cartão SD, antena embutida, wireless padrão 802.11 b/g/n e conexão Wifi 2.4 GHz. Possui 16 portas GPIO com as funções PWM, IC2, SPI e UART, sendo que 10 delas são de entrada e saída e 6 estão relacionadas a energia. A tensão de alimentação é de 5V.
Espressif IoT Development Framework
ESP-IDF is the development framework for Espressif SoCs supported on Windows, Linux and macOS.
Placa de desenvolvimento de câmera ESP32-CAM
Visão geral, características, cenários de aplicação, definição de pinos e documentação (especificações, esquema elétrico, tutorial)
ESP32-CAM - Aplicação: Câmera IP
"Câmera IP: Cuide do seu bebê com o ESP32-CAM" - Artigo publicado no blog do FilipeFlop
Por Rosana Guse | Em 10 de maio de 2019
ESP32-CAM Project - Color Detection & Tracking with ESP32 CAM & OpenCV
ESP32 CAM Based Color Detection System using OpenCV
By Priyansh Shankhdhar | On November 27, 2021 | at how2electronics.com
ESP32-CAM - Aplicação: ESP32 CAM para fazer filmagens com Drone
"Projeto 22 - Como usar o ESP32 CAM para fazer filmagens com Drone ? - Maker 4.0" - Vídeo didático publicado no Youtube
Objetivo de Projeto: Empregar o ESP32-CAM para tirar fotos e gravar filmagens.
Por L.Gustavo
The Onion Omega2 is a Wi-Fi enabled, Linux-based development module, designed specifically for IoT applications. It provides a drop-in, low-power solution ideal for prototyping and building IoT hubs and devices.
ESP32-CAM is the latest small size camera module released by Essence. The module can work independently as the smallest system, with a size of only 27*40.5*4.5mm, and a deep sleep current as low as 6mA. ESP32-CAM can be widely used in various IoT applications, suitable for home smart devices, industrial wireless control, wireless monitoring, QR wireless identification, wireless positioning system signals and other IoT applications. It is an ideal solution for IoT applications.
O módulo ESP32-CAM com Câmera OV2640 2MP tem como principais características: Bluetooth BLE 4.2, suporte para cartão SD, antena embutida, wireless padrão 802.11 b/g/n e conexão Wifi 2.4 GHz. Possui 16 portas GPIO com as funções PWM, IC2, SPI e UART, sendo que 10 delas são de entrada e saída e 6 estão relacionadas a energia. A tensão de alimentação é de 5V.
ESP-IDF is the development framework for Espressif SoCs supported on Windows, Linux and macOS.
Visão geral, características, cenários de aplicação, definição de pinos e documentação (especificações, esquema elétrico, tutorial)
"Câmera IP: Cuide do seu bebê com o ESP32-CAM" - Artigo publicado no blog do FilipeFlop
Por Rosana Guse | Em 10 de maio de 2019
ESP32 CAM Based Color Detection System using OpenCV
By Priyansh Shankhdhar | On November 27, 2021 | at how2electronics.com
"Projeto 22 - Como usar o ESP32 CAM para fazer filmagens com Drone ? - Maker 4.0" - Vídeo didático publicado no Youtube
Objetivo de Projeto: Empregar o ESP32-CAM para tirar fotos e gravar filmagens.
Por L.Gustavo
SDKs
SDK - Getting started with the Arduino Nano 33 BLE Sense
SDK - Sony Spresense
SDK - Intel® Movidius™ Neural Compute Stick
SDK - Dev Kit Weekly: Xilinx Kria KV260 Vision AI Starter Kit - by Embedded Computing Design
REDES SOCIAIS, COMUNIDADES E REPOSITÓRIOS PARA PROGRAMADORES E DESENVOLVEDORES
SOCIAL NETWORKS FOR PROGRAMMERS AND DESIGNERS
SOCIAL NETWORKS FOR PROGRAMMERS AND DESIGNERS
Github.
* - Plataforma de desenvolvimento que permite gerenciar o armazenamento de códigos. .
* - Comunidade de desenvolvedores. Contém uma biblioteca de projetos em múltiplas plataformas. Abrange machine learning, IoT, sensores, robótica, dentre outros tópicos.
* - Dentre os diversos tópicos, contempla artificial intelligence, deep learning, tensor flow,... .
* - Repositório de códigos e data sets, comunidade, cursos e competições .
