#Event – Let’s code a drone ✈ to follow faces 😀 with #AzureIoT (x2!) Supporting the #GlobalAI Bootcamp Singapore and Germany!

Hi !

Let’s start the 2021 with some drones events supporting 2 Global AI Bootcamp events

Please each event location for specific details on time and streaming options.

Let’s code a drone to follow faces syncing everything with Azure IoT

You can control a drone using 20 lines of code. That’s the easy part. However, adding extra features like face or object detection and program the drone to follow and object or a face requires … another 20 lines of code! During this workshop we will review how to connect to a drone, how to send and receive commands from the drone, how to read the camera video feed and how to apply AI on top of the camera feed to recognize objects or faces. We will use a simple house drone ($100) and Python. And, when we review some enterprise scenarios, we will use Azure IoT to sync the drone information in IoT mode. Let’s build this!

For this session I’ll explain how to create a SDK from zero to control a DJI Tello drone, and the last past will include some examples on how to connect the drone reported information to Azure IoT.

And this is probably the last one my Microsoft MVP room-office (see below), there are some changes in the near future, so let’ rock these 2 sessions !

Happy coding!

Greetings

El Bruno

¿Con ganas de ponerte al día?

En Lemoncode te ofrecemos formación online impartida por profesionales que se baten el cobre en consultoría:

Si tienes ganas de ponerte al día con Front End (ES6, Typescript, React, Angular, Vuejs…) te recomendamos nuestros Máster Front End: https://lemoncode.net/master-frontend#inicio-banner
Si te quieres poner al día en Backend (stacks .net y nodejs), te aconsejamos nuestro Bootcamp Backend: https://lemoncode.net/bootcamp-backend#bootcamp-backend/banner
Y si tienes ganas de meterte con Docker, Kubernetes, CI/CD…, tenemos nuestro Bootcamp Devops: https://lemoncode.net/bootcamp-devops#bootcamp-devops/inicio

#Event – Global AI Bootcamp Toronto on Dec 12 🤖🤖🤖 @GlobAICommunity

Hi !

This started to be my annual tradition: Global AI Bootcamp is the last event of the year!
And this year, we had a set of amazing session planned with the following topics:

Introduction to AI and Cognitive Services for Developers and Information Workers
Understanding Autonomous systems, Machine Teaching and Bonsai Platform
Knowledge Mining and MLOps

We have speakers from all around Canada and a special guest from the South !

As usual the event is free, no food this year (sorry!), however you can spend a nice Saturday morning learning about AI in your chosen location !

Registration: https://www.meetup.com/metrotorontoug/events/267883977/

Full details here 👇👇👇

Intro and Welcome

Session. 10:00 – 10:10

Kick off of the amazing event

Introduction to AI and Cognitive Services for Developers and Information Workers

Session 1. 10:10 – 11:00

Speaker: Prashant G Bhoyar | Microsoft AI MVP

“Artificial Intelligence and Machine Learning are the new buzzwords in the industry. Microsoft’s vision is to make AI accessible to every enterprise, data scientist, developer, information worker, consumer and device everywhere in the world. AI has a big role to play in the enterprise space. The field of AI is progressing at a rapid pace. Without understanding the concepts behind these advanced technologies, developers and administrators will struggle to evaluate the potential impact of new tools and solutions. In this session, we will break down the concepts behind existing technologies, outline various tools available today, and discuss the direction of AI and ML for Developers. We will cover how developers, Power Users, and Information workers can take advantage of Microsoft’s AI and Cognitive Services offerings to build real-life enterprise solutions.
You will learn:
1) Overview of Microsoft AI Platform
2) What are the cognitive services?
3) What tools are available today?
4) How to use Cognitive Services to implement real-life business solutions?

Understanding Autonomous systems, Machine Teaching and Bonsai Platform

Session 2. 11:10 – 12:00

Speaker: Ivana Tilca | Microsoft AI MVP | 3XM Group Quality Manager

Innovations in AI are creating the next wave of disruption in industrial technology. Autonomous machines are more than an expansion of automated systems: They are an entirely new way to amplify human expertise. In this session you will take a look to how to speed the creation of AI-powered automation to improve production efficiency and reduce downtime – without requiring data scientists with Project Bonsai. We will also take a look at AirSim, a simulator for drones, cars and more, built on Unreal Engine. AirSim a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles.

Knowledge Mining and MLOps

Session 3. 12:10 – 13:00

Speakers: Amol Mane, Meghana Madhusudhan and Niloofar Nayebi

Knowledge mining is an emerging discipline in artificial intelligence (AI) that uses a combination of intelligent services to quickly learn from vast amounts of information. It allows organizations to deeply understand and easily explore information, uncover hidden insights, and find relationships and patterns at scale. This platform allows to use machine learning model to address any specific business need. The life cycle of the models can be managed using MLOps. MLOps, or DevOps for machine learning, enables data science and IT teams to collaborate and increase the pace of model development and deployment via monitoring, validation, and governance of machine learning models. These two solutions combined can create a strong platform to extract, enrich, and expose any hidden data within any organization.
In this session you are going to learn about three main steps in KM platform:
– Ingestion
– Enrichment
– Exploration
And three main pipelines in MLOps:
– Continues Integration
– Continues Delivery
– Deployment

Let’s meet there !

Happy coding!

Greetings

El Bruno

#Event – Resources used during the session “Hack a drone, hack the camera and use AI” at the Global AI Tour, Lahore Pakistan, 2020

Hi !

I had a great time early in the day with my Microsoft Student Partners from Lahore Pakistan, for the Global AI Tour. As usual, time for slides and code:

Slides

Code

https://github.com/elbruno/events/tree/main/2020%2011%2030%20Global%20AI%20Tour%20Pakistan

Resources

DJI Tello Drone,
https://www.amazon.com/Tello-CP-PT-00000252-01-Quadcopter-Drone/dp/B07BDHJJTH
Ryze Tello SDK, https://www.ryzerobotics.com/tello
Viola Jones, Object Detection Framework,
https://en.wikipedia.org/wiki/Viola%E2%80%93Jones_object_detection_framework
Cognitive Services Custom Vision, https://customvision.ai

Coding4Fun Drone posts

Happy coding!

Greetings

El Bruno

#AI – #Lobe, exporting to ONNX, and running in C# #csharp @lobe_ai

Hi !

Follow up post after yesterday post on Lobe, and today focusing on ONNX and C# code. And, it all started because someone asked in twitter about an ETA to export the model to ONNX

Awesome! Any ETA on ONNX?
— Niels Laute (@Niels9001) October 28, 2020

I decided to give a try to the TensorFlow to Onnx tool, and it worked great ! (see references). I use the following command to convert my model

python -m tf2onnx.convert --saved-model model --output model.onnx

From the PB exported model from yesterday, and I got my 2 models

And, here I got an amazing surprise. Before I started to write some C# code, I found some NuGet packages available to use

lobe
lobe.Onnx
lobe.ImageSharp

And, after a quick search I found some sample code in GitHub about how to use these packages. So, I pickup the original Code and make a few changes to perform estimations on 2 manual drawings.

Remember my model was trained to analyze drawings and detect: humans, fish and flowers.

I created a new C# Console App and

copy the generated [model.onnx]
copy the 2 test files: [fishy.png] and [human.png]
copy the original [signature.json] file generated on the Lobe TensorFlow export

I edited the [signature.json] file and change the values

format to onnx
filename to the generated exported filename

And I was ready to run my code:

      
        using System;
      
        using System.IO;
      
        using SixLabors.ImageSharp;
      
        using SixLabors.ImageSharp.PixelFormats;
      
        using lobe.ImageSharp;
      
        using lobe;
      
        namespace ConsoleApp1
      
        {
      
            class Program
      
            {
      
                static void Main(string[] args)
      
                {
      
                    var signatureFilePath = "signature.json";
      
                    ImageClassifier.Register("onnx", () => new OnnxImageClassifier());
      
                    using var classifier = ImageClassifier.CreateFromSignatureFile(
      
                        new FileInfo(signatureFilePath));
      
                    // Images
      
                    ShowResults("fishy.png", classifier);
      
                    ShowResults("human.png", classifier);
      
                }
      
                private static void ShowResults(string imagePath, ImageClassifier classifier)
      
                {
      
                    var results = classifier.Classify(Image
      
                        .Load(imagePath).CloneAs<Rgb24>());
      
                    Console.WriteLine();
      
                    Console.WriteLine($"Image : {imagePath}");
      
                    Console.WriteLine($"Top Label: {results.Classification.Label}");             
      
                    foreach (var res in results.Classifications)
      
                    {
      
                        Console.WriteLine($"  – Label: {res.Label} – Confidence: {res.Confidence}");
      
                    }
      
                }
      
            }
      
        }

view raw lobeonnxcsharpsample.cs hosted with ❤ by GitHub

And the output is fast and great, as we are used to do with Onnx

Lobe looks great !

Happy coding!

Greetings

El Bruno

References

#AI – #Lobe, desktop tool to train custom machine learning models for Computer Vision @lobe_ai

Hi !

There are 2 ways to describe Lobe. You may want to use their official description

Lobe helps you train machine learning models with a free, easy to use tool.
Lobe AI Homepage

Or you may want to use the tool. Let’s review the 2nd one with a NNNN step tutorial.

Data Source Images

For this tutorial I’ll use a set of 24 drawings for fish, human and flowers. I have 8 drawings for each category in different folders.

Import and label Images

Ok, you probably have already installed the app, so let’s create a new project. I’ll name this project drawings.

The import button, will display a set of options. For this demo, I’ll go to DataSet, where I need to have all my images in a structured set of folders.

The import option also describes how to organize the images in folder.

Once we import the images, we will have the option to automatically label our images based on the folder name

Train

This is the most user friendly step, we don’t need to train the model. I mean, once we have our images, Lobe will automatically start the training process in the background.

Depending the size of your training dateset, this may take some time. Once the model is trained, we can also see some output around the correct and incorrect predictions.

Test with new images

This is also cool. Once the model is trained we can test is in the Play section. In example, I’ve uploaded a custom fish model, and it’s predicted as a fish. I can confirm or assign the correct label in the Play area.

I’ve uploaded a couple more test images, and the background training process created a perfect model !!! (I know, I know …)

Export generated model

And another great feature is the Export option.

There are several options:

TensorFlow
TensorFlow Lite
Local API

I haven’t used options 2 and 3, however option 1 is good enough to play around. It will include the TensorFlow frozen model, some supporting files, and a sample to use this in Python !

Super easy to start and learn without coding !

Happy coding!

Greetings

El Bruno

References

#Personal – We have a “Learn to pronounce” feature in Google !

Hi !

Some days ago, while I was searching for the meaning of a word, I found an amazing feature in Google:

Learn to pronounce

And it’s very basic and amazing at the same time.

You search for a definition of a word
In the result area, you get the speaker button, who reproduces the word
Once you play the word, a new feature will be available: [Learn to Pronounce]
This will open a new section, with the mouth movements for the American and British pronunciation

That’s it, super useful ! I could not find a lot of related information about this. It seems that it’s been around for over 2 years, based on these The Verge articles:

Besides some great AI in the back, this is so amazing 😀

Happy coding!

Greetings

El Bruno

#Event – Let’s hack a drone, hack the camera and use AI! virtual with Microsoft Reactor @MSFTReactor

Hi !

Today I’ll share a new version of my drone and Artificial Intelligence session, hosted by Microsoft Reactor Toronto.

The registration link and details are available here

https://developer.microsoft.com/en-us/reactor/Location/Toronto#filter?dayfrom=7-1-2020&id=7650

Happy coding!

Greetings

El Bruno

#Office – New Microsoft Word editor helps support Inclusive Language.

Hi!

I already write about some cool features embedded in Office to help us to be more productive. These features are mostly based on Artificial Intelligence. And one great example is the Microsoft Word Editor feature.

Today I was reading an article “New AI tools help writers be more clear, concise and inclusive in Office and across the web” (see references) , and I realize that the Microsoft Word Editor focus not only on productivity, it also help us to fight bias and to be more inclusive while we are writing.

Important: this feature is not enabled by default. In order to enable this, we must follow these steps “

Open Word Options
Select Proofing section
Go to [When correcting spelling …. / Writing Style] option
Open Settings
Enable the [Inclusiveness] options

enable Inclusiveness options in Microsoft Word

Once we enable these features, the editor will start to analyze for age bias, cultural bias, and more.

I’ve tested this, and it’s nice to get suggestions based on gender bias, like use firefighter instead of fireman.

suggestion change fireman by firefighter

It also suggest other options if we are using “whitelist”

In the references sections, I shared 2 amazing articles where Microsoft explains the details about this feature.

And, in the personal side, this is also a great tool for non-english speakers like myself, to learn Inclusiveness and also to do a better work.

Super cool !

Happy coding!

Greetings

El Bruno

References

Office and AI

#event – #GlobalAI On Tour Toronto, on Saturday June 27, let’s rock a full morning about AI

Hi !

The Global AI On Tour is a free event organized across the world in April, May and June by local communities that are passionate about artificial intelligence on Microsoft Azure.

We will run this in Virtual mode, so for our local one, the one for the Great Toronto Area, we are going to have speakers from all over the world !!!

Registration: https://www.meetup.com/metrotorontoug/events/267885516/

Agenda

https://sessionize.com/api/v2/tti45lz7/view/GridSmart?preview=True

9:30 – 9:45
Introduction and Opening

9:45 – 10:35
Computer, make it so! by Veronika Kolesnikova

10:40 – 11:30
Make your Mixed Reality App include AI with Cognitive Services by Ivana Tilca

11:35 – 12:25
AI and Cognitive Services in Power BI by Ashraf Ghonaim

Happy coding!

Greetings

El Bruno

#Event – Resources used during the #AI session on the Best of Build 2020 – Canada Community Edition event

Hi !

After an amazing event last Saturday, where we shared our best choices after Microsoft Build, now it’s time to share the resources used in the Artificial Intellitence session.

Let’s code a drone to follow faces syncing everything with Azure IoT

¿Con ganas de ponerte al día?

Share this:

Like this:

Intro and Welcome

Session. 10:00 – 10:10

Introduction to AI and Cognitive Services for Developers and Information Workers

Session 1. 10:10 – 11:00

Understanding Autonomous systems, Machine Teaching and Bonsai Platform

Session 2. 11:10 – 12:00

Knowledge Mining and MLOps

Session 3. 12:10 – 13:00

Share this:

Like this:

Slides

Code

Resources

Coding4Fun Drone posts

Share this:

Like this:

References

Share this:

Like this:

Data Source Images

Import and label Images

Train

Test with new images

Export generated model

References

Share this:

Like this:

Learn to pronounce

Share this:

Like this:

Share this:

Like this:

References

Office and AI

Share this:

Like this:

Registration: https://www.meetup.com/metrotorontoug/events/267885516/

Agenda

Share this:

Like this:

Slides

Resources

Virtual Stage

AI KeyNote

AI Super Computer

Cognitive Services

Project Bonsai

Share this:

Like this: