#Event – Building an Anomaly Detector System with a few or no lines of code at @MSFTReactor

Buy Me A Coffee

Hi !

Microsoft opened a brand new Microsoft Reactor in Toronto, and I’m lucky enough to host a AI session about Anomaly Detection. Below are the details

Detecting anomalies is a common scenario which can be applied to dozens of industries. From the analysis of power consumption, medical data, or even analysis of personal information, anomalies can be detected based on historical data.

During this workshop, Bruno will guide attendees to code a complete system that will detect anomalies: you will train a model based on historical data, and later use the same model with new data to identify anomalies. At the end of the workshop, attendees will review a new set of options to create an Anomaly Detection System without a single line of code!

Please bring a laptop or other personal device to participate in this hands-on workshop.

Event: https://www.microsoftevents.com/profile/form/index.cfm?PKformID=0x8330114abcd

Happy Coding!

Greetings @ Burlington

El Bruno

Advertisements

#Quantum – #Google AI Quantum, freaking awesome!

Buy Me A Coffee

Hi!

I was starting to read Nature article about Google Quantum breakthrough, and then I found this amazing video. No words, just amazing!

Greetings @ Toronto

El Bruno

References

#CustomVision – Label Images with suggested tags. Cool update for my #MSIgnite sessions

Buy Me A Coffee

Hi!

I’m updating some of my demos for Microsoft Ignite and I found an amazing new feature in Custom Vision: Suggested Tags (see references). This feature is super useful in scenarios for automatic detection, like the parking lot demo. I’ll use the official documentation to describe this feature

When you tag images for a Custom Vision model, the service uses the latest trained iteration of the model to predict the labels of untagged images. It then shows these predictions as suggested tags, based on the selected confidence threshold and prediction uncertainty. You can then either confirm or change the suggestions, speeding up the process of manually tagging the images for training.

Label images faster with suggested tags

And, as usual, let’s use 2 images to describe this. Once I add a new image to my Custom Vision project, I can start to select object and tag them. However, if I already trained my project, I will also see the [Suggested object on] option.

Custom Vision select objects and apply tags

With the default threshold value of 66%, the auto label feature does not detect any area. However, if I low the level, in example to 28%, it will automatically detect one of the parking slots: Slot 3. Once I’m happy with the suggested objects, I can confirm these objects and that’s it! Super easy.

Custom Vision enable suggested objects and low threshold

This feature is amazing, and I’m looking forward to using it in real projects to see how much time saves in image labeling scenarios.

Bonus: Below you can see the before and after of the demo project. My daughter also decorated the new parking lot box, with some IronMan content. I’ll need to figure out how to connect this with my session speech!

Happy coding!

Greetings @ Toronto

El Bruno

References

#Lego – Lego Replay, donate your bricks! #AmazingIdea

Buy Me A Coffee

Hi!

Short post today, however I think is the best one I’ve wrote in a while. That’s because, Lego has created a new amazing campaign where they help you to donate your old Lego bricks, for people who may not have access to Lego bricks.

The name of the campaign is LEGO Replay. And the main idea behind this, is to make it simple:

  • Put together all those loose LEGO pieces, that you may have (I know we have a lot!)
  • Place them into a cardboard box
  •  Visit the LEGO Replay website https://www.lego.com/replay
  • Print out a free shipping label
  • And send the box, via UPS or FedEx

Amazing!

As usual, a 60 seconds video is the best way to understand this

Happy coding!

Greetings @ Burlington

El Bruno

#AI – Getting started with #ComputerVision, #DeepLearning, and #OpenCV by Adrian Rosebrock @pyimagesearch

display face landmarks in python using face recognition
display face landmarks in python using face recognition
Buy Me A Coffee

Hi!

When you start to research the amazing world of Computer Vision, you find that there are plenty of courses, tutorials, videos and more resources. Something is kind of “too much”, and it’s not easy to choose where to start.

That’s why, when you arrive to one of the Adrian Rosebrock tutorials or articles, they’ll end in one of your favorites bookmarks. He has amazing detailed step by step tutorials, and I learned a lot of Raspberry Pi and OpenCV from his website.

A couple of weeks ago, Adrian released an amazing resource for Computer Vision enthusiasts:

Need help getting started with Computer Vision, Deep Learning, and OpenCV?

No matter if you are starting from zero, have some knowledge or you are already an expert; you must look at this amazing compile of resources. I’ll copy and paste the main topics

And I can’t thanks enough Adrian for his amazing work and also, for sharing all of this!

Happy coding!

Greetings @ Toronto

El Bruno

#Event – We will also have Learning Paths in #MSIgnite The Tour in Toronto on January 2020

Buy Me A Coffee

Hi!

In a couple of weeks; I’ll be at Microsoft Ignite 2019, and I’m very excited. I’ll have 2 sessions (see below), and I’m also excited for the networking opportunities and for some amazing sessions.

There are tons of awesome sessions, and one cool option that we have, is to choose a Learning Path around a specific subject like Artificial Intelligence, Workplace Modernization, Modern Operations, etc.

What is a Learning Path at Microsoft Ignite?

A Learning Path is a series of connected learning modules that include sessions, hands-on experiences, technical workshops, certifications, and expert connections. Each Learning Path works together to build upon what you’ve learned to provide a comprehensive set of skills to help you reach your goals.

https://myignite.techcommunity.microsoft.com/learning-paths

This is so cool!

And, even cooler, we will have Learning Paths in our own Microsoft Ignite The Tour in Toronto, on January 2020.

Microsoft Ignite The Tour in Toronto, on January 2020.

Microsoft Ignite The Tour brings the very best of Microsoft Ignite to a city near you. The tour provides technical training led by Microsoft experts and your community. You’ll learn new ways to build solutions, migrate and manage infrastructure, and connect with local industry leaders and peers.

Registration and more at https://www.microsoft.com/en-ca/ignite-the-tour/toronto#day1  

Greetings @ Toronto

El Bruno

My Sessions at Ignite

Diversity is more, much more! Living in tech as a Latino who can’t dance

I was born and raised in Argentina, then I lived eleven years in Spain working all around Europe. Finally, three years ago I moved to Canada. And yes, my Latin background impacted my professional career.

This session is mostly sharing what I’ve learned during these past years. How I learned to get the most from sentences like “You have a very strong accent; I don’t think you will fit this meeting. These are Senior Executives” or “Wow, your accent is amazing, our leadership team will love it!” In both scenarios, I manage to move from frustration or surprise to “let’s focus on our business.”

And it’s not only about language and accent; family, culture, and even food and drinks are a part of the story. Espero que nos veamos en la sesion!

https://myignite.techcommunity.microsoft.com/sessions/80650?source=sessions

How a PoC at home can scale to enterprise level using custom vision APIs

It all started with a DIY project to use computer vision for security cameras at home. A custom machine learning model is the core component used to analyze pictures to detect people, animals, and more in a house environment. The AI processing is performed at the edge, in dedicated hardware and the collected information is stored in the cloud. The same idea can be applied to several CCTV scenarios, like parking lots, train stations, malls, and more. However, moving this into enterprise scale brings a set of challenges, which are described and explained in this session.

https://myignite.techcommunity.microsoft.com/sessions/78686?source=sessions

#Windows10 – Cleaning some disk space, Windows SDK and #dotnetcore installs

Buy Me A Coffee

Hi!

I’m very careful with my disk space, however my C: drive in Windows 10 started to claim about low space. I got 3 disks on my machine, 2 SSDs and a regular one; and I always check to install all my software on my D: drive. So, that’s why running low space on C: was shocking.

So, I did a small check on the apps and contents using a lot of disk and I found 2 main sources

  • Windows 10 SDKs
  • DotNet Core SDKs and Runtimes

Every time a new version of Windows 10 is released, and I build a Windows 10 App, I get a new Windows SDK. Each one is around 2GBs, I got almost 20, so make your numbers.

Windows 10 Settings App and Features Apps sizes

Note: There is a cool feature to find usage space of installed apps by this, out of the box in Windows Settings.

The second one was related to .Net Core. I had a lot of versions installed, and every time I get a new update on Visual Studio 2019, it seems that I’m updating also my .Net Core SDKs. Right now, I only care about .Net Core 3, so it was time to uninstall all the others.

The official documentation ” How to remove the .NET Core Runtime and SDK” (see references) wasn’t very helpful. However, it was a good source to learn more about dotnet command, specially this one:

C:\> dotnet --list-sdks

This command list all the installed SDKs, and with a little of PowerShell scripting I manage to uninstall almost everything. Once I started this path, I also realize that the

$app.Uninstall()

command was not working, so a little search pointed me into an old article from Scott Hanselman, where he did a similar script to remove old .Net Core versions (see references).

The final script is

You can also get the ps1 file directly from GitHub here https://github.com/elbruno/Blog/tree/master/20191016%20Uninstall%20NetCore%20Versions

And a warning, the script will list all the installed dotnet sdks

And then, when the uninstall process start, we will require to confirm each uninstall action. Not very user friendly, but it get the work done!

Final advice is to repair the .Net Core 3 version, just in case something is missing.

Happy coding!

Greetings @ Burlington

El Bruno

References

#Event – #GlobalAIBootcamp 2019, Call for Speakers and pre-registration open !

Buy Me A Coffee

Hi !

The Global AI Bootcamp is a free one-day event organized across the world by local communities that are passionate about artificial intelligence on Microsoft Azure.

The Global #AI Bootcamp is a perfect balance of quality content, awesome talks, and hands-on learning with like-minded peers in your community. As usual, a video is better than my words:

And, here is a list of resources for the event.

Resources

See you on December!

Happy Coding!

Greetings @ Burlington

El Bruno