#Event – Resources used on my session at the largest Canada makeathon: @MakeUofT [How a PoC at home can scale to Enterprise Level using #CustomVision APIs]

2019 02 16 MakeUofT Custom Vision Bruno

Hi !

What an amazing time at the Canadian Largest Makeathon: MakeUofT (https://ieee.utoronto.ca/makeuoft/). The event, people and ideas are great. And now it’s time to share some of the materials used during my session

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 going to be described and explained in this session.

These are the slides I’ve used

And the source code is available here

https://github.com/elbruno/events/tree/master/2019%2002%2016%20MakeUofT%20Custom%20Vision

In the source code you can find the console and Windows 10 app samples I’ve coded live and also the exported images of my custom vision demo project in windows, linux and raspberry pi flavors. The 3rd one is where I spent some time updating the original linux one to work on the small device.

And as usual a couple of interesting links

Greetings @ Toronto

El Bruno

Advertisements

#Personal – My first and amazing #CodeMash

Hi!

Last week I was lucky enough to attend my first CodeMash (www.codemash.org). The experience was amazing, you just have to see the agenda and the speakers to see the quality of the event.

An interesting detail of the event is that it takes place in Ohio, in January. In other words, it is so cold and there is so much snow outside, that the only option you have is to stay at the event, attend the sessions and do networking, a lot networking.

The format of the sessions is quite interesting. The event starts on a Tuesday with 2 days of PreCompilers. These are all-day workshops around topics like Xamarin, AI, Containers and more. Never more than a 7 or 8 hour shift on a topic to have a intro On it.

codemash 19 bruno session

On Thursday, sessions begin in a more traditional way: sessions of 45 or 60 minutes. I was fortunate to have the 1st shift (08:00 AM!) to talk about Computer Vision. And during these days also take advantage to attend a couple of sessions. I liked a lot, but only mention 3:

  • The team of http://www.infernored.com/ did a great demo from scratch with Python and a RaspberryPi.
  • As always it was a pleasure to attend Jennifer’s session (@jennifermarsman) of AI for Earth. There are lot of incredible projects around make our world a better place, and I think we don’t care about this enough 😀
  • Kudos for Guy Rose (@guyroyse ) for his session [Deep Learning like a Viking]. It is not easy to do a Deep Learning session in fun and entertaining format, Guy has done it!

codemash 19 deep learning like a viking

The Weather forces you to stay all the time inside the hotel. If you are traveling with the family, this may seem like a problem, however the hotel has a Indoor WaterPark which is the ideal fun activity for children. I thought my kids would be all day in the WaterPark, but when they saw the agenda of the KidzMash, they spent all Day at the event.

KidzMash have sessions specially created for children and ranging from how to use duct Tape to 3d modeling and printing, just check the agenda http://www.codemash.org/kidzmash-schedule/.  It is something really amazing, for me it was a surprise and from here I want to thank you and congratulate the team CodeMash for this special flavor for children.

codemash 19 kidzmash

Another amazing place was the Game Room and the Laser Tags. We may need to be there until 02:00 AM to finish a 1000 pieces puzzle !

codemash 19 game room

I really recommend seeing the agenda, you may find sessions like the following ones:

  • [KidzMash] Systems Thinking for Kids
  • [KidzMash] Building Your First Video Game with Bloxels
  • [KidzMash] Gotta Catch ‘Em All!  Raspberry Pi and Java Pokemon Training

To finish, I don’t want to forget that I also had the opportunity to meet other MVPs from North America. Dinner in between and with amazing experiences.

codemash 19 mvp dinner

99% sure I’ll be at CodeMash 2020 !!!

Greetings @ Burlington

El Bruno

#Personal – Mis experiencias en mi primer #CodeMash

Buenas!

La semana pasada tuve la suerte de asistir a mi primer CodeMash (www.codemash.org). La experiencia fue increíble, solo hay que ver la agenda y los Speakers para ver la calidad del evento.

Un detalle interesante del evento es que se realiza en Ohio, en enero. Dicho de otra forma, hace tanto frio y hay tanta nieve afuera, que la única opción que tienes es quedarte en el evento, asistir a las sesiones y hacer networking, mucho networking.

El formato de las sesiones es bastante interesante. El evento empieza un martes con 2 días de PreCompilers. Estos son talleres de todo un día alrededor de temas como Xamarin, AI, Containers y más. Nunca esta de mas un turno de 7 u 8 horas sobre un tema para tener una intro sobre el mismo.

codemash 19 bruno session

El jueves ya comienzan las sesiones en modo mas tradicional: sesiones de 45 o 60 minutos. Yo tuve la suerte de tener el 1er turno (08:00 AM!) para hablar sobre Computer Vision. Y durante estos días también aproveche para asistir a un par de sesiones. Me gustaron muchas, aunque solo mencionare 3:

  • El equipo de http://www.infernored.com/ me dejo asombrado con una demo desde cero con Python y una RaspberryPi.
  • Como siempre fue un placer asistir a la sesión de Jennifer Marsman (@jennifermarsman) de AI for Earth. La visión y el trabajo que se hace desde Microsoft en este campo, no se da a conocer tanto como debería.
  • Kudos para Guy Rose (@guyroyse) por su sesión [Deep Learning like a Viking]. No es fácil hacer una sesión de DL en formato divertido y ameno, Guy lo ha hecho!

codemash 19 deep learning like a viking

Antes comente que el clima te obliga a estar todo el tiempo dentro del hotel. Si viajas con la familia, esto puede parecer un problema, sin embargo, el hotel tiene un WaterPark Indoor que es la diversión ideal para los niños. Yo pensaba que mis enanos estarían todo el día en el WaterPark, pero cuando vieron la agenda del KidzMash, se pasaron todo el dia en el evento.

KidzMash son sesiones especialmente creadas para niños y que van desde como usar duck tape hasta modelado e impresión 3D, solo hay que ver la agenda http://www.codemash.org/kidzmash-schedule/.  Es algo realmente increíble, para mi fue una sorpresa y desde aquí les quiero dar las gracias y felicitar al equipo de CodeMash por este flavor especial para niños.

codemash 19 kidzmash

Ademas la Game Room era una parada obligatoria. Por mas que nos tuviesemos que quedar hasta las 02:00 para armar un puzzle de 1000 piezas!

codemash 19 game room

Realmente recomiendo ver la agenda, para encontrar sesiones como las siguientes

  • [KidzMash] Systems Thinking for Kids
  • [KidzMash] Building Your First Video Game with Bloxels
  • [KidzMash] Gotta Catch ‘Em All!  Raspberry Pi and Java Pokemon Training

Para finalizar, no me quiero olvidar que también tuve la oportunidad de conocer otros MVPs de North America. Cena de por medio y con unas experiencias asombrosas.

codemash 19 mvp dinner

99% seguro que nos veremos en el CodeMash 2020 !!!

Saludos @ Burlington

El Bruno

#Event – Resources used on my @CodeMash session [How a PoC at home can scale to Enterprise Level using #CustomVision APIs]

code mash bruno session

Hi !

What an amazing time at CodeMash (http://codemash.org/). This conference is one the best experiences I’ve had so far. I’ll write a more detailed post next week, this one is to share some of the materials used during my session

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 going to be described and explained in this session.

These are the slides I’ve used

And the source code is available here

https://github.com/elbruno/events/tree/master/2019%2001%2010%20CodeMash%20CustomVision

In the source code you can find the console and Windows 10 app samples I’ve coded live and also the exported images of my custom vision demo project in windows, linux and raspberry pi flavors. The 3rd one is where I spent some time updating the original linux one to work on the small device.

And as usual a couple of interesting links

Greetings @ Sandusky, Ohio

El Bruno

#Event – I’ll be at @CodeMash on Ohio in 17 days sharing some #AI and #CustomVision experiences

codemash-logo

Hi!

I’m going to be part of one of the most amazing developer events in NA: CodeMash (http://www.codemash.org/). It will be my first time in Ohio, and also it will be an amazing opportunity to network and have some face-to-face chats with some amazing people. (Just look at the Speaker List)

I was also lucky to host a session around Artificial Intelligence with Cognitive Services at Enterprise Level. The latest announcements of containers and Cognitive Services are ready on time for this!

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 going to be described and explained in this session.

Session List: http://www.codemash.org/session-list/

Happy coding and see you there!

Greetings @ Toronto

El Bruno