Deep Learning 4 Chickens and the MapR Convergence Conference

Contributed by

4 min read

Editor’s Note: Join MapR and others for a one-day Convergence event in Seattle, WA, on July 27 to explore new ideas and find practical solutions to your own big data challenges. Use this link to get a free pass (while supplies last)!

Ever since I first heard about Tensorflow and the promises of deep learning, I've been anxious to give it a whirl.


Tensorflow is a powerful and easy-to-use library for machine learning. It was open-sourced by Google in November 2015. In less than 2 years, it has become one of the most popular projects on GitHub. I was introduced to Tensorflow at the O'Reilly Strata Data conference in San Jose last year. During a presentation by developer evangelists from Google, I saw several really fun image processing examples that used Tensorflow to identify and transform subjects in images. That presentation was—to this particular machine learning novice—nothing less than jaw dropping.

Fast forward 6 months, and I've just deployed a Tensorflow application to my chicken coop with Raspberry Pi and MapR Edge. It's sort of an over-engineered attempt to detect blue jays in my nesting box and chase them away before they break any eggs. The app detects movement in the nesting box with a camera attached to a Raspberry Pi, then identifies the moving creature, using an image classification model implemented in Tensorflow, and posts that results to @TensorChicken on Twitter. To learn more about how I put it all together, see my blog.

Flow Diagram

The fact that I'm using Tensorflow on a Raspberry Pi in my chicken coop is laughable because Tensorflow is capable of so much more. It can perform colossally large computations across hundreds of servers, and it's a core component for sites like Google Photos and Google Search. The science and math behind the deep learning is mind-bogglingly sophisticated. Frameworks such as Tensorflow have made it approachable by hobbyists and startups, but operationalizing conceptual applications in production introduces a lot of difficult challenges.

Imagine a high-tech chicken farm, where potentially hundreds of chickens are continuously monitored by smart cameras looking for predators, animal illnesses, and other environmental threats. In scenarios like this, you quickly run into questions like:

  • How do you deal with the enormity of raw data streams?
  • How do you reliably archive raw data and make it searchable?
  • Where do you run computationally difficult machine learning workloads?

The MapR Convergence Conference

MapR Convergence Conference

If you are building next generation applications for your business, it can be really helpful to exchange ideas with birds of a similar feather.

MapR periodically hosts one-day conferences called MapR Convergence in various places around the world. These are big data conferences which bring together industry experts, key practitioners, and technology providers, such as MapR, AWS, and SAP. When you attend this event, you’ll have the opportunity to engage with other attendees and presenters to explore new ideas and find practical solutions to your own big data challenges.

MapR's next Convergence conference is coming soon, on July 27th at The W Hotel in Seattle!

If you shake a tail feather, you might be able to register for free with the following link. Good cluck!

Register now to receive a free pass - while supplies last!

This blog originally appeared on Ian Downard's LinkedIn on July 12, 2017.

Additional Resources

This blog post was published July 18, 2017.

50,000+ of the smartest have already joined!

Stay ahead of the bleeding edge...get the best of Big Data in your inbox.

Get our latest posts in your inbox

Subscribe Now