Classify things in Go: the easy way. Building classifiers quickly with the community contributions.

Go and public training models can provide great potential: A fast way to build "eyes around the world", also known as classifiers. And with great powers, come great opportunities, such as building fantastic applications to turn our world a better place to live through the technology with few steps.

Go and public training models can provide great potential: A fast way to build "eyes around the world", also known as classifiers. And with great powers, come great opportunities, such as building fantastic applications to turn our world a better place to live through the technology. The GO language, have GoCV package, and it provides the most modern and advanced Computational Vision libraries that exist like OpenCV. In this talk, I'll demonstrate how to use public models from TensorFlow Hub and OpenCV library to easily build classifiers for APIs, taking a super leap from draft to a working classifier, in a few steps! The idea is to demystify the concepts behind classifiers and show how to build one in a few steps and make rankers accessible to the business, showing how GO does this in a unique, scalable and self-performing way, and of course, encouraging the community to contribute and sharing more training models to they can turn more and more accurate!

Transcript

1. Classify things in GO: The Easy Way Sheimy Rahman Software Engineer at Nuveo.ai @Sheimy_Rahman
2. Who am I?
3. Who am I? Sooo close! Is Sheimy :)
4. Session Content Introduction to CV Classifiers Challenge Models from community TensorFlow Hub and others Open Libraries Why use GoCV Gopher’s butt
5. What is Computer Vision? Is a field inside of Artificial Intelligence that trains computers to interpret and understand the human visual world. Through the images, videos and deep learning models, machines can have “eyes and brain” to identifying objects and then, they are capable to react to what they “see”.
6. Scenario A IOT company received a proposal of new client who asked for ten distinct image classifiers for a different products. Some classifiers will be wrapped into a API and connect into a Kafka’s queue and others will run independently. You need to do a POC (Proof Of Concept) to show to your company if is viable do it on the terms and time proposed. How would you do it?
7. Building Image Classifiers from scratch?
8. WRONG ANSWER!
9. The other way is:
10. Through the community and open source things like GoCV.
11. Why GoCV? • GoCV gives to gophers access to the OpenCV computer vision library. • GoCV package supports the latest releases of Go and OpenCV v.4 on Linux, macOS ans Windows! -> Yes, I said Windows! And I’ll prove that! making the CV accessible for everyone! • GoCV supports the Intel OpenVINO toolkit.
12. Show me the Code!
13. For who wants to learn more: • https://gocv.io/ • https://www.tensorflow.org/hub • http://caffe.berkeleyvision.org/ • My presentation QRCode
14. sheimyrahman@gmail.com https://github.com/SheimyRahman https://twitter.com/Sheimy_Rahman Thank you! :)