Watson Visual Recognition allows enterprise developer the ability to quickly & accurately tag, classify & train visual content using machine learning.
In this workshop we'll learn how to customize Watson perfectly for your unique use case. Using Watson Studio & only a few images, Watson can learn any new object, person, or attribute.
But how do manage Watson Visual Recognition at scale? Typical scale scenarios may include collections with tens of thousands of images. We'll look at building a Digital Asset Management (DAM) workflow with Cloudinary to automate your Watson Visual Recognition workflow. We'll leverage Cloudinary's APIs to upload, auto tag, resize & prepare your image collections for Watson.
The agenda will include:
* Discussion on training images & best practices for creating Watson Visual Recognition custom models.
* How to leverage a Digital Asset Management solution to find & manage your AI Training images.
* Discussion on how to efficiently scale the AI workflow for the enterprise from a single class to 10,000's.
You will also be introduced to IBM code patterns (http://ibm.biz/C4CTranslate) that give you a 360-degree view of the underlying code, including overviews, architecture diagrams, process flows, repo pointers, & additional reading.
Your speakers are Dan Zeitman, Developer Advocate at Cloudinary & Upkar Lidder, Developer Advocate at IBM.