Make an Intelligent Video App at Speed

This event features hands-on tutorials by Santi Adavani (CTO and co-founder of RocketML), to learn how to build amazing Computer Vision apps from videos within hours. You will learn computer vision, OpenCV, object detection, pretrained models from TensorFlow Hub, Google Vision API and RocketML tools.

TOPICS

You will learn the following topics with hands-on tutorials:

OpenCV Image and Video Processing

• Learn how to use OpenCV to read and edit images
• Learn how to download videos from Youtube and read frames using OpenCV

Object Detection using Tensorflowhub

• Learn how to download object detection models from Tensorflow-hub and use them to detect objects in images
• Learn how to run object detection on video frames

Object detection using REST APIs

• Learn how to use Google Vision REST APIs to detect objects, logos, and landmarks
• Learn how to detect all these properties on video frames

Distributed object detection

• Learn how to use HPC clusters with 10 or 100s of cores simultaneously to perform object detection fast

UI application using Streamlit

• Learn how to use streamlit to build a UI to search and query object detection results

SPEAKER

Santi Adavani is the CTO and co-founder of RocketML. As CTO, Santi drives the technology roadmap that includes design and development of big data machine learning algorithms for cloud and on-prem HPC clusters. Before RocketML, Santi worked as a senior data scientist and AI product manager at Intel where he led development of AI systems for automated data management for yield enhancement. Prior to Intel, he received a PhD from the University of Pennsylvania, where he developed fast algorithms to solve partial differential equations (PDE) constrained optimization problems on supercomputers with applications in electro-cardiology.

Santi has given talks at large conferences such as O’Reilly AI conference, SparkAI Conferences and numerous tutorials in Machine Learning.