There are billions of cameras and sensors worldwide, capturing an abundance of data that can be used to generate business insights, unlock process efficiencies and improve revenue streams.
Intelligent Video Analytics eConnect Session with Nvidia
-
-
-
Online
Online
Monday 26 October 2020
16:30 pm - 19:30 pm AEST
Join the session for live hands-on demo and discussion to know how to kick start your journey in the real-time Intelligent Video Analytics world.
This intermediate course will run online over two sessions from 4:30 pm to 7:30 pm
- Session one on 22 October
- Session two on 26 October
Instructors:
Dr Johan Barthelemy: After his PhD in Applied Mathematics at the University of Namur (Belgium), Dr Johan Barthélemy joined the SMART Infrastructure Facility of the University of Wollongong in 2014 where he is a Lecturer. He is also a NVIDIA Deep Learning Institute certified instructor for computer vision. He is leading the Digital Living Lab where he is developing innovative Artificial Intelligence of Things and Intelligent Video Analytics applications.
Dr. Ettikan Karuppiah: Director of Developers Ecosystem at NVIDIA (APAC South Region) assists innovators, researchers and techno-entrepreneurs to accelerate GPU adaptation for their R&D and software solutioning needs. He has direct experience and passionate in accelerated computing/software research, deep learning, design and development covering end-to-end needs. He also has published numerous publications, patents and software libraries from his past work.
Pre-requisite:
- Familiarity with Python, basic understanding of computer vision, basic knowledge of deep learning frameworks (Pytorch or Tensorflow)
- Access to a machine with a NVIDIA GPU and running under a Linux environment (GPU enabled cloud instance from Amazon, Google Cloud Platform, GPU EATER can be used).
Session 1: 22nd of October - Open Neural Network Exchange and Transfer Learning Toolkit
- Quickly prototype a deep learning IVA application using the ONXX model zoo
- ONXX – overview
- Demonstration
- Hands-on exercise
- Q and A
- Do not start from scratch: Fine tune an existing model for your needs
- Transfert Learning Toolkit – overview
- Demonstration
- Hands-on exercise
- Q and A
Session 2: 26th of October – TensorRT and DeepStream
- Optimising your model for real-time applications and power-consumption efficiency
- TensorRT – overview
- Demonstration
- Hands-on exercise
- Q and A
- Building smart cities applications: the DeepStream pipeline
- DeepStream – Overview
- Demonstration
- Hands-on exercise
- Q and A
