TEACHING YOU TO SOLVE PROBLEMS WITH DEEP LEARNING
NVIDIA Deep Learning Institute (DLI) offers hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning. DLI is excited to announce this one-day “Scene Description Generation with TensorFlow” hands-on workshop taking place in Sydney International Convention Centre on Thursday, August 10th.
WHAT WILL YOU LEARN?
In this hands-on workshop, attendees will train a network to generate captions from images and videos to learn:
- How to solve novel problems in deep learning by combining best practices.
- The fundamentals of both convolutional and recurrent neural networks using TensorFlow.
- How to process and prepare data for network ingestion, how to configure and train networks, and how to perform and evaluate inference.
- Problem specific skills such as:
- The difference between processing image and textual data
- Extracting high-level features from images
- One-hot sentence encoding
Thursday, August 10th 2017
Parkside 2 Meeting Room, International Convention Centre, Sydney AUSTRALIA (MAP)
09:30 - 11:30
Image Classification with DIGITS
11:30 - 12:30
12:30 - 14:30
Recurrent Neural Networks (RNNs) with TensorFlow
14:30 - 15:00
15:00 - 17:00
Scene Description Generation Combining Image Classification with RNNs using TensorFlow
DLI Workshop Attendee Instructions
- You must bring your own laptop to this workshop.
- Make sure your laptop is ready to go prior to the workshop by following these steps.
- Create a qwikLABS account by going to https://nvlabs.qwiklab.com/ using the same email address as you have for event registration.
- Ensure qwikLABS runs smoothly on your laptop by going to http://websocketstest.com/
- Make sure that WebSockets work for you by seeing under Environment, WebSockets is supported and Data Receive, Send and Echo Test all check Yes under WebSockets (Port 80).
- If there are issues with WebSockets, try updating your browser. Best browsers for qwikLABS are Chrome, FireFox and Safari. The labs will run in IE but it is not an optimal experience.