NVIDIA GPU Boot Camp and Deep Learning Workshop
Welcome to the NVIDIA GPU boot camp and deep learning workshop to be held at KTH on 24-25 September 2019!
Time: Tue 2019-09-24 08.30 - Wed 2019-09-25 17.30
Location: Room Fantum, Lindstedtsvägen 24, F-huset, floor 5, KTH, Stockholm
Whether you’re a seasoned researcher or novice programmer, you’re welcome to join this boot camp. Be prepared to learn, brainstorm, and build amazing real-world skills.
On the second day, you will learn deep learning techniques for a range of computer vision tasks through a series of hands-on exercises. You will work with widely-used deep learning tools, frameworks, and workflows to train and deploy neural network models on a fully-configured, GPU-accelerated workstation in the cloud. After a quick introduction to deep learning, you will advance to: building and deploying deep learning applications for image classification and object detection, modifying your neural networks to improve their accuracy and performance, and implementing the workflow you have learned on a final project. At the end of the workshop, you will have access to additional resources to create new deep learning applications on your own.
Although in most cases it will be relevant to attend both days of the workshop, if you would like to attend only one of the two days, you can opt to do so in the registration form .
Day 1: Introduction to GPU Programming with OpenACC
- Introduction to GPU programming (15 min)
- What is a GPU and Why Should You Care?
- What is GPU Programming?
- Available Libraries, Programming Models, Platforms
- Introduction to OpenACC (55 min)
- What is OpenACC and Why Should You Care?
- Profile-driven Development
- First Steps with OpenACC
- Lab 1
- OpenACC Data Management (55 min)
- CPU and GPU Memories
- CUDA Unified (Managed) Memory
- OpenACC Data Management
- Lab 2
- Gangs, Workers, and Vectors Demystified (55 min)
- GPU Profiles
- Loop Optimizations
- Lab 3
- Mini-application challenge (13:00-18:00)
- Overview of the mini-application (15 min)
- Review steps to acceleration (5 min)
- The application challenge using AWS and Linux academy infrastructure (the rest of the day)
Day 2: Fundamentals of Deep Learning for Computer Vision
In this hands-on course, you will learn the basics of deep learning by training and deploying neural networks. You will
- implement common deep learning workflows such as Image Classification and Object Detection,
- experiment with data, training parameters, network structure, and other strategies to increase performance and capability, and
- deploy your networks to start solving real-world problems.
On completion of this course, you will be able to start solving your own problems with deep learning.
- Introduction (45 min)
- Course overview
- Getting started with deep learning
- Unlocking New Capabilities (120 mins)
- Biological inspiration for deep neural networks (DNNs)
- Training DNNs with big data
- Break (45 min)
- Unlocking New Capabilities (40 mins)
- Deploying DNN models
- Measuring and Improving Performance (100 min)
- Optimizing DNN performance
- Incorporating object detection
- Summary (20 mins)
- Summary of key learnings
- Break (15 mins)
- Assessment (60 min)
- Assessment project: train and deploy a deep neural network
- Next Steps (15 mins)
- Workshop survey
- Setting up your own GPU-enabled environment
- Additional project ideas
Note that this event is only open to people who are working in academia or studying in academia.
Please register using your academic email address.To register for this event, please visit www.kth.se/form/5ce79caeeafec7224520bf3c .
Note that you can choose to register for only one of the two days, but we recommend attending both.
Upon successful completion of the Deep Learning workshop (day 2), participants will receive NVIDIA DLI Certification to recognize subject matter competency and support professional career growth.
To maximize your training time during this training, please follow the instructions below prior to attending the workshop:
- You must bring your own laptop in order to run the training.
- A current browser is needed. For optimal performance, Chrome, Firefox or Safari for Macs are recommended. Internet Explorer is operational but does not provide the best performance.
- Create an account at courses.nvidia.com/join .
- Ensure your laptop will run smoothly by going to websocketstest.com . Make sure that WebSockets work for you by looking under Environment, and see that WebSockets is supported and that Data Receive, Send and Echo Test all have "Yes" checked under WebSockets (Port 80). If there are issues with WebSockets, try updating your browser.
- If you have any questions, please contact Thor Wikfeldt at email@example.com .