Learn how to leverage deep neural networks (DNN) within the deep learning workflow to solve a real-world image classification problem using NVIDIA DIGITS. You will walk through the process of data preparation, model definition, model training and troubleshooting. You will use validation data to test and try different strategies for improving model performance using GPUs. On completion of this lab, you will be able to use NVIDIA DIGITS to train a DNN on your own image classification application.
This lab explores three approaches to identify a specific feature within an image. Each approach is measured in relation to three metrics: model training time, model accuracy and speed of detection during deployment. On completion of this lab, you will understand the merits of each approach and learn how to detect objects using neural networks trained on NVIDIA DIGITS using real-world datasets. Prerequisites: Basic knowledge of data science and machine learning. This lab utilizes GPU resources in the cloud, you are required to bring your own laptop.
Prerequisites
This course is focus on Deep learning theory and hands on instruction, with preliminary programming background is recommended.
Recommend student should at least complete NVIDIA DLI online course: 'Getting Start with Deep Learning' before registration.
This course is inter-mediate level, student must be familiar with QWIKLAB instruction interface, and have some knowledge about Python language and training models. You will require to bring your own laptop and install required software and operating package require upgrade to recommended version.
Deep Learning for Image Segmentation
Course Description
There are a variety of important applications that need to go beyond detecting individual objects within an image, and that will instead segment the image into spatial regions of interest. An example of image segmentation involves medical imagery analysis, where it is often important to separate the pixels corresponding to different types of tissue, blood or abnormal cells, so that you can isolate a particular organ. Another example includes self-driving cars, where it is used to understand road scenes. In this lab, you will learn how to train and evaluate an image segmentation network.
Prerequisites
This course is focus on Deep learning theory and hands on instruction, with preliminary programming background is recommended.
Recommend student should at least complete NVIDIA DLI online course: 'Getting Start with Deep Learning' before registration.
This course is inter-mediate level, student must be familiar with QWIKLAB instruction interface, and have some knowledge about Python language and training models. You will require to bring your own laptop and install required software and operating package require upgrade to recommended version.
Medical Image Segmentation using NVIDIA DIGITS
Course Description
This lab explores various approaches to the problem of semantic image segmentation, which is a generalization of image classification where class predictions are made at the pixel level. We use the Sunnybrook Cardiac Data to train a neural network to learn to locate the left ventricle on MRI images. In this lab, you will learn how to use popular image classification neural networks for semantic segmentation, how to extend Caffe with custom Python layers, become familiar with the concept of transfer learning and train two Fully Convolutional Networks (FCNs). Prerequisites: Basic knowledge of Convolutional Neural Networks. This lab utilizes GPU resources in the cloud, you are required to bring your own laptop.
Prerequisites
This course is focus on Deep learning theory and hands on instruction, with preliminary programming background is recommended.
Recommend student should at least complete NVIDIA DLI online course: 'Getting Start with Deep Learning' before registration.
This course is inter-mediate level, student must be familiar with QWIKLAB instruction interface, and have some knowledge about Python language and training models. You will require to bring your own laptop and install required software and operating package require upgrade to recommended version.
Neural Network Deployment with NVIDIA DIGITS and TensorRT
Course Description
This lab will show three approaches for deployment. The first approach is to directly use inference functionality within a deep learning framework, in this case DIGITS and Caffe. The second approach is to integrate inference within a custom application by using a deep learning framework API, again using Caffe, but this time through its Python API. The final approach is to use the NVIDIA TensorRT, which will automatically create an optimized inference run-time from a trained Caffe model and network description file. In this lab, you will learn about the role of batch size in inference performance, as well as various optimizations that can be made in the inference process. You will also explore inference for a variety of different DNN architectures trained in other DLI labs. Prerequisites: C++ programming experience. This lab utilizes GPU resources in the cloud, you are required to bring your own laptop.
Prerequisites
This course is focus on Deep learning deployment and inferencing hands on training, student requires to have programming background.
Recommend student should attend beginner Instructor-led Labs hosted by NVIDIA Deep Learning Institute before.
This course is advanced level, student must be familiar with QWIKLAB instruction interface, and have some knowledge about Python language, C++ language, and training models. You will require to bring your own laptop and install required software and operating package require upgrade to recommended version.
Image Classification and Object Detection using NVIDIA Jetson TX2
Course Description
Learn to build an end-to-end Deep Learning pipeline. You'll develop the skills to not only train a deep neural network but also how to deploy it in a production environment. In this lab, you take pre-trained image classification and object detection networks and deploy them on Jetson TX1 or TX2 Developer Kits. You will then test these networks using the built-in camera to classify and detect several real-world objects. The networks will be deployed in a variety of programming environments, and we will even cover how to optimize classification and detection performance at runtime using NVIDIA's TensorRT inference engine library.
Prerequisites
This course is focus on Deep learning deployment and inferencing hands on training, student requires to have programming background.
Recommend student should attend beginner Instructor-led Labs hosted by NVIDIA Deep Learning Institute before.
This course is advanced level, student must be familiar with QWIKLAB instruction interface, and have some knowledge about Python language, C++ language, and training models. You will require to bring your own laptop and install required software and operating package require upgrade to recommended version.
NVIDIA AI Forum
GPU deep learning is bringing on a new era of AI computing. By drawing inspiration from the processes in the human brain, we are making machines that can perceive, understand, and react to the real world. From UAVs to the data center, this technology is being used to help in our lives, and change every industry over time.
Register for NVIDIA AI Forum on May 30 to join the conversation about the future of AI. The NVIDIA DEEP LEARNING INSTITUTE also hosts instructor-led workshops on May 31 to help you learning more about deep learning solutions.
AGENDA
5.30
5.31
NVIDIA AI FORUM
TIME
EVENT
11:30 - 12:30
KEYNOTE Jensen Huang Founder, President and CEO, NVIDIA
13:30 - 14:20
AI in IoT and Smart Cities Deepu Talla VP and GM, Mobile Business Unit, NVIDIA
14:30 - 15:20
AI in Healthcare and Bioinformatics Ethan Tu Taiwan AI Lab
15:30 - 16:30
The Roadmap to AI: How to Get Started Getting buy-in, assembling the team, and more Marc Hamilton VP, Solutions Architecture and Engineering, NVIDIA