Two Days to a Demo is our introductory series of deep learning tutorials for deploying AI and computer vision to the field with NVIDIA Jetson AGX Xavier, Jetson TX2, Jetson TX1 and Jetson Nano. This tutorial takes roughly two days to complete from start to finish, enabling you to configure and train your own neural networks. It includes all of the necessary source code, datasets, and documentation to get you started. Dive into deep learning today with Two Days to a Demo.

Hello AI World is a great way to start using Jetson and experiencing the power of AI. In just a couple of hours, you can have a set of deep learning inference demos up and running for realtime image classification and object detection on your Jetson Developer Kit with JetPack SDK and NVIDIA TensorRT. The tutorial focuses on networks related to computer vision, and includes the use of live cameras. You’ll also get to code your own easy-to-follow recognition program in Python or C++, and train your own DNN models onboard Jetson with PyTorch.

Hello AI World supports Jetson Nano, Jetson TX1/TX2, and Jetson AGX Xavier.

Ready to dive into deep learning? It only takes two days. We’ll provide you with all the tools you need, including easy to follow guides, software samples such as TensorRT code, and even pre-trained network models including ImageNet and DetectNet examples. Follow these directions to integrate deep learning into your platform of choice and quickly develop a proof-of-concept design. In this guide, you'll get a stronger background in deep learning, be able to load and run a pre-trained deep neural network on the Jetson AGX Xavier Developer Kit or Jetson TX1/TX2 Developer Kit, and learn how to retrain the network with your own dataset to produce a live demo.

DIGITS Workflow

Recommended System Requirements:

Training GPU:
  • Maxwell, Pascal, or Volta-based TITAN, Quadro, Tesla, or NGC instance.
  • Ubuntu 14.04 x86_64 or Ubuntu 16.04 x86_64 (see DIGITS AWS AMI).
Deployment:
  • Jetson TX1 Developer Kit with JetPack 2.3 or newer (Ubuntu 16.04).
  • Jetson TX2 Developer Kit with JetPack 3.0 or newer (Ubuntu 16.04).
  • Jetson AGX Xavier Developer Kit with JetPack 4.1 Developer Preview Early Access (Ubuntu 18.04).

Deep Learning ROS Nodes integrate the recognition, detection, and segmentation AI capabilities from Two Days to a Demo with ROS (Robot Operating System) for incorporation into advanced robotic systems and platforms. These realtime inferencing nodes can easily be dropped into existing ROS applications.

Versions of ROS that are supported include ROS Melodic (Jetson Nano, Jetson TX2, and Jetson AGX Xavier) and ROS Kinetic (Jetson TX1).

In this tutorial, we'll be creating artificially intelligent agents that learn from interacting with their environment, gathering experience, and a system of rewards with deep reinforcement learning (deep RL). Using end-to-end neural networks that translate raw pixels into actions, RL-trained agents are capable of exhibiting intuitive behaviors and performing complex tasks.

Deep Reinforcement Learning

Recommended System Requirements:

  • Jetson TX1 Developer Kit with JetPack 2.3 or newer (Ubuntu 16.04).
  • Jetson TX2 Developer Kit with JetPack 3.0 or newer (Ubuntu 16.04).

Interested in running TensorFlow networks optimally on Jetson TX1/TX2? Deep neural networks developed with TensorFlow can be deployed on NVIDIA Jetson and accelerated up to 5x with TensorRT. This tutorial covers the conversion of pretrained TensorFlow image classification models to TensorRT for deployment on the Jetson platform.

TensorFlow to TensorRT Workflow

Recommended System Requirements:

  • Jetson TX2 Developer Kit with JetPack 3.2 or newer (Ubuntu 16.04).


Want to dive deeper into Deep Learning?

Sign up for an online course in our Deep Learning Institute.