dusty-nv /jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

★ 9,034⑂ 3,119👁 278⑃ 88● 1,864▤ 1
Download: Model Download Mirrormodel-mirror-190618 ↓1906182019-06-18
+1
Daily
9,034
stars
3,119
forks
278
watchers
88
prs
1,864
issues
1
releases

README

Deploying Deep Learning
Welcome to our instructional guide for inference and realtime vision DNN library for NVIDIA Jetson devices.  This project uses TensorRT to run optimized networks on GPUs from C++ or Python, and PyTorch for training models.

Supported DNN vision primitives include imageNet for image classification, detectNet for object detection, segNet for semantic segmentation, poseNet for pose estimation, and actionNet for action recognition.  Examples are provided for streaming from live camera feeds, making webapps with WebRTC, and support for ROS/ROS2.



Follow the Hello AI World tutorial for running inference and transfer learning onboard your Jetson, including collecting your own datasets, training your own models with PyTorch, and deploying them with TensorRT.

 Table of Contents

 Hello AI World
 Jetson AI Lab
 Video Walkthroughs
 API Reference
 Code Examples
 Pre-Trained Models
 System Requirements
 Change Log

 >   JetPack 6 is now supported on Orin devices (developer.nvidia.com/jetpack) 
 >   Check out the Generative AI and LLM tutorials on Jetson AI Lab! 
 >   See the Change Log for the latest updates and new features. 

 Hello AI World

Hello AI World can be run completely onboard your Jetson, including live inferencing with TensorRT and transfer learning with PyTorch.  For installation instructions, see System Setup.  It's then recommended to start with the Inference section to familiarize yourself with the concepts, before diving into Training your own models.

 System Setup

 Setting up Jetson with JetPack
 Running the Docker Container
 Building the Project from Source

 Inference

 Image Classification
	 Using the ImageNet Program on Jetson
	 Coding Your Own Image Recognition Program (Python)
	 Coding Your Own Image Recognition Program (C++)
	 Running the Live Camera Recognition Demo
	 Multi-Label Classification for Image Tagging
 Object Detection
	 Detecting Objects from Images
	 Running the Live Camera Detection Demo
	 Coding Your Own Object Detection Program
	 Using TAO Detection Models
	 Object Tracking on Video
 Semantic Segmentation
	 Segmenting Images from the Command Line
	 Running the Live Camera Segmentation Demo
 Pose Estimation
 Action Recognition
 Background Removal
 Monocular Depth

 Training

 Transfer Learning with PyTorch
 Classification/Recognition (ResNet-18)
	 Re-training on the Cat/Dog Dataset
	 Re-training on the PlantCLEF Dataset
	 Collecting your own Classification Datasets
 Object Detection (SSD-Mobilenet)
	 Re-training SSD-Mobilenet
	 Collecting your own Detection Datasets

 WebApp Frameworks

 WebRTC Server
 HTML / JavaScript
 Flask + REST
 Plotly Dashboard
 Recognizer (Interactive Training)

 Appendix

 Camera Streaming and Multimedia
 Image Manipulation with CUDA
 DNN Inference Nodes for ROS/ROS2

 Jetson AI Lab



The Jetson AI Lab has additional tutorials on LLMs, Vision Transformers (ViT), and Vision Language Models (VLM) that run on Orin (and in some cases Xavier).

Top issues

Latest release

Model Download Mirror model-mirror-190618 2019-06-18
This release contains mirror downloads of the DNN models used by the repo.

During the build process, the jetson-inference repo will automatically attempt to download the models for you.  

The primary site storing the models is on Box.com.  However, users from China may be unable to access Box.com, so if your system is unable to download the models from their primary location, you can grab the models that you wish to download below.

For each model that you wish to use for inferencing at runtime, download the associated archive found below to your /data/networks directory, and then extr

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON