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
+1
日增长
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
#1795Docker fails after reboot.23 comments · 2024-02-20#1605Exception: jetson.utils -- function wasn't passed a valid cudaImage or cudaMemory object22 comments · 2023-04-13#1731installation of jetson inference20 comments · 2023-09-16#1859RTSP Video Output Fails on Jetpack 613 comments · 2024-06-03#1781[gstreamer] gstCamera::Capture() -- an error occurred retrieving the next image buffer`12 comments · 2024-01-13#1715WebRTC - The stream has not shown in the browser12 comments · 2023-08-03#1806Custom object detection model training keeps failing11 comments · 2024-03-09#1792Unable to run author's TAO converter with resnet18_facedetect_pruned.etlt11 comments · 2024-02-05
Latest release
Model Download Mirror model-mirror-190618 2019-06-18This 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