Discover NVIDIA-AI-IOT/TAO-Toolkit-Whitepaper-use-cases Open Source

An educational AI robot based on NVIDIA Jetson Nano.

4,547

jetbot

DeepStream SDK Python bindings and sample applications

3,012

deepstream_python_apps

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution, YUV2RGB, cuOSD,).

1,439

Lidar_AI_Solution

Samples for TensorRT/Deepstream for Tesla & Jetson

1,249

deepstream_reference_apps

An autonomous AI racecar using NVIDIA Jetson Nano

1,127

jetracer

Perception and AI components for autonomous mobile robotics.

1,059

redtail

Real-time pose estimation accelerated with NVIDIA TensorRT

1,013

trt_pose

TensorFlow models accelerated with NVIDIA TensorRT

974

tf_trt_models

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

683

nanosam

A project demonstrating how to use the libs of cuPCL.

616

cuPCL

yolo model qat and deploy with deepstream&tensorrt

551

yolo_deepstream

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

534

CUDA-PointPillars

Image classification with NVIDIA TensorRT from TensorFlow models.

525

tf_to_trt_image_classification

Easy to use Python camera interface for NVIDIA Jetson

454

jetcam

Sample apps to demonstrate how to deploy models trained with TAO on DeepStream

426

deepstream_tao_apps

jetson_benchmarks

deepstream_360_d_smart_parking_application

Describes the full end to end smart parking application that is available with DeepStream 5.0

JavaScript

340

deepstream_pose_estimation

This is a DeepStream application to demonstrate a human pose estimation pipeline.

A tutorial for getting started with the Deep Learning Accelerator (DLA) on NVIDIA Jetson

290

jetson_dla_tutorial

Face Mask Detection using NVIDIA Transfer Learning Toolkit (TLT) and DeepStream for COVID-19

272

face-mask-detection

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

243

nanoowl

This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.

230

deepstream-occupancy-analytics

217

tensorrt_plugin_generator

A simple tool that can generate TensorRT plugin code quickly.

An SD card image for web programming AI projects with NVIDIA Jetson Nano

215

jetcard

Real-time hand pose estimation and gesture classification using TensorRT

210

trt_pose_hand

An example of using DeepStream SDK for redaction

207

redaction_with_deepstream

205

deepstream_lpr_app

Sample app code for LPR deployment on DeepStream

203

jetson-cloudnative-demo

Multi-container demo for Jetson Xavier NX and Jetson AGX Xavier

cuDLA-samples

jetson-multicamera-pipelines

A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson

158

jetson-intro-to-distillation

Gesture recognition neural network to classify various hand gestures

143

Gesture-Recognition

Zero-label image classification via OpenCLIP knowledge distillation

129

clip-distillation

ROS 2 packages for PyTorch and TensorRT for real-time classification and object detection on Jetson Platforms

104

ros2_torch_trt

This repository provides YOLOV5 GPU optimization sample

101

yolov5_gpu_optimization

Semantic-Segmentation based autonomous indoor navigation for mobile robots

100

Foresee-Navigation

A project demonstrating how to use nvmetamux to run multiple models in parallel.

deepstream_parallel_inference_app

deepstream 4.x samples to deploy TLT training models

deepstream_4.x_apps

Sample app code for deploying TAO Toolkit trained models to Triton

tao-toolkit-triton-apps

ROS 2 package for NVIDIA DeepStream applications on Jetson Platforms

ros2_deepstream

Simple Python / C++ interface to CSI camera connected to NVIDIA Jetson.

argus_camera

Autonomous delivery robot with turtlebot3 and Jetson TX2

turtlebot3

A reference application for a local AI assistant with LLM and RAG

ros2_jetson

Shell

jetson-copilot

jetson-stereo-depth

An open source Jetson Nano baseboard and tools to design your own.

my-jetson-nano-baseboard

nvidia-tao

Easy to use neural networks for NVIDIA Jetson (and desktop too!)

jetnet

How to deploy open source models using DeepStream and Triton Inference Server

deepstream_triton_model_deploy

ROS2 node for 3D object detection using TAO-PointPillars.

jetson-generative-ai-playground

ros2_tao_pointpillars

An autonomous R.C. racecar which detects people.

Formula1Epoch

Makefile

ros2_trt_pose

ROS 2 package for "trt_pose": real-time human pose estimation on NVIDIA Jetson Platform

An autonomous deep learning indoor delivery robot made with Jetson

Electron

A project demonstrating how to make DeepStream docker images.

deepstream_dockers

Shell

ros2_jetson_stats

ROS 2 package for monitoring and controlling NVIDIA Jetson Platform resources

CUDA-accelerated Apriltag detection

isaac_ros_apriltag

Autonomous humanoid that picks up and throws away trash

jetson-trashformers

This repository provides optical character detection and recognition solution optimized on Nvidia devices.

NVIDIA-Optical-Character-Detection-and-Recognition-Solution

A pallet model trained with SDG optimized for NVIDIA Jetson.

sdg_pallet_model

ChatBot: sample for TensorRT inference with a TF model

JEP_ChatBot

A project that optimizes Whisper for low latency inference using NVIDIA TensorRT

jetson-min-disk

Shell

whisper_trt

This project demonstrate how to infer and track from a 360 videos by using the dewarper plugin.

Deepstream-Dewarper-App

deepstream-retail-analytics

A DeepStream sample application demonstrating end-to-end retail video analytics for brick-and-mortar retail.

Isaac ROS image_pipeline package for hardware-accelerated image processing in ROS2.

isaac_ros_image_pipeline

A project demonstrating how to train your own gesture recognition deep learning pipeline. We start with a pre-trained detection model, repurpose it for hand detection using Transfer Learning Toolkit 3.0, and use it together with the purpose-built gesture recognition model. Once trained, we deploy this model on NVIDIA® Jetson™ using Deepstream SDK.

gesture_recognition_tlt_deepstream

synthetic_data_generation_training_workflow

Workflow for generating synthetic data and training CV models.

Sample showing how to use YOLOv5 with Nvidia Isaac ROS DNN Inference

YOLOv5-with-Isaac-ROS

This sample shows how to train and deploy a deep learning model for the real time redaction of faces from video streams using the NVIDIA DeepStream SDK

retinanet_for_redaction_with_deepstream

scene-text-recognition

A series of plugins to the ROS navigation stack to incorporate deep learning inputs.

deep_nav_layers

Makefile

Nav2-with-Isaac-ROS-GEMs

tao_toolkit_recipes

AI kiosk with a camera and a projector to visualize waste type of cafeteria objects

GreenMachine

Visualization tool for 3D bounding box results of TAO-PointPillars

viz_3Dbbox_ros2_pointpillars

Set of demo to try Isaac ROS with Isaac SIM

isaac_demo

A notebook that demonstrates how to use the NVIDIA Intelligent Video Analytics suite to detect objects in real-time. We use Transfer Learning Toolkit to train a fast and accurate detector and DeepStream to run that detector on an NVIDIA Jetson edge device.

tlt-iva-examples

A reference example for integrating NanoOwl with Metropolis Microservices for Jetson

mmj_genai

ROS2 nodes for LLM, VLM, VLA

ros2_nanollm

Package containing nodes for deep learning in ROS.

caffe_ros

Hosting a tutorial documentation for running Isaac ROS Visual SLAM on Jetson device.

jetson_isaac_ros_visual_slam_tutorial

jetbot_mini

Real-time CenterNet based object detection on fused IR/Depth images from Kinect sensor. Works on NVIDIA Jetson.

centernet_kinect

DeepStream Libraries offer CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs for seamless integration into custom frameworks.

deepstream_libraries

In this workflow we demonstrate using SDG + TAO for a freespace segmentation application

robot_freespace_seg_Isaac_TAO

A project demonstration on how to use the GigE camera to do the DeepStream Yolo3 object detection, how to set up the GigE camera, and deployment for the DeepStream apps.

deepstream-yolo3-gige-apps

ros2_torch2trt_examples

ros2 packages for torch2trt examples

ROS2 package for trt_pos_hand, "Real-time hand pose estimation and gesture classification using TensorRT"

ros2_trt_pose_hand

Triton Migration Guide for DeepStreamSDK.

deepstream_triton_migration

ROS2-NanoOWL

ROS 2 node for open-vocabulary object detection using NanoOWL.

A collection of reference AI microservices and workflows for Jetson Platform Services

jetson-platform-services

Enables Jetson to be controlled with handpose using trt_pose

jetson_virtual_touchpanel

A project demonstration to do the industrial defect segmentation based on loading the image from directory and generate the output ground truth.

deepstream-segmentation-analytics

isaac_ros_common

Isaac ROS common utilities, Dockerfiles, and testing code.

Examples of converting different open-source deep learning models to TAO compatible format through TAO BYOM package.

tao_byom_examples

Husky Simulation and Hardware In the Loop simulation on Isaac SIM with Isaac ROS

husky_demo

A utility library to help integrate Python applications with Metropolis Microservices for Jetson

mmj_utils

100

a2j_handpose_3d