NVIDIA-AI-IOT/deepstream_reference_apps

Stars
1,127
Rank 41,294 (Top 0.9 %)
Language
C++
License
Other
Created over 6 years ago
Updated 3 months ago

NVIDIA-AI-IOT/deepstream_reference_apps

NVIDIA-AI-IOT

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Samples for TensorRT/Deepstream for Tesla & Jetson

Reference Apps using DeepStream 6.3

This repository contains the reference applications for video analytics tasks using TensorRT and DeepSTream SDK 6.3.

Getting Started

We currently provide three different reference applications:

Preferably clone this project in /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/

To clone the project in the above directory, sudo permission may be required.

For further details, please see each project's README.

back-to-back-detectors : README

The project shows usage of 2 detectors in cascaded mode

Anomaly Detection : README

The project contains auxiliary dsdirection plugin to show the capability of DeepstreamSDK in anomaly detection.

Runtime Source Addition Deletion: README

The project demonstrates addition and deletion of video sources in a live Deepstream pipeline.

Body Pose 3D: README

The project demonstrates usage of Body Pose 3D model in Deepstream application

torch2trt

An easy to use PyTorch to TensorRT converter

jetbot

An educational AI robot based on NVIDIA Jetson Nano.

Jupyter Notebook

deepstream_python_apps

DeepStream SDK Python bindings and sample applications

Jupyter Notebook

Lidar_AI_Solution

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,).

jetracer

An autonomous AI racecar using NVIDIA Jetson Nano

Jupyter Notebook

redtail

Perception and AI components for autonomous mobile robotics.

trt_pose

Real-time pose estimation accelerated with NVIDIA TensorRT

tf_trt_models

TensorFlow models accelerated with NVIDIA TensorRT

nanosam

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

cuPCL

A project demonstrating how to use the libs of cuPCL.

yolo_deepstream

yolo model qat and deploy with deepstream&tensorrt

CUDA-PointPillars

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

tf_to_trt_image_classification

Image classification with NVIDIA TensorRT from TensorFlow models.

jetcam

Easy to use Python camera interface for NVIDIA Jetson

Jupyter Notebook

deepstream_tao_apps

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

jetson_benchmarks

Jetson Benchmark

deepstream_360_d_smart_parking_application

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

deepstream_pose_estimation

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

jetson_dla_tutorial

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

face-mask-detection

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

nanoowl

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

deepstream-occupancy-analytics

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.

tensorrt_plugin_generator

A simple tool that can generate TensorRT plugin code quickly.

jetcard

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

trt_pose_hand

Real-time hand pose estimation and gesture classification using TensorRT

Jupyter Notebook

redaction_with_deepstream

An example of using DeepStream SDK for redaction

deepstream_lpr_app

Sample app code for LPR deployment on DeepStream

jetson-cloudnative-demo

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

cuDLA-samples

YOLOv5 on Orin DLA

jetson-multicamera-pipelines

jetson-intro-to-distillation

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

Gesture-Recognition

Gesture recognition neural network to classify various hand gestures

clip-distillation

Zero-label image classification via OpenCLIP knowledge distillation

ros2_torch_trt

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

yolov5_gpu_optimization

This repository provides YOLOV5 GPU optimization sample

Foresee-Navigation

Semantic-Segmentation based autonomous indoor navigation for mobile robots

deepstream_parallel_inference_app

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

deepstream_4.x_apps

deepstream 4.x samples to deploy TLT training models

tao-toolkit-triton-apps

Sample app code for deploying TAO Toolkit trained models to Triton

ros2_deepstream

ROS 2 package for NVIDIA DeepStream applications on Jetson Platforms

argus_camera

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

turtlebot3

Autonomous delivery robot with turtlebot3 and Jetson TX2

ros2_jetson

jetson-copilot

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

jetson-stereo-depth

my-jetson-nano-baseboard

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

nvidia-tao

Jupyter Notebook

jetnet

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

deepstream_triton_model_deploy

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

jetson-generative-ai-playground

ros2_tao_pointpillars

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

Formula1Epoch

An autonomous R.C. racecar which detects people.

ros2_trt_pose

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

Electron

An autonomous deep learning indoor delivery robot made with Jetson

deepstream_dockers

A project demonstrating how to make DeepStream docker images.

ros2_jetson_stats

ROS 2 package for monitoring and controlling NVIDIA Jetson Platform resources

isaac_ros_apriltag

CUDA-accelerated Apriltag detection

jetson-trashformers

Autonomous humanoid that picks up and throws away trash

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

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

sdg_pallet_model

A pallet model trained with SDG optimized for NVIDIA Jetson.

JEP_ChatBot

ChatBot: sample for TensorRT inference with a TF model

jetson-min-disk

whisper_trt

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

Deepstream-Dewarper-App

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

deepstream-retail-analytics

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

isaac_ros_image_pipeline

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

gesture_recognition_tlt_deepstream

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.

synthetic_data_generation_training_workflow

Workflow for generating synthetic data and training CV models.

Jupyter Notebook

YOLOv5-with-Isaac-ROS

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

retinanet_for_redaction_with_deepstream

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

scene-text-recognition

deep_nav_layers

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

Nav2-with-Isaac-ROS-GEMs

tao_toolkit_recipes

Jupyter Notebook

GreenMachine

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

viz_3Dbbox_ros2_pointpillars

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

isaac_demo

Set of demo to try Isaac ROS with Isaac SIM

tlt-iva-examples

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.

Jupyter Notebook

mmj_genai

A reference example for integrating NanoOwl with Metropolis Microservices for Jetson

TAO-Toolkit-Whitepaper-use-cases

TAO best practices. How to adapt for a new domain, new classes, and generalize the model with a small dataset using Nvidia's TAO toolkit

Jupyter Notebook

ros2_nanollm

ROS2 nodes for LLM, VLM, VLA

caffe_ros

Package containing nodes for deep learning in ROS.

jetson_isaac_ros_visual_slam_tutorial

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

jetbot_mini

centernet_kinect

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

deepstream_libraries

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

robot_freespace_seg_Isaac_TAO

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

deepstream-yolo3-gige-apps

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.

ros2_torch2trt_examples

ros2 packages for torch2trt examples

ros2_trt_pose_hand

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

deepstream_triton_migration

Triton Migration Guide for DeepStreamSDK.

ROS2-NanoOWL

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

jetson-platform-services

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

Jupyter Notebook

jetson_virtual_touchpanel

Enables Jetson to be controlled with handpose using trt_pose

deepstream-segmentation-analytics

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

isaac_ros_common

Isaac ROS common utilities, Dockerfiles, and testing code.

tao_byom_examples

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

husky_demo

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

mmj_utils

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

a2j_handpose_3d