Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Sample apps to demonstrate how to deploy models trained with TAO on DeepStream
| Date | Stars |
|---|---|
| 2026-07-24 | 454 |
| 2026-07-25 | 454 |
| 2026-07-28 | 454 |
| 2026-07-30 | 454 |
| 2026-08-06 | 454 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# This repository has ceased updates, please refer to https://github.com/NVIDIA/deepstream for latest DeepStream TAO sample applications.
# Integrate TAO model with DeepStream SDK
- [Integrate TAO model with DeepStream SDK](#integrate-tao-model-with-deepstream-sdk)
- [Description](#description)
- [Prerequisites](#prerequisites)
- [Download](#download)
- [1. Download Source Code with SSH or HTTPS](#1-download-source-code-with-ssh-or-https)
- [2. Download Models](#2-download-models)
- [Triton Inference Server](#triton-inference-server)
- [Build](#build)
- [Build Sample Application](#build-sample-application)
- [Run](#run)
- [Information for Customization](#information-for-customization)
- [TAO Models](#tao-models)
- [Label Files](#label-files)
- [DeepStream configuration file](#deepstream-configuration-file)
- [Model Outputs](#model-outputs)
- [1. CitySemSegFormer](#1-citysemsegformer)
- [2. PoseClassification](#2-poseclassification)
- [3~4. Retail Object Detection / PeopleNet Transformer](#34-retail-object-detection--peoplenet-transformer)
- [5~6. Re-Identification / Retail Item Recognition](#56-re-identification--retail-item-recognition)
- [7. BodyPose3DNet](#7-bodypose3dnet)
- [8~9. OCDNet / OCRNet](#89-ocdnet--ocrnet)
- [10~11. LPDNet / LPRNet](#1011-lpdnet--lprnet)
- [12. Mask2Former](#12-mask2former)
- [FAQ](#faq)
- [Measure The Inference Perf](#measure-the-inference-perf)
- [About misc folder](#about-misc-folder)
- [Others Models](#others-models)
- [TAO pyservicemaker samples](#tao-pyservicemaker-samples)
- [Known issues](#known-issues)
## Description
This repository provides a DeepStream sample application based on [NVIDIA DeepStream SDK](https://developer.nvidia.com/deepstream-sdk) to run twelve TAO models ( **Peoplenet Transformer** / **CitySemSegformer** / **Mask2Former** /**Reidentification** / **Bodypose3dnet** / **Pose Classifier** / **OCDNet**/ **OCRNet**/ **LPDNet** / **LPRNet** / **Retail Detector**/ **Retail Object Recognition** ) with below files:
- **apps**: sample application for detection models and segmentation models
- **configs**: DeepStream nvinfer configure file and label files
- **post_processor**: include inference postprocessor for the models
- **models**: The models which will be used as samples.
- **TRT-OSS**: The OSS nvinfer plugin build and download instructions. The OSS plugins are needed for some models with DeepStream 7.1 GA.
The pipeline of the sample:
```
|-->filesink(save the output in local dir)
|--> encode -->
|-->fakesink(use -f option)
uridecoderbin -->streammux-->nvinfer(detection)-->nvosd-->
|--> display
```
## Prerequisites
* [DeepStream SDK 9.0 GA](https://developer.nvidia.com/deepstream-sdk)
Make sure deepstream-test1 sample can run successful to verify your installation. According to the
[document](https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_docker_containers.html),
please run below command to install additional audio video packages.
```
/opt/nvidia/deepstream/deepstream/user_additional_install.sh
```
* Eigen development packages
```
sudo apt install libeigen3-dev
cd /usr/include
sudo ln -sf eigen3/Eigen Eigen
```
## Download
### 1. Download Source Code with SSH or HTTPS
```
sudo apt update
sudo apt install git-lfs
git lfs install --skip-repo
// SSH
git clone [email protected]:NVIDIA-AI-IOT/deepstream_tao_apps.git
// or HTTPS
git clone https://github.com/NVIDIA-AI-IOT/deepstream_tao_apps.git
//download submoudle
git submodule update --init --recursive
```
### 2. Download Models
Run below script to download models except multi_task and YoloV5 models.
Excerpt of 15,731 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:595fb33c43894f76, topic:tensorrt, readme:inference server