Samples for TensorRT/Deepstream for Tesla & Jetson
Samples for TensorRT/Deepstream for Tesla & Jetson
This repository contains the reference applications for video analytics tasks using TensorRT and DeepSTream SDK 9.0.
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.
The project contains auxiliary dsdirection plugin to show the capability of DeepstreamSDK in anomaly detection.
The project demonstrates addition and deletion of video sources in a live Deepstream pipeline.
This sample app demonstrates DeepStream MaskTracker for multi-object tracking and segmentation using SAM2.
The sample app demonstrates single-view 3D tracking with DeepStream multi-object tracking to reconstruct 3D human model in world coordinates under occlusion.
The samples demonstrate multi-view 3D tracking in DeepStream, a distributed, real-time framework designed for large-scale, calibrated camera networks.
The project demonstrate how to implement multiple models inferencing in parallel with DeepStream APIs.
The sample demonstrate how to customize the multiple input layers model preprocessing and the customization of the bodypose 3D model postprocessing.
This sample demonstrates how to share video buffers over IPC and how to change output video buffers.
The sample demonstrates the usage of nvdsdynamicsrcbin in DeepStream pipeline.It helps to construct the application of multiple dynamic sources with a single video decoder to adapt to the high decoder throughput scenarios.
This sample demonstrates the usage of "custom-tile-config" of nvmultistreamtiler to customize the tiling positions and sizes of multiple videos in batch.
A GStreamer plugin for NVIDIA DeepStream that integrates Vision-Language Models (VLM) using VLLM for real-time video understanding and analysis.
The apps in pyservicemaker_sample_apps are additional samples demonstrating usage of the Python API for DeepStream Service Maker, either by flow API or by pipeline API. See the Python Service Maker documentation for details.
Some old samples are not supported any more for different reasons. The legacy samples are moved to the legacy folder /legacy_apps.
No open issues yet, or sync has not completed.