414
edits
DeepStream 6.3 pipelines: Difference between revisions
→Introduction
No edit summary |
|||
| Line 5: | Line 5: | ||
On this page, you are going to find a set of DeepStream pipelines used on Jetson Xavier NX DevKit. This wiki page tries to describe some of the DeepStream features for the NVIDIA platforms and other multimedia features. The goal is to provide you some example pipelines. A general NVIDIA Deepstream overview can be found at: [https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Overview.html NVIDIA Deepstream overview]. | On this page, you are going to find a set of DeepStream pipelines used on Jetson Xavier NX DevKit. This wiki page tries to describe some of the DeepStream features for the NVIDIA platforms and other multimedia features. The goal is to provide you some example pipelines. A general NVIDIA Deepstream overview can be found at: [https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Overview.html NVIDIA Deepstream overview]. | ||
''' | '''Various Deepstream elements found in this wiki:''' | ||
* '''[https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html nvinfer]''': The Gst-nvinfer element performs inference on input data using NVIDIA TensorRT. It accepts batched NV12/RGBA buffers, converts and scales the data according to network requirements, and passes it to the TensorRT engine for inference. This plugin can operate in primary, secondary, or preprocessed tensor input modes and supports various object detection and classification networks. | * '''[https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html nvinfer]''': The Gst-nvinfer element performs inference on input data using NVIDIA TensorRT. It accepts batched NV12/RGBA buffers, converts and scales the data according to network requirements, and passes it to the TensorRT engine for inference. This plugin can operate in primary, secondary, or preprocessed tensor input modes and supports various object detection and classification networks. | ||
* '''[https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvtracker.html nvtracker]''': The Gst-nvtracker element allows the DeepStream pipeline to use a tracking library to track detected objects with unique IDs over time. It converts input buffers as needed and processes data in batch mode for efficient GPU execution. The plugin updates metadata with tracked object coordinates, tracker confidence, and object IDs. | * '''[https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvtracker.html nvtracker]''': The Gst-nvtracker element allows the DeepStream pipeline to use a tracking library to track detected objects with unique IDs over time. It converts input buffers as needed and processes data in batch mode for efficient GPU execution. The plugin updates metadata with tracked object coordinates, tracker confidence, and object IDs. | ||