DeepStream Python Apps - freecodes.cloud

DeepStream Python Apps

This repository contains Python bindings and sample applications for the DeepStream SDK. SDK version supported: 6.4

This release only supports Ubuntu 22.04 for DeepStreamSDK 6.4 with Python 3.10 and gst-python 1.20.3! Ubuntu 20.04 for DeepStreamSDK 6.3 with Python 3.8 support is NOW DEPRECATED

The bindings sources along with build instructions are available under bindings! We include one guide for contributing to bindings and another guide for advanced use-cases such as writing bindings for custom data structures.

Download the latest release package complete with bindings and sample applications from the release section.

Please report any issues or bugs on the DeepStream SDK Forums. This enables the DeepStream community to find help at a central location.

Python Bindings

DeepStream pipelines can be constructed using Gst Python, the GStreamer framework’s Python bindings. For accessing DeepStream MetaData, Python bindings are provided as part of this repository. This module is generated using Pybind11.

python apps - freecodes cloud

These bindings support a Python interface to the MetaData structures and functions. Usage of this interface is documented in the HOW-TO Guide and demonstrated in the sample applications.

Python Bindings Breaking API Change

The binding for function alloc_nvds_event_msg_meta() now expects a NvDsUserMeta pointer which the NvDsEventMsgMeta is associated with. Please refer to deepstream-test4 and bindschema.cpp for reference.

Sample Applications

Sample applications provided here demonstrate how to work with DeepStream pipelines using Python.
The sample applications require MetaData Bindings to work.

To run the sample applications or write your own, please consult the HOW-TO Guide

python apps - freecodes cloud

We currently provide the following sample applications:

Detailed application information is provided in each application’s subdirectory under apps.

GITHUB REPOSITORY

https://github.com/NVIDIA-AI-IOT/deepstream_python_apps

  • All rights reserved to the respective owners/authors