YOLO26 on DeepStream — working example + parser submitted as PR (deepstream_tools #2)

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
9.0
• Issue Type( questions, new requirements, bugs)
new requirements
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I followed the blog post on building vision AI pipelines with DeepStream (link) and the new doc covering YOLO26 setup, but I couldn’t find an actual working end-to-end example anywhere in the repos.

So I put one together and opened a PR on the deepstream_tools repo: Add YOLOv26 DeepStream support (DS8.0 + DS9.0 validated) by levipereira · Pull Request #2 · NVIDIA-AI-IOT/deepstream_tools · GitHub

It would be great if the team could take a look and consider merging it.

3

Thanks for your feedback.
We provided a set of DeepStream skills for code generation, including a YOLOv26 example; you can refer to this. Cursor/ClaudeCode/CodeX can be used for automated programming.

4

Thanks! Adding AI resources to the repo is definitely valuable. However, considering not everyone in the community uses these tools daily yet, a working base code maintained by NVIDIA still carries huge weight and provides a much easier starting point.