NvOSD_MaskParams - missing from Python Bindings

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Orin
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only) 5.01
• TensorRT Version 8.4
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) Bug
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

Attempt to obtain NvOSD_MaskParams through Python bindings
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)


I’m trying to implement (in Python) a MRCNN model built with TAO (appropriate libs for the parser applied and working) however, during debugging it is noted that when attempting to obtain the mask parameters the debugger reports

Unable to convert function return value to a Python type!

I checked the forums and there was a suggestion that the bindings for maskParams is missing from the python bindings src and that the user needed to implement this further. On inspection of the


source, there does not seem to be any entry for the mask params (that would need additional modification).

How do we proceed, or how do we get the masks to appear (the model is displaying bounding boxes). I do not want to drop back to a C++ solution? I do not think this is a config issue, rather a missing piece to the python bindings.

Thank you.

The pyds python bindings are open source deepstream_python_apps/bindings at master · NVIDIA-AI-IOT/deepstream_python_apps (github.com), you can add the binding and build the pyds library.

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.