Feature request to implement function pyds.get_nvds_buf_surface_gpu(hash(gst_buffer) for Jetson devices

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) : Jetson Orin Agx
• DeepStream Version : Deepstream 6.2
• JetPack Version (valid for Jetson only) : 5.1-b147
• TensorRT Version : 8.5.2-1+cuda11.4
• Issue Type( questions, new requirements, bugs) : New Requirement

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Can you please make this function available for Jetson devices?

**pyds.get_nvds_buf_surface_gpu(hash(gst_buffer)**

It would be handy to do in-place operations on the image.

Have you tried deepstream_python_apps/apps/deepstream-imagedata-multistream-cupy at master · NVIDIA-AI-IOT/deepstream_python_apps (github.com)?

Hi @Fiona.Chen ! Yes, I did. But apparently, the function is only implemented for discrete GPUs and not for jetson devices. You can also find this under the Note section of the README file. “This application is only supported on x86, not Jetson.”

This requirement is already in our roadmap.

1 Like