Deepstream Multistream tiler rtsp out

[mvpavan42]

Please provide complete information as applicable to your setup.

• Hardware Platform: GPU
• DeepStream Version: 6.2
• JetPack Version (valid for Jetson only)
• TensorRT Version 8502
• NVIDIA GPU Driver Version (valid for GPU only) 525.58
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hi,

I am facing an issue of :

nvbufsurface: NvBufSurfaceCopy: batch size doesn’t match

Here is my pipeline:

multisrcbin → stream_muxer → triton_server → nvvidconv → capsfilter → nvtiler → nvosd → nvvidconv2 → queue → nvv4l2h264enc → rtph264pay → udpsink

• I give multiple input sources and tile them after inference and pass through rtsp/filesink.
• When I use filesink with appropriate encoder and parser it works fine.
• But when I use rtsp I am facing the above issue at nvv4l2h264enc.

I understand it means input and output batch size for NvBufSurfaceCopy is not matching. However, I don’t understand why it’s happening.

If I run it with single source, it works fine, but not with more than one. Ideally after nvtiler irrespective of number of input sources the output batch size should be 1 right? Then why this error?

Thanks,
Pavan MV

[yuweiw]

@mvpavan42

nvbufsurface: NvBufSurfaceCopy: batch size doesn’t match

From the log you posted, we cannot determine which plug-in outputs this log. Could you provide us a minimized code that can be run in our env?

[mvpavan42]

Hi, Got it resolved. Its a bug from one of our video sources. Thanks.