No frames send from rtsp server to deepstream_test3

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): dPU A40.
• DeepStream Version: 6.4-triton-multiarch.
• TensorRT Version: 8.6.1.6.
• NVIDIA GPU Driver Version (valid for GPU only): 535.146.02.
• Issue Type( questions, new requirements, bugs): bugs.
• 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)

I’m using DeepStream with Python and the Docker image nvcr.io/nvidia/deepstream:6.4-triton-multiarch to run the deepstream_test3.py for an RTSP input, where I launch RTSP from offline video via cvlc and its duration equal one hour. However, it immediately show black screen and print **PERF: {‘stream0’: 0.0} frequently . But it runs fine with the same offline video without RTSP also If we use videos less than 30mins whether RTSP/Offline.

What does it mean ? Do you mean to stream the local file into rtsp stream through VLC ?

If what I described above is correct, I think the problem lies in the encoding parameters of the stream. This is not a problem with DeepStream.

I will check again thank you, but what meaning of printing **PERF: {‘stream0’: 0.0} frequently? because sometimes happen through streaming of real cameras, one by one frequently till all streams got 0 fps. @junshengy

This usually means that the RTSP Camera is disconnected, or that the data cannot be decoded (due to the lack of meta data such as sps/pps).

The pipeline does not work properly for inference

The scenario happen in our pipeline of real cameras where the pipeline works normally and at sometime some camera got **PERF: {‘stream0’: 0.0} one by one till all cameras @junshengy

this what happened with me @junshengy

As I mentioned above, when **PERF: {‘stream0’: 0.0} appears, you can first check whether the rtsp camera link has been disconnected.

You can use rtsp-reconnect-interval property of nvurisrcbin to reconnection.

without use rtsp-reconnect-interval property of nvurisrcbin to reconnection and all cameras have been disconnected, the pipeline continue forever with **PERF: {‘stream’: 0.0} for all cameras?

I tried using deepstream-test3.py to process multiple rtsp streams, and then tried to disconnect one of them.

Only the disconnected fps will become 0.0. I’m not sure what your network status is.

I think this has nothing to do with deepstream. Reconnection is a suitable solution for handling rtsp disconnection

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. Thanks

As a supplement, the batched-push-timeout parameter will also affect this scenario. You can refer to this FAQ.

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