Deepstream python Reading RTSP Stream with 0 FPS

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

• Hardware Platform (Jetson / GPU) : Jetson Orin Nano
• DeepStream Version : 7.1
• JetPack Version (valid for Jetson only) : 6.2
• TensorRT Version : 10.3.0.30

Hi,

When I am running the deepstream python app, most of the time, it works fine, but some time, the FPS is showing 0 eventhough the RTSP stream is working fine,

image
image1313×668 78.1 KB


Now playing...
1 :  rtsp://192.168.20.104:8080/h264.sdp
Starting pipeline 

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvMultiObjectTracker] Initialized
Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode.
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:00.798239996   631 0xaaaad86daf20 INFO                 nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-7.1/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/yolov8n_320_15op_d.pt.onnx_b1_gpu0_fp16.engine
Implicit layer support has been deprecated
INFO: [Implicit Engine Info]: layers num: 0

0:00:00.798365788   631 0xaaaad86daf20 INFO                 nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary-inference> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-7.1/sources/deepstream_python_apps/apps/deepstream-imagedata-multistream/yolov8n_320_15op_d.pt.onnx_b1_gpu0_fp16.engine
0:00:00.805844797   631 0xaaaad86daf20 INFO                 nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus:<primary-inference> [UID 1]: Load new model:dstest_imagedata_config.txt sucessfully
Decodebin child added: source 


(python3:631): GStreamer-WARNING **: 13:48:03.135: ../gst/gstpad.c:4677:gst_pad_push_data:<rtpsession0:sync_src> Got data flow before segment event

(python3:631): GStreamer-WARNING **: 13:48:03.135: ../gst/gstpad.c:4416:gst_pad_chain_data_unchecked:<rtpssrcdemux0:rtcp_sink> Got data flow before segment event

(python3:631): GStreamer-WARNING **: 13:48:03.137: ../gst/gstpad.c:4677:gst_pad_push_data:<rtpssrcdemux0:rtcp_src_2796152137> Got data flow before segment event

(python3:631): GStreamer-WARNING **: 13:48:03.137: ../gst/gstpad.c:4416:gst_pad_chain_data_unchecked:<rtpjitterbuffer0:sink_rtcp> Got data flow before segment event
Decodebin child added: decodebin0 

Decodebin child added: rtph264depay0 

Decodebin child added: h264parse0 

Decodebin child added: capsfilter0 

Decodebin child added: nvv4l2decoder0 

Opening in BLOCKING MODE 
NvMMLiteOpen : Block : BlockType = 261 
NvMMLiteBlockCreate : Block : BlockType = 261 

**PERF:  {'stream0': 0.0} 


**PERF:  {'stream0': 0.0} 


**PERF:  {'stream0': 0.0} 

^CExiting app

[NvMultiObjectTracker] De-initialized

how to debug this issue, where is the issue for showing 0 FPS, it is not reading the frame,

thanks

3

Seems there is no frame came into the pipeline when the FPS is 0. Are you working with the deepstream-app sample? If so, please use “export GST_DEBUG=rtspsrc:7” command to enable the RTSP log before you run the app. Then you can check with the log to find out what happens when the FPS is 0.

4

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

5

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