Why can these sources be displayed in one window after configuring multiple sources on deepstream, but yolov5 can only identify one of them
Can you share the pipeline you used in your testing? Please also provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
• The pipeline being used
I created a docker container with a deepstream version of 6.0 in Ubuntu 20.04, and the graphics card is 3060. The problem is that I used the example of 30 video sources in the sample folder being displayed at the same time, and the result is that it can be scanned at the same time. However, when I use the configuration file written by myself, this configuration file can identify an RTSP video source and return the output result to the Kafka server, However, when I change to multiple RTSP streams, yolov5 can only identify one of the video sources at the same time, instead of identifying all the video sources at the same time as in the official case, and the data sent to Kafka server by the changed configuration file is only the scan data of one of the video sources
This is my profile（The instruction executed with is 【deepstream-test5-app xxxx.txt】）：
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[tiled-display]
enable=1
rows=2
columns=2
width=1280
height=720
gpu-id=1
nvbuf-memory-type=0
[source0]
enable=1
type=3
uri=rtsp://admin:123654zjk@10.129.53.45:554/h264/ch1/main/av_stream
num-sources=2
gpu-id=1
cudadec-memtype=0
drop-frame-interval=0
[source1]
enable=1
type=3
uri=rtsp://admin:123654zjk@10.129.53.45:554/h264/ch1/main/av_stream
num-sources=2
gpu-id=1
cudadec-memtype=0
drop-frame-interval=0
[sink0]
enable=1
type=2
sync=0
gpu-id=1
nvbuf-memory-type=0
[sink1]
enable=1
type=6
msg-conv-config=dstest5_msgconv_sample_config.txt
msg-conv-payload-type=1
msg-broker-proto-lib=/opt/nvidia/deepstream/deepstream-6.1/lib/libnvds_kafka_proto.so
msg-broker-conn-str=10.129.53.100;9092;video
topic=video2
iframeinterval=10
source-id=0
[sink2]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=0
bitrate=4000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
profile=0
set below properties in case of RTSPStreaming
rtsp-port=8554
udp-port=5400
[osd]
enable=1
gpu-id=1
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0
[streammux]
gpu-id=1
live-source=0
batch-size=4
batched-push-timeout=40000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
[primary-gie]
enable=1
gpu-id=1
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_gang.txt
batch-size=4
[tests]
file-loop=0
I created a docker container with a deepstream version of 6.1 in Ubuntu 20.04, and the graphics card is 3060. The problem is that I used the example of 30 video sources in the sample folder being displayed at the same time, and the result is that it can be scanned at the same time. However, when I use the configuration file written by myself, this configuration file can identify an RTSP video source and return the output result to the Kafka server, However, when I change to multiple RTSP streams, yolov5 can only identify one of the video sources at the same time, instead of identifying all the video sources at the same time as in the official case, and the data sent to Kafka server by the changed configuration file is only the scan data of one of the video sources
This is my profile（The instruction executed with is 【deepstream-test5-app xxxx.txt】）：
[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
[tiled-display]
enable=1
rows=2
columns=2
width=1280
height=720
gpu-id=1
nvbuf-memory-type=0
[source0]
enable=1
type=3
uri=rtsp://admin:123654zjk@10.129.53.45:554/h264/ch1/main/av_stream
num-sources=2
gpu-id=1
cudadec-memtype=0
drop-frame-interval=0
[source1]
enable=1
type=3
uri=rtsp://admin:123654zjk@10.129.53.45:554/h264/ch1/main/av_stream
num-sources=2
gpu-id=1
cudadec-memtype=0
drop-frame-interval=0
[sink0]
enable=1
type=2
sync=0
gpu-id=1
nvbuf-memory-type=0
[sink1]
enable=1
type=6
msg-conv-config=dstest5_msgconv_sample_config.txt
msg-conv-payload-type=1
msg-broker-proto-lib=/opt/nvidia/deepstream/deepstream-6.1/lib/libnvds_kafka_proto.so
msg-broker-conn-str=10.129.53.100;9092;video
topic=video2
iframeinterval=10
source-id=0
[sink2]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
#encoder type 0=Hardware 1=Software
enc-type=0
sync=0
bitrate=4000000
#H264 Profile - 0=Baseline 2=Main 4=High
#H265 Profile - 0=Main 1=Main10
profile=0
set below properties in case of RTSPStreaming
rtsp-port=8554
udp-port=5400
[osd]
enable=1
gpu-id=1
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0
[streammux]
gpu-id=1
live-source=0
batch-size=4
batched-push-timeout=40000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0
[primary-gie]
enable=1
gpu-id=1
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_gang.txt
batch-size=4
[tests]
file-loop=0
Did it mean bbox shown on all the video output for local file? but after change to multi rtsp sources, only one video output have bbox shown?
Yes, but when I changed from 4 RTSP video sources to 16 RTSP video sources (i.e. the number of video sources changed from 4 to 16), it became possible to identify two video sources at the same time. I don’t know what the problem is！
Yes, but when I changed from 4 RTSP video sources to 16 RTSP video sources (i.e. the number of video sources changed from 4 to 16), it became possible to identify two video sources at the same time. I don’t know what the problem is
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
Please try below to isolate the issue:
1 Please change live-source from 0 to 1 and try again.
2 Please change the model to builtin model to see if the issue exist with the same rtsp stream you used.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.