Deepstream for multi-rtsp stream (Solved)

when i use deepstream in jetson Tx2.
i set the multi-rtsp stream in conifguare

[application]
enable-perf-measurement=1
roi-marking=0
perf-measurement-interval-sec=5
gie-kitti-output-dir=/home/nvidia/kitti1

0 = standalone; 1 = server; 2 = client

app-mode=3

[source0]
#enable=1
Type - 1=CameraCSi 2=CameraV4L2 3=URI
#type=3
camera-width=1920
camera-height=1080
camera-fps-n=25
camera-fps-d=1
camera-csi-sensor-id=0
camera-v4l2-dev-node=0
uri=rtsp://admin:hik12345@192.168.0.102:554/

[source1]
enable=1
#Type - 1=CameraCSi 2=CameraV4L2 3=URI
type=3
camera-width=1920
camera-height=1080
camera-fps-n=25
camera-fps-d=1
camera-csi-sensor-id=0
camera-v4l2-dev-node=0
uri=rtsp://admin:hik12345@192.168.0.100:554/

[sink0]
enable=1
#Type - 1=FakeSink 2=OverlaySink 3=EglSink 4=XvImageSink 5=File
type=2
display-id=0
offset-x=0
offset-y=0
width=0
height=0
sync=0
overlay-index=1
source-id=0

[sink1]
enable=0
#Type - 1=FakeSink 2=OverlaySink 3=EglSink 4=XvImageSink 5=File
type=5
#1=mp4 2=mkv
container=2
#1=h264 2=h265
codec=1
bitrate=10000000
#1=cbr 2=vbr
rc-mode=2
iframeinterval=30
#1=baseline 2=main 3=high
profile=3
output-file=out.mp4
source-id=0

[osd]
enable=1
osd-mode=2
border-width=3
text-size=10
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Arial
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0;

#[face-detector]
#enable=1
#mode=0
#unique-id=15
#interval=2
#multi-stream=1

[primary-gie]
enable=1
net-scale-factor=0.0039215697906911373
model-file=file:///home/nvidia/Model/ResNet_18/ResNet_18_threeClass_VGA_pruned.caffemodel
proto-file=file:///home/nvidia/Model/ResNet_18/ResNet_18_threeClass_VGA_deploy_pruned.prototxt
model-cache=file:///home/nvidia/Model/ResNet_18/ResNet_18_threeClass_VGA_pruned.caffemodel_b2_fp16.cache
labelfile-path=file:///home/nvidia/Model/ResNet_18/labels.txt

net-stride=16
batch-size=2
#bbox-bg-color0=0;1;0;0.2
#bbox-bg-color1=0;1;1;0.2
#bbox-bg-color2=0;1;1;0.2
#bbox-bg-color3=1;0;0;0.2
bbox-border-color0=1;0;0;1
bbox-border-color1=0;1;1;1
bbox-border-color2=0;1;1;1
bbox-border-color3=0;1;0;1
num-classes=3
class-thresholds=0.2;0.2;0.2;0.2
class-eps=0.1;0.1;0.1;0.1
class-group-thresholds=3;3;3;3
color-format=0
roi-top-offset=0;0;0;0
roi-bottom-offset=0;0;0;0
detected-min-w=0;0;0;0
detected-min-h=0;0;0;0
detected-max-w=1920;100;1920;1920
detected-max-h=1080;1080;1080;1080
interval=1

-2 for all; -1 for none;

To set multiple class id’s use format as “1;2;0”

detect-color-class-ids=0;
gie-unique-id=1
parse-func=4
is-classifier=0
output-bbox-name=Layer11_bbox
output-blob-names=Layer11_cov

Uncomment below lines for DBSCAN. EPS and minBoxes can be tuned for DBSCAN

#enable-dbscan=1
#class-minBoxes=4;4;4;4
#class-eps=0.7;0.7;0.7;0.7

Bit 0: Model decryption required

crypto-flags=0

[secondary-gie4]
enable=1
net-scale-factor=1
model-file=file:///home/nvidia/Model/ivaSecondary_VehicleTypes_V1/snapshot_iter_13740.caffemodel
proto-file=file:///home/nvidia/Model/ivaSecondary_VehicleTypes_V1/deploy.prototxt
model-cache=file:///home/nvidia/Model/ivaSecondary_VehicleTypes_V1/snapshot_iter_13740.caffemodel_b2_fp16.cache
labelfile-path=file:///home/nvidia/Model/ivaSecondary_VehicleTypes_V1/labels.txt
net-stride=16
batch-size=2
num-classes=6
detected-min-w=128
detected-min-h=128
detected-max-w=1920;100;1920;1920
detected-max-h=1080;1080;1080;1080
color-format=1
interval=0
gie-unique-id=4
operate-on-gie-id=1
operate-on-class-ids=2;
is-classifier=1
output-blob-names=softmax
offsets=73.00;77.55;88.9
sgie-async-mode=1
sec-class-threshold=0.51

[secondary-gie5]
enable=1
net-scale-factor=1
model-file=file:///home/nvidia/Model/IVA_secondary_carcolor_V1/CarColorPruned.caffemodel
proto-file=file:///home/nvidia/Model/IVA_secondary_carcolor_V1/deploy.prototxt
mean-file=file:///home/nvidia/Model/IVA_secondary_carcolor_V1/mean.ppm
model-cache=file:///home/nvidia/Model/IVA_secondary_carcolor_V1/CarColorPruned.caffemodel_b2_fp16.cache
labelfile-path=file:///home/nvidia/Model/IVA_secondary_carcolor_V1/labels.txt
net-stride=16
batch-size=2
detected-min-w=128
detected-min-h=128
detected-max-w=1920;100;1920;1920
detected-max-h=1080;1080;1080;1080
color-format=1
num-classes=12
interval=0
gie-unique-id=5
operate-on-gie-id=1
operate-on-class-ids=2;
is-classifier=1
output-blob-names=softmax
sgie-async-mode=1
sec-class-threshold=0.51

[secondary-gie6]
enable=1
net-scale-factor=1
model-file=file:///home/nvidia/Model/IVASecondary_Make_V1/snapshot_iter_6240.caffemodel
proto-file=file:///home/nvidia/Model/IVASecondary_Make_V1/deploy.prototxt
model-cache=file:///home/nvidia/Model/IVASecondary_Make_V1/snapshot_iter_6240.caffemodel_b2_fp16.cache
mean-file=file:///home/nvidia/Model/IVASecondary_Make_V1/mean.ppm
labelfile-path=file:///home/nvidia/Model/IVASecondary_Make_V1/labels.txt
net-stride=16
batch-size=2
num-classes=24
detected-min-w=128
detected-min-h=128
detected-max-w=1920;100;1920;1920
detected-max-h=1080;1080;1080;1080
color-format=1
interval=0
gie-unique-id=6
operate-on-gie-id=1
operate-on-class-ids=2;
is-classifier=1
output-blob-names=softmax
sgie-async-mode=1
sec-class-threshold=0.51
crypto-flags=0

[tracker]
enable=1
tracker-width=960
tracker-height=540

[tests]
file-loop-count=0
#0=send overlaps; 1=do not send overlaps
server-overlap-mode=1
#Fixed to 1 for diplay color in GUI mode
color-mode=1

**PERF: FPS (Avg) FPS 0 (Avg) FPS 1 (Avg)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)
**PERF: nan (nan) nan (nan) nan (nan)

Hello,

May I know what issue you are facing?

Thanks
wayne zhu

Hello waynezhu,
I want to support multi-rtsp stream using deepstream. Can you give me a configure to me to test it ?

Hello bingxinhu,
I am sorry to tell you that our tegra version can’t support multimedia stream because some component can’t support batch operation.
It will be supported in next release.

Thanks
wayne zhu