How to use csi camera in deepstream yolov3-tiny?

Thanks in advanced. I update source1_csi_dec_infer_resnet_int8.txt ‘model-engine-file=…/…/models/Primary_Detector/resnet10.caffemodel_b1_fp16.engine’ and run:

nvidia@nvidia-desktop:/opt/nvidia/deepstream/deepstream-4.0/sources/objectDetector_Yolo$ deepstream-app -c ../../samples/configs/deepstream-app/source1_csi_dec_infer_resnet_int8.txt 
Creating LL OSD context new

Runtime commands:
	h: Print this help
	q: Quit

	p: Pause
	r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
      To go back to the tiled display, right-click anywhere on the window.

** INFO: <bus_callback:163>: Pipeline ready

** INFO: <bus_callback:149>: Pipeline running

Creating LL OSD context new
GST_ARGUS: Creating output stream
CONSUMER: Waiting until producer is connected...
GST_ARGUS: Available Sensor modes :
GST_ARGUS: 3264 x 2464 FR = 21.000000 fps Duration = 47619048 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;

GST_ARGUS: 3264 x 1848 FR = 28.000001 fps Duration = 35714284 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;

GST_ARGUS: 1920 x 1080 FR = 29.999999 fps Duration = 33333334 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;

GST_ARGUS: 1280 x 720 FR = 59.999999 fps Duration = 16666667 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;

GST_ARGUS: 1280 x 720 FR = 120.000005 fps Duration = 8333333 ; Analog Gain range min 1.000000, max 10.625000; Exposure Range min 13000, max 683709000;

GST_ARGUS: Running with following settings:
   Camera index = 0 
   Camera mode  = 4 
   Output Stream W = 1280 H = 720 
   seconds to Run    = 0 
   Frame Rate = 120.000005 
GST_ARGUS: PowerService: requested_clock_Hz=627200000
GST_ARGUS: Setup Complete, Starting captures for 0 seconds
GST_ARGUS: Starting repeat capture requests.
CONSUMER: Producer has connected; continuing.

**PERF: FPS 0 (Avg)	
**PERF: 0.00 (0.00)	
**PERF: 29.29 (29.29)	
**PERF: 29.07 (29.18)	
**PERF: 29.06 (29.14)	
q
Quitting
GST_ARGUS: Cleaning up
CONSUMER: Done Success
GST_ARGUS: Done Success
App run successful
GST_ARGUS: 
PowerServiceHwVic::cleanupResources
......

I can’t see camera video window, would anyone tell me how to solve it? I’m trying to find where is imshow.

Hi,

The default output of source1_csi_dec_infer_resnet_int8.txt is FakeSink.
Please update the parameter based on your requirement:

https://docs.nvidia.com/metropolis/deepstream/4.0/dev-guide/index.html#page/DeepStream_Development_Guide%2Fdeepstream_app_config.3.2.html%23wwpID0ENHA

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

Thanks.

Thank you. I update and test on nano, the fps is about 29. But I meet a new problem: how can I fix camera’s distortion in deepstream framework yolov3? I know I should do something about variable ‘caps’ in deepstream-4.0/sources/apps/apps-common/src/deepstream_sink_bin.c, but I don’t know how to update in c file, I don’t know such APIs. In previous version yolov3 in deepstream_reference_apps, it’s c++ file, opencv is supported, so it’s easy to implement distortion fix. I have camera’s Homography matrix, would nvidia develop a mechanism that just put Homography matrix in config file, for example, source1_csi_dec_infer_resnet_int8.txt, to fix camera’s distortion?