i use nvidia jetson nano with rpi camera to run yolov3, i’m 100% sure that the camera is compatible and working perfectly.
when i try to run live detection demo using this command
./darknet detector demo data/yolo.data cfg/yolov3_custom_train.cfg yolov3_custom_train_3000.weights -c 0
i get
[ WARN:0] global /home/jn/opencv_build/opencv/modules/videoio/src/cap_gstreamer.cpp (1759) handleMessage OpenCV | GStreamer warning: Embedded video playback halted; module v4l2src0 reported: Internal data stream error.
[ WARN:0] global /home/jn/opencv_build/opencv/modules/videoio/src/cap_gstreamer.cpp (888) open OpenCV | GStreamer warning: unable to start pipeline
[ WARN:0] global /home/jn/opencv_build/opencv/modules/videoio/src/cap_gstreamer.cpp (480) isPipelinePlaying OpenCV | GStreamer warning: GStreamer: pipeline have not been created
then the demo window pops up and i get a constant green screen
It looks like you are meeting the same error of topic 112954:
However, the user fixes it by using the NV12 as nvarguscamerasrc output format, which is what I share with you.
To narrow down the issue, could you run this command to see if the camera works without OpenCV first?
I just tried to run command
"./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights ‘nvarguscamerasrc ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720,format=(string)NV12, framerate=(fraction)30/1 ! nvvidconv flip-method=2 ! video/x-raw, format=(string)BGRx ! videoconvert ! video/x-raw, format=(string)BGR ! appsink’
It can work