The camera stops working after pointing it to the object

hi, i have a custom object detection model and i want to use it with a python script so that i can connect it with the GPIO later.
the problem is whenever i point the camera to the object i want it to detect it stops working and close without any error. note that
1- the camera is working and i can capture anything as long as that specific object is outside the frame.
2- and the same code will work fine when i use the pre-trained models like ssd-mobilenet-v2 or googlenet

i’ve tried multiple scripts from the tutorials like

import jetson.inference
import jetson.utils

net=jetson.inference.detectNet('SSD-mobilenet-v2',['--model=jetson-inference/python/training/detection/ssd/models/gg/ssd-mobilenet.onnx', '--input-blob=input_0', '--output-cvg=scores', '--output-bbox=boxes', '--label=jetson-inference/python/training/detection/ssd/models/gg/labels.txt'], threshold=0.5)

camera = jetson.utils.videoSource("csi://0")      
display = jetson.utils.videoOutput("display://0") 
while True:
	img = camera.Capture()
	detections = net.Detect(img)
	display.SetStatus("Object Detection | Network {:.0f} FPS".format(net.GetNetworkFPS()))


import jetson.inference
import jetson.utils
import argparse
import sys

# parse the command line
parser = argparse.ArgumentParser(description="Locate objects in a live camera stream using an object detection DNN.", 
                                 formatter_class=argparse.RawTextHelpFormatter, epilog=jetson.inference.detectNet.Usage() +
                                 jetson.utils.videoSource.Usage() + jetson.utils.videoOutput.Usage() + jetson.utils.logUsage())

parser.add_argument("input_URI", type=str, default="", nargs='?', help="URI of the input stream")
parser.add_argument("output_URI", type=str, default="", nargs='?', help="URI of the output stream")
parser.add_argument("--network", type=str, default="ssd-mobilenet-v2", help="pre-trained model to load (see below for options)")
parser.add_argument("--overlay", type=str, default="box,labels,conf", help="detection overlay flags (e.g. --overlay=box,labels,conf)\nvalid combinations are:  'box', 'labels', 'conf', 'none'")
parser.add_argument("--threshold", type=float, default=0.5, help="minimum detection threshold to use") 

is_headless = ["--headless"] if sys.argv[0].find('') != -1 else [""]

	opt = parser.parse_known_args()[0]

# load the object detection network
#net = jetson.inference.detectNet(, sys.argv, opt.threshold)
net=jetson.inference.detectNet(argv=['--model=jetson-inference/python/training/detection/ssd/models/gg/ssd-mobilenet.onnx', '--label=jetson-inference/python/training/detection/ssd/models/gg/labels.txt', '--input-blob=input_0', '--output-cvg=scores', '--output-bbox=boxes'], threshold=0.5)

# create video sources & outputs
input = jetson.utils.videoSource(opt.input_URI, argv=sys.argv)
output = jetson.utils.videoOutput(opt.output_URI, argv=sys.argv+is_headless)

# process frames until the user exits
while True:
	# capture the next image
	img = input.Capture()

	# detect objects in the image (with overlay)
	detections = net.Detect(img, overlay=opt.overlay)

	# print the detections
	print("detected {:d} objects in image".format(len(detections)))

	for detection in detections:

	# render the image

	# update the title bar
	output.SetStatus("{:s} | Network {:.0f} FPS".format(, net.GetNetworkFPS()))

	# print out performance info

	# exit on input/output EOS
	if not input.IsStreaming() or not output.IsStreaming():


Usually, post-processing will be triggered once an object is detected.
Would you mind checking if there is an issue with the post-processing? (ex. invalid access)


would you mine tell me how can i check it. thank you


You can try to run the script with gdb and get the backtrace first.

For example:

$ gdb --args python3 arg1 arg2 ...
(gdb) run
(gdb) bt


well sadly i just came back from uni and attempted to run the jetson and its stuck nvidia logo now :) .
i tried to disconnect it from everything and rerun but didnt work, soo idk


Sorry for the late update.

Have you filed a new topic for the freeze issue?
If not, would you mind doing this?


1 Like