Why am I getting this error during object recognition?

TensorFlow General Discussion
1

Hi,

I’m putting together a cat doorbell. The idea is to listen for a meow, then look for a cat. If both are true, then send an alert.
The code is here

But sometimes I get this error when starting the object recognition portion of my code:

Sep 27 20:42:17 new-cat-doorbell python3[96266]: INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Sep 27 20:42:21 new-cat-doorbell python3[96266]: INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Sep 27 20:42:22 new-cat-doorbell python3[96266]: No protocol specified
Sep 27 20:42:22 new-cat-doorbell python3[96266]: qt.qpa.xcb: could not connect to display :0
Sep 27 20:42:22 new-cat-doorbell python3[96266]: qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/usr/local/lib/python3.9/dist-packages/cv2/qt/plugins" even though it was found.
Sep 27 20:42:22 new-cat-doorbell python3[96266]: This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.
Sep 27 20:42:22 new-cat-doorbell python3[96266]: Available platform plugins are: xcb.

This confuses me because I can’t tell if its a display problem of a plugin issue. Anyone have any ideas?

TIA,
-T

3

Hi @gamename
Did you try running your app setting QT_DEBUG_PLUGINS environment variable set to 1? Didn’t you get insightful information then?

4

Hi!

Thanks for the reply. I figured out the problem. I need to run the app as a user and not root.

Thanks again,
-T

1 Like
5

I am also facing same error.