TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi
TensorFlow-Lite-Object-Detection-on-Android-and-Raspberry-Pi copied to clipboard
I have a webcam running on the Pi - Is there a way to use that stream as the source for TF
I was wondering if you could direct me to using your tutorial with an existing video stream. I have a webcam running on the Pi - Is there a way to use that stream as the source for TF? Meaning its running a live stream already and is unavailable...
Thanks for your time!
i get the following error providing a stream and a model to the stream.py file:
Traceback (most recent call last):
File "TFLite_detection_stream.py", line 174, in
but if i go to the stream url - it resolves fine.
thanks
i get the following error providing a stream and a model to the stream.py file:
Traceback (most recent call last): File "TFLite_detection_stream.py", line 174, in frame = frame1.copy() AttributeError: 'NoneType' object has no attribute 'copy'
but if i go to the stream url - it resolves fine.
thanks
How did you manage to get a stream running??? I am struggling. It is saying no port found in URI. What did you do to get it working. What port and ipaddress did you use? Please help me.
Modifying the webcam.py script at line 32 could work: Change
self.stream = cv2.VideoCapture()
into
self.stream = cv2.VideoCapture("/dev/video0")
or
self.stream = cv2.VideoCapture("v4l2:///dev/video0")
or something like that. Hope that helps!