How to output results from a camera using python

[Jason1-2]

I am very new to python and ultralytics, but so far I trained my raspberry pi camera to detect bottles, cups, and cans for segmentation. I'm using YOLOv8 and Thonny for python, so far my code only has three lines and it's able to identify objects perfectly.
Here are my lines of code:

from ultralytics import YOLO
model=YOLO('best.pt')
model.predict(source=0,show=True)

My camera can successfully detect objects on a live camera. I can see frames are getting printed on the bottom of the code saying
0: 480x640 1 Bottle, 2330.8ms
"0:" is the name of the camera, "480x640" is the size, "1 Bottle" is what is getting identified, and "2330.8ms" is the time the frame was shown.

I got help and was told that I can output results and handle them however I want. An example I was given was:

results = model(image)

In conclusion, my question is if the "results" would be considered the feedback of what the camera is detecting? Which it would be detecting "bottle", "Can" or "Cup". Or would that be "image" in that code.
If anyone has examples or videos for me to follow I would appreciate it if you shared them to me.
Thank you!!!

[glenn-jocher]

@Jason1-2 Yes, the "results" variable in the code snippet results = model(image) would contain the output of the YOLOv8 model's prediction on the input image. The output would be in the form of a tensor or list containing information about the detected objects, such as their class labels, confidence scores, and bounding box coordinates.

You can use this output to further process the detections and display them in a way that suits your needs. For example, you could filter out low-confidence detections, draw bounding boxes around the detected objects, and display the class labels next to the boxes.

[Jason1-2]

Would I need to create my own code for "results"? I see on YOLOv8 Docs for Results there are Source Codes
https://docs.ultralytics.com/reference/results/?h=results

Or would be as easy as typing in results=model(bottle)

I just need to send a 3.3 volt signal from my raspberry pi. I already have code to send out a signal, but I need to activate that signal when the object gets detected.

Also, thank you for responding!!!

[glenn-jocher]

Results are returned automatically and you can handle them however you'd like. You can use the docs for guidance at https://docs.ultralytics.com/reference/results as you mentioned :)