Model prediction

1. CLI usage

CLI currently only supports calling USB cameras. CSI camera users can directly modify the previous python code to call onnx and ncnn models!

xxxxxxxxxx
cd ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights
yolo predict model=best.onnx source=0 save=False show # For multiple cameras, follow the number after the ring source
yolo predict model='best_ncnn_model' source=0 save=False show

2. Use Python

Use Python to call USB camera and CSI camera to identify oranges.

2.1, USB camera

Use best.engine to predict the camera screen:

xxxxxxxxxx
cd /home/pi/ultralytics/ultralytics/yahboom_demo

Run the code: Click the preview screen, press the q key to terminate the program!

xxxxxxxxxx
python3 06.orange_camera_usb.py

Effect preview

Yolo recognizes the output video location: /home/pi/ultralytics/ultralytics/output/

Sample code:

xxxxxxxxxx
import cv2
from ultralytics import YOLO
​
# Load the YOLO model
# model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.pt")
# model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.onnx")
model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best_ncnn_model")
​
# Open the cammera
cap = cv2.VideoCapture(0)
​
# Get the video frame size and frame rate
frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = int(cap.get(cv2.CAP_PROP_FPS))
​
# Define the codec and create a VideoWriter object to output the processed video
output_path = "/home/pi/ultralytics/ultralytics/output/06.orange_camera_usb.mp4"
fourcc = cv2.VideoWriter_fourcc(*'mp4v')  # You can use 'XVID' or 'mp4v' depending on your platform
out = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))
​
# Loop through the video frames
while cap.isOpened():
    # Read a frame from the video
    success, frame = cap.read()
​
    if success:
        # Run YOLO inference on the frame
        results = model(frame)
​
        # Visualize the results on the frame
        annotated_frame = results[0].plot()
​
        # Write the annotated frame to the output video file
        out.write(annotated_frame)
​
​
        # Display the annotated frame
        cv2.imshow("YOLO Inference", cv2.resize(annotated_frame, (640, 480)))
​
        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break
# Release the video capture and writer objects, and close the display window
cap.release()
out.release()
cv2.destroyAllWindows()

2.2, CSI camera

Use best.engine to predict the camera screen:

xxxxxxxxxx
cd /home/pi/ultralytics/ultralytics/yahboom_demo

Run the code: Click the preview screen, press the q key to terminate the program!

xxxxxxxxxx
python3 06.orange_camera_csi.py

Effect preview

Yolo recognizes the output video location: /home/pi/ultralytics/ultralytics/output/

Sample code:

xxxxxxxxxx
import cv2
from picamera2 import Picamera2
​
from ultralytics import YOLO
​
# Initialize the Picamera2
picam2 = Picamera2()
picam2.preview_configuration.main.size = (640, 480)
picam2.preview_configuration.main.format = "RGB888"
picam2.preview_configuration.align()
picam2.configure("preview")
picam2.start()
​
# Load the YOLO11 model
# model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.pt")
# model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.onnx")
model = YOLO("/home/pi/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best_ncnn_model")
​
# Set up video output
output_path = "/home/pi/ultralytics/ultralytics/output/06.orange_camera_csi.mp4"
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
out = cv2.VideoWriter(output_path, fourcc, 30, (640, 480))
​
# Loop through the video frames
while True:
    # Capture frame-by-frame
    frame = picam2.capture_array()
​
    # Run YOLO11 inference on the frame
    results = model(frame)
​
    # Visualize the results on the frame
    annotated_frame = results[0].plot()
​
    # Write the frame to the video file
    out.write(annotated_frame)
​
    # Display the resulting frame
    cv2.imshow("Camera", annotated_frame)
​
    # Break the loop if 'q' is pressed
    if cv2.waitKey(1) == ord("q"):
        break
​
# Release resources and close windows
picam2.close()
out.release()
cv2.destroyAllWindows()