Model Prediction

1. Maximum Performance Mode

1.1. Enable MAX Mode

Enabling MAX Power Mode on Jetson will ensure that all CPU and GPU cores are turned on:

#Orin Nano
sudo nvpmodel -m 2
#Orin Nx
sudo nvpmodel -m 0

1.2. Enable Jetson Clocks

Enabling Jetson Clocks will ensure that all CPU and GPU cores run at maximum frequency:

xxxxxxxxxx
sudo jetson_clocks

2. Model Prediction

2.1. CLI Usage

CLI currently only supports USB cameras. For CSI cameras, users can directly modify the previous Python code to call ONNX and ENGINE models!

xxxxxxxxxx
yolo predict model=best.engine source=0 save=False show # For multiple cameras, change the number after source

2.2. Python Usage

Use Python to call USB and CSI cameras for orange recognition.

2.2.1. USB Camera

Use best.engine to predict camera feed:

xxxxxxxxxx
cd /home/jetson/ultralytics/ultralytics/yahboom_demo

Run the code: Click on the preview window and press 'q' key to terminate the program!

xxxxxxxxxx
python3 06.orange_camera_usb.py

Effect Preview

yolo recognition output video location: /home/jetson/ultralytics/ultralytics/output/

Example code:

​x
import cv2
from ultralytics import YOLO
​
# Load the YOLO model
# model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.pt")
# model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.onnx")
model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.engine")
​
# Open the camera
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/jetson/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()

2.2.2. CSI Camera

Use best.engine to predict camera feed:

xxxxxxxxxx
cd /home/jetson/ultralytics/ultralytics/yahboom_demo

Run the code: Click on the preview window and press 'q' key to terminate the program!

xxxxxxxxxx
python3 06.orange_camera_csi.py

Effect Preview

yolo recognition output video location: /home/jetson/ultralytics/ultralytics/output/

Example code:

xxxxxxxxxx
import cv2
from ultralytics import YOLO
from jetcam.csi_camera import CSICamera
​
# Load the YOLO model
# model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.pt")
# model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.onnx")
model = YOLO("/home/jetson/ultralytics/ultralytics/data/yahboom_data/orange_data/runs/detect/train/weights/best.engine")
​
# Open the camera (CSI Camera)
cap = CSICamera(width=640, height=480)
​
# Get the video frame size and frame rate
frame_width = 640
frame_height = 480
fps = 30
​
# Define the codec and create a VideoWriter object to output the processed video
output_path = "/home/jetson/ultralytics/ultralytics/output/06.orange_camera_csi.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 True:
    # Read a frame from the camera
    frame = cap.read()
​
    if frame is not None:
        # 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 no frame is received (camera error or end of stream)
        print("No frame received, breaking the loop.")
        break
​
# Release the video capture and writer objects, and close the display window
cap.release()
out.release()
cv2.destroyAllWindows()