Welcome to Jetson Orin NANO Developer Kit repository
11.Model prediction
Model Prediction
Model Prediction1. Best Performance Mode1.1. Enabling MAX Mode1.2. Enabling Jetson Clocks2. Model Prediction2.1. Using the CLI2.2. Using Python2.2.1. USB CameraResult Preview2.2.1. CSI CameraResult Preview
1. Best Performance Mode
1.1. Enabling MAX Mode
Enabling MAX Power Mode on the Jetson ensures that all CPU and GPU cores are turned on:
xxxxxxxxxxsudo nvpmodel -m 2
1.2. Enabling Jetson Clocks
Enabling Jetson Clocks ensures that all CPU and GPU cores run at their maximum frequency:
xxxxxxxxxxsudo jetson_clocks
2. Model Prediction
2.1. Using the CLI
The CLI currently only supports calling a USB camera; users of CSI cameras can directly modify the earlier Python code to call the onnx and engine models!
xxxxxxxxxxyolo predict model=best.engine source=0 save=False show # for multiple cameras, change the number after source

2.2. Using Python
Use Python to call a USB camera and a CSI camera to recognize oranges.
2.2.1. USB Camera
Use best.engine to predict the camera feed:
xxxxxxxxxxcd /home/jetson/ultralytics/ultralytics/yahboom_demo
Run the code: click the preview window and press the q key to terminate the program!
xxxxxxxxxxpython3 06.orange_camera_usb.py
Result Preview
The output videos recognized by yolo are located at: /home/jetson/ultralytics/ultralytics/output/

Example code:
xxxxxxxxxximport cv2from 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 cammeracap = cv2.VideoCapture(0)# Get the video frame size and frame rateframe_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 videooutput_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 platformout = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))# Loop through the video frameswhile cap.isOpened():# Read a frame from the videosuccess, frame = cap.read()if success:# Run YOLO inference on the frameresults = model(frame)# Visualize the results on the frameannotated_frame = results[0].plot()# Write the annotated frame to the output video fileout.write(annotated_frame)# Display the annotated framecv2.imshow("YOLO Inference", cv2.resize(annotated_frame, (640, 480)))# Break the loop if 'q' is pressedif cv2.waitKey(1) & 0xFF == ord("q"):breakelse:# Break the loop if the end of the video is reachedbreak# Release the video capture and writer objects, and close the display windowcap.release()out.release()cv2.destroyAllWindows()
2.2.1. CSI Camera
Use best.engine to predict the camera feed:
xxxxxxxxxxcd /home/jetson/ultralytics/ultralytics/yahboom_demo
Run the code: click the preview window and press the q key to terminate the program!
xxxxxxxxxxpython3 06.orange_camera_csi.py
Result Preview
The output videos recognized by yolo are located at: /home/jetson/ultralytics/ultralytics/output/

Example code:
ximport cv2from ultralytics import YOLOfrom 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(capture_device=0, width=640, height=480)# Get the video frame size and frame rateframe_width = 640frame_height = 480fps = 30# Define the codec and create a VideoWriter object to output the processed videooutput_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 platformout = cv2.VideoWriter(output_path, fourcc, fps, (frame_width, frame_height))# Loop through the video frameswhile True:# Read a frame from the cameraframe = cap.read()if frame is not None:# Run YOLO inference on the frameresults = model(frame)# Visualize the results on the frameannotated_frame = results[0].plot()# Write the annotated frame to the output video fileout.write(annotated_frame)# Display the annotated framecv2.imshow("YOLO Inference", cv2.resize(annotated_frame, (640, 480)))# Break the loop if 'q' is pressedif cv2.waitKey(1) & 0xFF == ord("q"):breakelse:# 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 windowcap.release()out.release()cv2.destroyAllWindows()