How to Build a Real-Time Video Classifier on NVIDIA Jetson Nano with Python

### Import OpenCV for video I/O, frame processing, and on-screen drawing.
import cv2
### Import Jetson Inference high-level APIs for classification models.
import jetson.inference
### Import Jetson Utils for CUDA memory interop with NumPy images.
import jetson.utils

### Load the video file using OpenCV’s VideoCapture. Replace the path with your local video if needed.
cap = cv2.VideoCapture('/home/feitdemo/github/Jetson-Nano-Python/Wildlife.mp4')
### Set capture width to 1280 pixels for a 720p workflow with good real-time performance on Jetson Nano.
cap.set(3,1280)
### Set capture height to 720 pixels to match the desired display resolution.
cap.set(4,720)

### Load a pretrained image classification network. "googlenet" maps to an ImageNet-trained model on Jetson.
net = jetson.inference.imageNet("googlenet")

### Keep processing frames while the capture is open.
while cap.isOpened():
    ### Read the next frame from the video. 're' is the success flag and 'img' is the frame array.
    re, img = cap.read()

    ### Convert the BGR frame from OpenCV to RGBA, which is expected before moving into CUDA memory.
    frame_rgba = cv2.cvtColor(img,cv2.COLOR_BGR2RGBA)
    ### Move the NumPy frame into GPU memory so Jetson Inference can run classification on the device.
    cuda_frame = jetson.utils.cudaFromNumpy(frame_rgba)

    ### Run classification on the current frame. Returns the predicted class ID and a confidence score.
    class_id , confidence = net.Classify(cuda_frame)

    ### Retrieve the human-readable class description for the predicted class ID.
    class_desc = net.GetClassDesc(class_id)

    ### If the prediction confidence is above 0.40, overlay the label text on the frame for the viewer.
    if confidence > 0.4 : 
        cv2.putText(img, class_desc, (30,80), cv2.FONT_HERSHEY_COMPLEX, 1, (255,0,0),3 )

    ### Show the annotated frame in a window titled 'img'.
    cv2.imshow('img',img)
    ### Position the window at the top-left corner of the screen for convenience.
    cv2.moveWindow('img',0,0)

    ### Check for a 'q' key press to allow the user to quit the loop gracefully.
    if cv2.waitKey(10) & 0xFF == ord('q'):
        break

### Release the video capture to free camera or file resources.
cap.release()
### Destroy OpenCV windows to clean up GUI resources before exit.
cv2.destroyAllWindows()

### Import OpenCV for video I/O, frame processing, and on-screen drawing. import cv2 ### Import Jetson Inference high-level APIs for classification models. import jetson.inference ### Import Jetson Utils for CUDA memory interop with NumPy images. import jetson.utils  ### Load the video file using OpenCV’s VideoCapture. Replace the path with your local video if needed. cap = cv2.VideoCapture('/home/feitdemo/github/Jetson-Nano-Python/Wildlife.mp4') ### Set capture width to 1280 pixels for a 720p workflow with good real-time performance on Jetson Nano. cap.set(3,1280) ### Set capture height to 720 pixels to match the desired display resolution. cap.set(4,720)  ### Load a pretrained image classification network. "googlenet" maps to an ImageNet-trained model on Jetson. net = jetson.inference.imageNet("googlenet")  ### Keep processing frames while the capture is open. while cap.isOpened():     ### Read the next frame from the video. 're' is the success flag and 'img' is the frame array.     re, img = cap.read()      ### Convert the BGR frame from OpenCV to RGBA, which is expected before moving into CUDA memory.     frame_rgba = cv2.cvtColor(img,cv2.COLOR_BGR2RGBA)     ### Move the NumPy frame into GPU memory so Jetson Inference can run classification on the device.     cuda_frame = jetson.utils.cudaFromNumpy(frame_rgba)      ### Run classification on the current frame. Returns the predicted class ID and a confidence score.     class_id , confidence = net.Classify(cuda_frame)      ### Retrieve the human-readable class description for the predicted class ID.     class_desc = net.GetClassDesc(class_id)      ### If the prediction confidence is above 0.40, overlay the label text on the frame for the viewer.     if confidence > 0.4 :          cv2.putText(img, class_desc, (30,80), cv2.FONT_HERSHEY_COMPLEX, 1, (255,0,0),3 )      ### Show the annotated frame in a window titled 'img'.     cv2.imshow('img',img)     ### Position the window at the top-left corner of the screen for convenience.     cv2.moveWindow('img',0,0)      ### Check for a 'q' key press to allow the user to quit the loop gracefully.     if cv2.waitKey(10) & 0xFF == ord('q'):         break  ### Release the video capture to free camera or file resources. cap.release() ### Destroy OpenCV windows to clean up GUI resources before exit. cv2.destroyAllWindows()