Search before asking

• I have searched the YOLOv8 issues and discussions and found no similar questions.

Question

Hi,

I tried to run yolo8 in GPU but it's not working.
I use torch to set the device to cuda but still not working on my GPU. The model I am using is PPE detection yolo8. I want to achieve fast reading and detection from the camera using rtsp and then sending the detection frame to rtmp server.

`
import cv2
from ultralytics import YOLO
import subprocess
import requests
import json
import random
import base64
from PIL import Image
import threading

import torch

torch.cuda.set_device(0)

Camera Stream

path = "rtsp://admin:deer2022@192.168.1.149:554/Streaming/Channels/101/"
cap = cv2.VideoCapture(path)

Load the YOLOv8 model

model = YOLO('best.pt')
classes= {0: 'Hardhat', 1: 'Mask', 2: 'NO-Hardhat', 3: 'NO-Mask', 4: 'NO-Safety Vest', 5: 'Person', 6: 'Safety Cone', 7: 'Safety Vest', 8: 'machinery', 9: 'vehicle'}

Loop through the video frames

while cap.isOpened():
# Read a frame from the video
success, frame = cap.read()

if success:
    # Run YOLOv8 inference on the frame
    results = model(frame)
    annotated_frame = results[0].plot()
    # Saving the image
    cv2.imwrite("test1.jpeg", annotated_frame)
    # Encode the resized annotated frame to base64


    # Display the annotated frame
    cv2.imshow("YOLOv8 Inference", annotated_frame)

    # 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

def show_frame(frame):
cv2.imshow("YOLOv8 Inference", frame)

Release the video capture object and close the display window

cap.release()
cv2.destroyAllWindows()`

Additional

No response