yolo

import numpy as np
import cv2 as cv
from ultralytics import YOLO

cap = cv.VideoCapture("/mnt/c/Users/Bemposta/Videos/madrid.mp4")
if not cap.isOpened():
    print("Cannot open camera")
    exit()

model = YOLO("yolo26s.pt")  # pretrained YOLO26n model

while True:
    # Capture frame-by-frame
    ret, frame = cap.read()

    # if frame is read correctly ret is True
    if not ret:
        print("Can't receive frame (stream end?). Exiting ...")
        break

    # Our operations on the frame come here
    #imgrgb = cv.cvtColor(frame, cv.COLOR_BGR2RGB)

    # Run batched inference on a list of images
    results = model.predict(source=frame, iou=0.5, verbose=False, imgsz=[736, 1280])  # return a list of Results objects
    #print(model.names)
    #model.info()  # Prints model summary and returns tuple
    #model.info(detailed=True)  # Prints detailed info and returns tuple
    img_result = results[0].plot(
        line_width=1,       # Grosor de las cajas
        font_size=10,       # Tamaño del texto
        labels=True,        # Mostrar etiquetas
        conf=True,          # Mostrar confianza
        boxes=True,         # Dibujar cajas
    )
    print("results[0].to_json():\n", results[0].to_json(normalize=True, decimals=5))
    # Display the resulting frame
    #img_result = cv.cvtColor(img_result, cv.COLOR_RGB2BGR)
    cv.imshow('frame', img_result)
    if cv.waitKey(10) == ord('q'):
       break

# When everything done, release the capture
cap.release()
cv.destroyAllWindows()