Untitled

import numpy as np
import cv2

min_confidence = 0.6
classes = ['background', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow',
           'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']
net = cv2.dnn.readNetFromCaffe(
    "models/MobileNetSSD_deploy.prototxt.txt", "models/MobileNetSSD_deploy.caffemodel"
)
colors = np.random.uniform(0, 255, size=(len(classes), 3))
cap = cv2.VideoCapture(0)


while True:
    ret, frame = cap.read()
    height, width = frame.shape[0], frame.shape[1]

    blob = cv2.dnn.blobFromImage(cv2.resize(
        frame, (300, 300)), 0.007843, (300, 300), 127.5)
    net.setInput(blob)
    detections = net.forward()
    for i in range(0, detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        if confidence > min_confidence:
            class_id = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * \
                np.array([width, height, width, height])
            (startX, startY, endX, endY) = box.astype('int')
            text = "{:.2f}%".format(confidence * 100) + \
                f"- {classes[class_id]}"
            y = startY - 10 if startY - 10 > 10 else startY+10
            print(startX, startY, endX, endY)
            cv2.rectangle(frame, (startX, startY),
                          (endX, endY),  colors[class_id], 2)
            cv2.putText(frame, text, (startX, y),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.45, colors[class_id], 2)
            print(classes[class_id])
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF
    if key == ord("q"):
        break
cap.release()
cv2.destroyAllWindows()