main.py

import cv2

thres = 0.5 #threshold to detect objects, anything less than this value will not be detected

cap = cv2.VideoCapture(0) #value can change dependending on the video device you use
cap.set(3, 640)
cap.set(4, 480)

classNames = []
classFile = 'coco.names'

with open(classFile, 'rt') as f:
    classNames = f.read().rstrip('\n').split('\n')

configPath = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = 'frozen_inference_graph.pb'

net = cv2.dnn_DetectionModel(weightsPath,configPath)
# configurations found on the official documentation
net.setInputSize(320, 320)
net.setInputScale(1.0/ 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)

while True:
    success, img = cap.read()
    classIds, confs, bbox = net.detect(img, confThreshold=thres)
    print(classIds, bbox)

    if len(classIds)!=0:
        for classId, confidence, box in zip(classIds.flatten(), confs.flatten(), bbox): #reduces the need for 3 separate for loops
            cv2.rectangle(img, box, color=(0,255,0), thickness=3)
            cv2.putText(img, classNames[classId-1], (box[0]+10, box[1]+30), cv2.FONT_HERSHEY_COMPLEX, 1, (0,255,0), 2)
            cv2.putText(img, str(round(confidence*100,2)), (box[0]+200, box[1]+30), cv2.FONT_HERSHEY_COMPLEX, 1, (0,255,0), 2)

    cv2.imshow("Output", img)
    cv2.waitKey(1)