Making an object detection model in OpenCv python with tensorflow classification model (frozen graph)

Question

I am a beginner in computer vision and machine learning. I want to make an object detection program in OpenCv python with a TensorFlow classification model. This model is generated from teachable machine and exported as saved model. It has only the frozen graph and classnames text files of the model. I am not getting how I should do that

I have tried it with this:

pb = '/frozen - graph.pb'
net = cv2.dnn.readNetFromTensorflow(pb)
model = cv2.dnn_DetectionModel(net)
model.setInputParams(size = (n,n),  scale=1/127.5)
(cl_ids, scores, bboxes) = model.detect(frame)

but didn't get the output.