How to make (predict draw bounding box) function for face recognition in real time?

i’m working on facenet-pytorch library now i want to take faces using webcam after detected using mtcnn then recognize it depend on the model which trained with evaluation mode?

thanks for responding any idea i will appreciate , this is a apart of the code

cap = cv.VideoCapture(0) 
while True:
    ret, frame =
    frame = cv.resize(frame, None, fx=0.5, fy=0.5, interpolation=cv2.INTER_AREA)     
image = predict_draw_bounding_box(frame)
    cv.imshow('Output', image)
    c = cv.waitKey(1) if c == 27: break