# define the labels
labels = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus", "train", "truck",
        "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench",
        "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe",
        "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard",
        "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard",
        "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl",
        "banana","apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut",
        "cake","chair", "sofa", "pottedplant", "bed", "diningtable", "toilet", "tvmonitor", "laptop",
        "mouse","remote", "keyboard", "cell phone", "microwave", "oven", "toaster", "sink",
        "refrigerator","book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"]

# get the details of the detected objects
v_boxes, v_labels, v_scores = get_boxes(boxes, labels, class_threshold)

# summarize what we found
for i in range(len(v_boxes)):
    print(v_labels[i], v_scores[i])

person 99.3196427822113
person 98.71615767478943
person 96.0106909275055