How can I measure the test results after training, like calculate each class precision and recall?

I trained the model on my own dataset, then I modified the object_detection_test.ipynb to my_test_tutorial.py for my test images. But I found this code just for draw predict bounding box, how I change it to draw ground truth box and calculate the precison and recall of every class?

`# Imports
import time

start = time.time()
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import cv2

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

os.chdir('D:\models-master\models\research\object_detection')

sys.path.append("..")

from utils import label_map_util

from utils import visualization_utils as vis_util

MODEL_NAME = 'D:\models-master\models\research\object_detection\myoutput'

PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

PATH_TO_LABELS = os.path.join('D:\models-master\models\research\object_detection\mydata', 'mylabelmap.pbtxt')

NUM_CLASSES = 5

detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
use_display_name=True)
category_index = label_map_util.create_category_index(categories)

def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint16)

PATH_TO_TEST_IMAGES_DIR = 'D:\models-master\models\research\object_detection\myimages\test_images'
os.chdir(PATH_TO_TEST_IMAGES_DIR)
TEST_IMAGE_PATHS = os.listdir(PATH_TO_TEST_IMAGES_DIR)

IMAGE_SIZE = (12, 8)

output_path = ('D:\models-master\models\research\object_detection\mytestout\')

with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:

    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
   
    detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
    
    
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')
    for image_path in TEST_IMAGE_PATHS:
        
        image = Image.open(PATH_TO_TEST_IMAGES_DIR + '\\' + image_path)
        
        image_np = load_image_into_numpy_array(image)

        image_np_expanded = np.expand_dims(image_np, axis=0)

        (boxes, scores, classes, num) = sess.run(
            [detection_boxes, detection_scores, detection_classes, num_detections],
            feed_dict={image_tensor: image_np_expanded})

        vis_util.visualize_boxes_and_labels_on_image_array(
            image_np,
            np.squeeze(boxes),
            np.squeeze(classes).astype(np.int32),
            np.squeeze(scores),
            category_index,
            use_normalized_coordinates=True,
            line_thickness=8)

        cv2.imwrite(output_path + image_path.split('\\')[-1], image_np)

end = time.time()
print("Execution Time: ", end - start)`