tensorflow 訓練完模型的導出和測試模型

在我的另一篇博客中[tensorflow 物體檢測（檢測限速標誌）](https://blog.csdn.net/WK785456510/article/details/86149398)中已經訓練好了模型，接下來我們進行測試模型。

1. 導出模型文件
   訓練完以後，如何對單張圖片進行目標檢測呢？Object Detection API提供了一個export_inference_graph.py腳本用於導出訓練好的模型，我們先將訓練好的checkpoint導出成“,pb”文件，再用上一講的代碼，對圖片進行目標檢測。導出模型命令如下：python export_inference_graph.py --pipeline_config_path=object_detection/my_images/VOCdevkit/VOC2012/ssd_mobilenet_v1.config --trained_checkpoint_prefix=object_detection/my_images/train/model.ckpt-xxxxx --output_directory=object_detection/my_images/train,最後的文件名存在train中的frozen_inference_graph.pb 。
2. 批量測試代碼
   訓練過程中會輸出精確度，但是我們需要測試自己的圖像，查看驗證集和訓練集效果的時候就需要批量測試。在object_detection建立python文件。代碼如下:根據自己圖像數量和路徑進行必要的修改：

import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import matplotlib

# Matplotlib chooses Xwindows backend by default.
matplotlib.use('Agg')

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from utils import label_map_util
from utils import visualization_utils as vis_util

##################### Download Model
# What model to download.
MODEL_NAME = 'my_images'
#MODEL_FILE = MODEL_NAME + '.tar.gz'
#DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'

# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join(MODEL_NAME, 'pascal_label_map.pbtxt')

NUM_CLASSES = 1

# Download model if not already downloaded
if not os.path.exists(PATH_TO_CKPT):
    print('Downloading model... (This may take over 5 minutes)')
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    print('Extracting...')
    tar_file = tarfile.open(MODEL_FILE)
    for file in tar_file.getmembers():
        file_name = os.path.basename(file.name)
        if 'frozen_inference_graph.pb' in file_name:
            tar_file.extract(file, os.getcwd())
else:
    print('Model already downloaded.')

##################### Load a (frozen) Tensorflow model into memory.
print('Loading model...')
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='')

    ##################### Loading label map
print('Loading label map...')
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)


##################### Helper code
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.uint8)


##################### Detection
# Path to test image
for i in range(250):
    path='my_images/VOCdevkit/VOC2012/JPEGImages/'
    graph=str(2007) + str('_') + str(i).zfill(4) + '.jpg'
    TEST_IMAGE_PATH = os.path.join(path,graph)
# Size, in inches, of the output images.
    IMAGE_SIZE = (12, 8)

    print('Detecting...')
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            print(TEST_IMAGE_PATH)
            image = Image.open(TEST_IMAGE_PATH)
            image_np = load_image_into_numpy_array(image)
            image_np_expanded = np.expand_dims(image_np, axis=0)
            image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
            boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
            scores = detection_graph.get_tensor_by_name('detection_scores:0')
            classes = detection_graph.get_tensor_by_name('detection_classes:0')
            num_detections = detection_graph.get_tensor_by_name('num_detections:0')
        # Actual detection.
            (boxes, scores, classes, num_detections) = sess.run(
                [boxes, scores, classes, num_detections],
                feed_dict={image_tensor: image_np_expanded})
        # Print the results of a detection.
            print(scores)
            print(classes)
            print(category_index)
        # Visualization of the results of a detection.
            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)
            print(TEST_IMAGE_PATH.split('.')[0] + '.jpg')
            plt.figure(figsize=IMAGE_SIZE, dpi=300)
            plt.imshow(image_np)

            plt.savefig(TEST_IMAGE_PATH.split('.')[0] + '.jpg')