一、運行樣例

官網鏈接：https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb 但是一直有問題，沒有運行起來，所以先使用一個別人寫好的代碼

上一個在ubuntu下可用的代碼鏈接：https://gitee.com/bubbleit/JianDanWuTiShiBie 使用python2運行，python3可能會有問題

該代碼由https://gitee.com/talengu/JianDanWuTiShiBie/tree/master而來，經過我部分的調整與修改，代碼包含在ODtest.py文件中，/ssd_mobilenet_v1_coco_11_06_2017中存儲的是預訓練模型

原始代碼如下

import numpy as np
from matplotlib import pyplot as plt
import os
import tensorflow as tf
from PIL import Image
from utils import label_map_util
from utils import visualization_utils as vis_util

import datetime
# 關閉tensorflow警告
os.environ[‘TF_CPP_MIN_LOG_LEVEL‘]=‘3‘

detection_graph = tf.Graph()

 
# 加載模型數據-------------------------------------------------------------------------------------------------------
def loading():

    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        PATH_TO_CKPT = ‘ssd_mobilenet_v1_coco_11_06_2017‘ + ‘/frozen_inference_graph.pb‘
        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=‘‘)
    return detection_graph



# Detection檢測-------------------------------------------------------------------------------------------------------
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)
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join(‘data‘, ‘mscoco_label_map.pbtxt‘)
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=90, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

def Detection(image_path="images/image1.jpg"):
    loading()
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            # for image_path in TEST_IMAGE_PATHS:
            image = Image.open(image_path)

            # the array based representation of the image will be used later in order to prepare the
            # result image with boxes and labels on it.
            image_np = load_image_into_numpy_array(image)

            # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
            image_np_expanded = np.expand_dims(image_np, axis=0)
            image_tensor = detection_graph.get_tensor_by_name(‘image_tensor:0‘)

            # Each box represents a part of the image where a particular object was detected.
            boxes = detection_graph.get_tensor_by_name(‘detection_boxes:0‘)

            # Each score represent how level of confidence for each of the objects.
            # Score is shown on the result image, together with the class label.
            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})

            # Visualization of the results of a detection.將識別結果標記在圖片上
            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)
            # output result輸出
            for i in range(3):
                if classes[0][i] in category_index.keys():
                    class_name = category_index[classes[0][i]][‘name‘]
                else:
                    class_name = ‘N/A‘
                print("物體：%s 概率：%s" % (class_name, scores[0][i]))
                
            # matplotlib輸出圖片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()



# 運行
Detection()

git clone到本地後執行有幾個錯誤

問題1

報錯信息： UnicodeDecodeError: ‘ascii‘ codec can‘t decode byte 0xe5 in position 1: ordinal not in range(128)

solution：參考：https://www.cnblogs.com/QuLory/p/3615584.html

主要錯誤是上面最後一行的Unicode解碼問題，網上搜索說是讀取文件時使用的編碼默認時ascii而不是utf8，導致的錯誤；

在代碼中加上如下幾句即可。

import sys
reload(sys)
sys.setdefaultencoding(‘utf8‘)

問題1

報錯信息：_tkinter.TclError: no display name and no $DISPLAY environment variable 詳情：

Traceback (most recent call last):
  File "ODtest.py", line 103, in <module>
    Detection()
  File "ODtest.py", line 96, in Detection
    plt.figure(figsize=IMAGE_SIZE)
  File "/usr/local/lib/python2.7/dist-packages/matplotlib/pyplot.py", line 533, in figure
    **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/matplotlib/backend_bases.py", line 161, in new_figure_manager
    return cls.new_figure_manager_given_figure(num, fig)
  File "/usr/local/lib/python2.7/dist-packages/matplotlib/backends/_backend_tk.py", line 1046, in new_figure_manager_given_figure
    window = Tk.Tk(className="matplotlib")
  File "/usr/lib/python2.7/lib-tk/Tkinter.py", line 1822, in __init__
    self.tk = _tkinter.create(screenName, baseName, className, interactive, wantobjects, useTk, sync, use)
_tkinter.TclError: no display name and no $DISPLAY environment variable

solution：參考：https://blog.csdn.net/qq_22194315/article/details/77984423

純代碼解決方案

這也是大部分人在網上諸如stackoverflow的問答平臺得到的解決方案，在引入pyplot、pylab之前，要先更改matplotlib的後端模式為”Agg”。直接貼代碼吧！

# do this before importing pylab or pyplot
Import matplotlib
matplotlib.use(‘Agg‘)
import matplotlib.pyplot asplt

修改之後代碼為：

#!usr/bin/python
# -*- coding: utf-8 -*-

import numpy as np
import matplotlib
matplotlib.use(‘Agg‘)
import matplotlib.pyplot 
from matplotlib import pyplot as plt
import os
import tensorflow as tf
from PIL import Image
from utils import label_map_util
from utils import visualization_utils as vis_util

import datetime
# 關閉tensorflow警告
import sys
reload(sys)
sys.setdefaultencoding(‘utf8‘)

os.environ[‘TF_CPP_MIN_LOG_LEVEL‘]=‘3‘

detection_graph = tf.Graph()

# 加載模型數據-------------------------------------------------------------------------------------------------------
def loading():

    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        PATH_TO_CKPT = ‘ssd_mobilenet_v1_coco_11_06_2017‘ + ‘/frozen_inference_graph.pb‘
        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=‘‘)
    return detection_graph



# Detection檢測-------------------------------------------------------------------------------------------------------
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)
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join(‘data‘, ‘mscoco_label_map.pbtxt‘)
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=90, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

def Detection(image_path="images/image1.jpg"):
    loading()
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            # for image_path in TEST_IMAGE_PATHS:
            image = Image.open(image_path)

            # the array based representation of the image will be used later in order to prepare the
            # result image with boxes and labels on it.
            image_np = load_image_into_numpy_array(image)

            # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
            image_np_expanded = np.expand_dims(image_np, axis=0)
            image_tensor = detection_graph.get_tensor_by_name(‘image_tensor:0‘)

            # Each box represents a part of the image where a particular object was detected.
            boxes = detection_graph.get_tensor_by_name(‘detection_boxes:0‘)

            # Each score represent how level of confidence for each of the objects.
            # Score is shown on the result image, together with the class label.
            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})

            # Visualization of the results of a detection.將識別結果標記在圖片上
            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)
            # output result輸出
            for i in range(3):
                if classes[0][i] in category_index.keys():
                    class_name = category_index[classes[0][i]][‘name‘]
                else:
                    class_name = ‘N/A‘
                print("object：%s gailv：%s" % (class_name, scores[0][i]))
                
            # matplotlib輸出圖片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()



# 運行
Detection()

運行結果：

如無意外，加上時間統計函數，調用已下載好的預訓練模型即可

二、使用與訓練模型

aa

tensorflow利用預訓練模型進行目標檢測（一）：預訓練模型的使用