tensorflow利用预训练模型进行目标检测（二）：预训练模型的使用

一、运行样例

官网链接：https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb  但是一直有问题，没有运行起来，所以先使用一个别人写好的代码

上一个在ubuntu下可用的代码链接：https://gitee.com/bubbleit/JianDanWuTiShiBie  使用python2运行，python3可能会有问题

该代码由https://gitee.com/talengu/JianDanWuTiShiBie/tree/master而来，经过我部分的调整与修改，代码包含在ODtest.py文件中，/ssd_mobilenet_v1_coco_11_06_2017中存储的是预训练模型

原始代码如下

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
# 关闭tensorflow警告
os.environ['TF_CPP_MIN_LOG_LEVEL']='3'

detection_graph = tf.Graph()

# 加载模型数据-------------------------------------------------------------------------------------------------------
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检测-------------------------------------------------------------------------------------------------------
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.将识别结果标记在图片上
            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输出
            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("物体：%s 概率：%s" % (class_name, scores[0][i]))
                
            # matplotlib输出图片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()



# 运行
Detection()

git clone到本地后执行有几个错误

问题1

报错信息： UnicodeDecodeError: 'ascii' codec can't decode byte 0xe5 in position 1: ordinal not in range(128) 

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

主要错误是上面最后一行的Unicode解码问题，网上搜索说是读取文件时使用的编码默认时ascii而不是utf8，导致的错误；

在代码中加上如下几句即可。

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

问题2

报错信息：_tkinter.TclError: no display name and no $DISPLAY environment variable 详情：

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：参考：https://blog.csdn.net/qq_22194315/article/details/77984423

纯代码解决方案

这也是大部分人在网上诸如stackoverflow的问答平台得到的解决方案，在引入pyplot、pylab之前，要先更改matplotlib的后端模式为”Agg”。直接贴代码吧！

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

修改之后代码为：

#!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
# 关闭tensorflow警告
import sys
reload(sys)
sys.setdefaultencoding('utf8')

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

detection_graph = tf.Graph()

# 加载模型数据-------------------------------------------------------------------------------------------------------
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检测-------------------------------------------------------------------------------------------------------
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.将识别结果标记在图片上
            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输出
            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输出图片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()



# 运行
Detection()

运行结果：

如无意外，加上时间统计函数，调用已下载好的预训练模型即可

二、使用预训练模型

使用ssd_mobilenet_v1_coco_11_06_2017

对上边的代码进行修改，注意修改PATH_TO_LABELS的路径，models中包括mscoco_label_map.pbtxt文件，在/models/research/object_detection/data目录下，另外注意from object_detection.utils import label_map_util中，在utils前边要加上object_detection

修改后的代码路径为：/models/models/mcode/ODtest.py   代码如下

#!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 object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

import datetime
# 关闭tensorflow警告
import sys
reload(sys)
sys.setdefaultencoding('utf8')

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

detection_graph = tf.Graph()

# 加载模型数据-------------------------------------------------------------------------------------------------------
def loading():

    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        PATH_TO_CKPT = '/home/yanjieliu/models/models/research/object_detection/pretrained_models/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检测-------------------------------------------------------------------------------------------------------
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('/home/yanjieliu/models/models/research/object_detection/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="/home/yanjieliu/dataset/img_test/p1.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.将识别结果标记在图片上
            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输出
            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输出图片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()



# 运行
Detection()

可正确运行
若想使用该链接中的脚本http://www.baiguangnan.com/2018/02/12/objectdetection2/，则需要进行一些修改，否则会有错误，待做

传参并将时间记录到txt文档的版本，将ODtest.py进行部分修改，修改后的内容在1to10test.py中

#!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 object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

import datetime
# 关闭tensorflow警告
import time
import argparse
import sys
reload(sys)
sys.setdefaultencoding('utf8')

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

detection_graph = tf.Graph()

# 加载模型数据-------------------------------------------------------------------------------------------------------
def loading(model_name):

    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        PATH_TO_CKPT = '/home/yanjieliu/models/models/research/object_detection/pretrained_models/'+model_name + '/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检测-------------------------------------------------------------------------------------------------------
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('/home/yanjieliu/models/models/research/object_detection/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(args):
    image_path=args.image_path
    loading(args.model_name)
    #start = time.time()
    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.将识别结果标记在图片上
            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输出
            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输出图片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()

def parse_args():
    '''parse args'''
    parser = argparse.ArgumentParser()
    parser.add_argument('--image_path', default='/home/yanjieliu/dataset/img_test/p4.jpg')
    parser.add_argument('--model_name',
                        default='mask_rcnn_inception_resnet_v2_atrous_coco_2018_01_28')
    return parser.parse_args()


# 运行
start = time.time()
Detection(parse_args())
end = time.time()
print('time:
')
print str(end-start)

with open('./outputs/1to10test_outputs.txt', 'a') as f:
    f.write('
')
    f.write(str(end-start))

使用 python 1to10test_new.py --image_path /home/yanjieliu/dataset/img_test/p5.jpg --model_name mask_rcnn_inception_resnet_v2_atrous_coco_2018_01_28 便可调用运行

或者写一个shell脚本，将此命令执行10遍，然后求平均运行时间即可

例如

#!/bin/bash

for i in $(seq 1 10)
do 
    python 1to10test_new.py --image_path /home/yanjieliu/dataset/img_test/p4.jpg --model_name mask_rcnn_inception_resnet_v2_atrous_coco_2018_01_28
done

检测单张图片的模板

#!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 object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

import datetime
# 关闭tensorflow警告
import time
import MySQLdb
import argparse
import sys
reload(sys)
sys.setdefaultencoding('utf8')

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

detection_graph = tf.Graph()





# 加载模型数据-------------------------------------------------------------------------------------------------------
def loading(model_name):

    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        PATH_TO_CKPT = '/home/yanjieliu/models/models/research/object_detection/pretrained_models/'+model_name + '/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检测-------------------------------------------------------------------------------------------------------
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('/home/yanjieliu/models/models/research/object_detection/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(args):
    image_path=args.image_path
    image_name=args.image_name
    loading(args.model_name)
    #start = time.time()
    with detection_graph.as_default():
        with tf.Session(graph=detection_graph) as sess:
            # for image_path in TEST_IMAGE_PATHS:
            image = Image.open('%s%s'%(image_path, image_name))

            # 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.将识别结果标记在图片上
            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输出
            list = []
            for i in range(5):
                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]))
                #print(boxes)
                if(float(scores[0][i])>0.5):
                    list.append(class_name.encode('utf-8'))

                
                
            # matplotlib输出图片
            # Size, in inches, of the output images.
            IMAGE_SIZE = (20, 12)
            plt.figure(figsize=IMAGE_SIZE)
            plt.imshow(image_np)
            plt.show()

def parse_args():
    '''parse args'''
    parser = argparse.ArgumentParser()
    parser.add_argument('--image_path', default='/home/yanjieliu/rdshare/dataset/dog/')
    parser.add_argument('--image_name', default='dog768_576.jpg')
    parser.add_argument('--model_name',
                        default='faster_rcnn_resnet50_coco_2018_01_28')
    return parser.parse_args()



if __name__ == '__main__':
# 运行
    args=parse_args()
    start = time.time()
    Detection(args)
    end = time.time()
    print('time:
')
    print str(end-start)