利用 Tensorflow 构建自己的物体识别模型(一)

拼搏现实的明天。 2022-04-12 13:53 236阅读 0赞

# 本文首发于: [我的简书][Link 1] #

## 原料 ##

windows10+python3.5+pycharm

## 安装tensorflow ##

利用Tensorflow训练搭建自己的物体训练模型，万里长征第一步，先安装tensorflow。

tensorflow分为cpu版和gpu版，gpu版的运行速度是cpu的50倍，但是gpu版的坑太多，要安装许多开发套件,对windows的支持不够友好；更为致命的是,它需要Nvida的中高端显卡，我的电脑系统是windows10,显卡是入门级显卡，开始我还想挣扎一下，安装个gpu版，大概试了一个晚上，到底是没有成功，识时务者为俊杰，那就安装cpu版的吧。

> pip insatll tensorflow

假如没有报错，做个测试，运行以下代码

import tensorflow as tf
    #指定一个常数张量
    first_blood = tf.constant('double kill')
    #创建一个会话，方便查看结果
    sess = tf.Session()
    print(str(sess.run(first_blood)))

运行结果如下

E:\python\python.exe "E:/pycharm src/TF/__init__.py"
    2018-12-01 23:33:25.181550: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
    double kill
    
    Process finished with exit code 0

如果出现警告:

`Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2`

翻译过来的大致意思是:  
`你的CPU支持AVX扩展，但是你安装的TensorFlow版本无法编译使用`

此时需要在第一行代码前加上两行代码:

import os
    os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
    import tensorflow as tf
    # 指定一个常数张量
    first_blood = tf.constant('double kill')
    # 创建一个会话，方便查看结果
    sess = tf.Session()
    print(str(sess.run(first_blood)))

## 下载Tensorflow object detection API ##

如果有git的话，右键`git bash`,使用命令下载：

> git clone [https://github.com/tensorflow/models.git][https_github.com_tensorflow_models.git]

或者直接打开网站:

> [https://github.com/tensorflow/models][https_github.com_tensorflow_models]

点击绿色按钮->downlaod zip

下载好之后，把文件解压，注意解压路径不要包含中文，比如我的解压后的路径是:

> C:\\Users\\lenovo\\Desktop\\note\\gitclone\\models

如果下载速度很慢，可以参考:[https://blog.csdn.net/ygdxt/article/details/82825013][https_blog.csdn.net_ygdxt_article_details_82825013]

## 下载并配置protoc ##

在[https://github.com/google/protobuf/releases][https_github.com_google_protobuf_releases]中选择windows版本：  
![1.png][]

只有win32,也就是windows32位的，64位是兼容32位的。

下载好之后，解压，把bin目录下的`protoc.exe`复制到`..\models\research`文件夹下。

接着就是配置protoc了，在打开cmd下切换到`..\models\research`目录，

执行命令`protoc object_detection\protos\*.proto --python_out=.`

如果报以下的错(其实很大可能性会报错，无论是不是在管理员模式下）：

> object\_detection\\protos\*.proto: No such file or directory

则需要对指令做修改，指令`protoc object_detection\protos\*.proto --python_out=.`中的`*.proto`表示是对`research`目录下的所有后缀名为`proto`的文件做操作，那干脆我们把指令中的`*.proto`这部分改成所有后缀名为`proto`的文件，每执行一次，就会生成一个`.py`文件，由于文件太多，我已经把指令写成脚本:

import os
    
    path_url = os.path.join(os.getcwd(),r"object_detection\protos")
    print("proto path:",path_url)
    
    for file in os.listdir(path_url):
    	cmd = "protoc object_detection\protos\{} --python_out=."
    	if file.endswith(".proto"):
        	command = cmd.format(file)
        	print("excuting command:",command)
        	os.popen(command)

在`..\research`目录下新建一个文件`excuter.py`,把以上代码复制进去，保存运行，稍等一会儿就可以看到`..\research\object_detection\protos`目录下生成了许多`.py`文件，说明protoc配置成功。

## models环境变量配置 ##

### 配置环境变量 ###

依次打开：`我的电脑`—>`高级系统设置`—>`环境变量`，新建一个系统变量:  
![2.png][]

![3.png][]

> 系统变量名只要不和已有的重复，符合命令规范，没有其他要求，我这里是`tensorflow`  
> 系统变量名下有两个值,`..\research`和`..\research\slim`的绝对路径。

### 测试 ###

在`..\research`下打开cmd，运行以下命令，

> python object\_detection/builders/model\_builder\_test.py

如果出现错误:  
![4.png][]

报错原因是你的models路径太长，python无法找指定模块，  
解决办法是在你的`python`安装路径下新建一个`tensorflow_model.pth`文件  
(比如我的是`E:\python\Lib\site-packages`)  
把写到环境变量里的那两个路径复制到该文件中。  
![5.png][]

再运行命令`python object_detection/builders/model_builder_test.py`  
![6.png][]

说明配置成功

## 利用tensorflow自带模型测试 ##

测试的图片是在

> `C:\Users\lenovo\Desktop\note\gitclone\models\research\object_detection\test_images`

我们看到这里有现成的两张图片，当然也可以换成自己的。

测试的脚本是

> C:\\Users\\lenovo\\Desktop\\note\\gitclone\\models\\research\\object\_detection\\object\_detection\_tutorial.ipynb

这是一个需要用`jupyter notebook`打开的文件，不过好像在`jupyter notebook`运行会有许多毛病  
我已经把这个`ipynb`文件改写成`py`文件，并修复了一些未知问题，文件内容如下:

import numpy as np
    import os
    import six.moves.urllib as urllib
    import sys
    import tarfile
    import tensorflow as tf
    import zipfile
    
    from distutils.version import StrictVersion
    from collections import defaultdict
    from io import StringIO
    from matplotlib import pyplot as plt
    from PIL import Image
    
    # This is needed since the notebook is stored in the object_detection folder.
    sys.path.append("..")
    from object_detection.utils import ops as utils_ops
    
    if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
      raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
    
    
    
    import numpy as np
    import os
    import six.moves.urllib as urllib
    import sys
    import tarfile
    import tensorflow as tf
    import zipfile
    
    from distutils.version import StrictVersion
    from collections import defaultdict
    from io import StringIO
    from matplotlib import pyplot as plt
    from PIL import Image
    
    # This is needed since the notebook is stored in the object_detection folder.
    sys.path.append("..")
    from object_detection.utils import ops as utils_ops
    
    if StrictVersion(tf.__version__) < StrictVersion('1.9.0'):
      raise ImportError('Please upgrade your TensorFlow installation to v1.9.* or later!')
    
    
    
    from utils import label_map_util
    
    from utils import visualization_utils as vis_util
    
    
    
    
    # What model to download.
    MODEL_NAME = 'ssd_mobilenet_v1_coco_2017_11_17'
    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_FROZEN_GRAPH = 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('data', 'mscoco_label_map.pbtxt')
    
    
    
    opener = urllib.request.URLopener()
    opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)
    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())
    
    
    
    
    detection_graph = tf.Graph()
    with detection_graph.as_default():
      od_graph_def = tf.GraphDef()
      with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:
    	serialized_graph = fid.read()
    	od_graph_def.ParseFromString(serialized_graph)
    	tf.import_graph_def(od_graph_def, name='')
    
    
    
    category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)
    
    
    
    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)
    
    
    
    # For the sake of simplicity we will use only 2 images:
    # image1.jpg
    # image2.jpg
    # If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
    PATH_TO_TEST_IMAGES_DIR = 'test_images'
    TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 3) ]
    
    # Size, in inches, of the output images.
    IMAGE_SIZE = (12, 8)
    
    output_num = 1
    output_img_dic = r'\output_images'
    
    
    def run_inference_for_single_image(image, graph):
      with graph.as_default():
    	with tf.Session() as sess:
    	  # Get handles to input and output tensors
    	  ops = tf.get_default_graph().get_operations()
    	  all_tensor_names = {output.name for op in ops for output in op.outputs}
    	  tensor_dict = {}
    	  for key in [
    		  'num_detections', 'detection_boxes', 'detection_scores',
    		  'detection_classes', 'detection_masks'
    	  ]:
    		tensor_name = key + ':0'
    		if tensor_name in all_tensor_names:
    		  tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(
    			  tensor_name)
    	  if 'detection_masks' in tensor_dict:
    		# The following processing is only for single image
    		detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
    		detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
    		# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
    		real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
    		detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
    		detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
    		detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
    			detection_masks, detection_boxes, image.shape[0], image.shape[1])
    		detection_masks_reframed = tf.cast(
    			tf.greater(detection_masks_reframed, 0.5), tf.uint8)
    		# Follow the convention by adding back the batch dimension
    		tensor_dict['detection_masks'] = tf.expand_dims(
    			detection_masks_reframed, 0)
    	  image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')
    
    	  # Run inference
    	  output_dict = sess.run(tensor_dict,
    							 feed_dict={image_tensor: np.expand_dims(image, 0)})
    
    	  # all outputs are float32 numpy arrays, so convert types as appropriate
    	  output_dict['num_detections'] = int(output_dict['num_detections'][0])
    	  output_dict['detection_classes'] = output_dict[
    		  'detection_classes'][0].astype(np.uint8)
    	  output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
    	  output_dict['detection_scores'] = output_dict['detection_scores'][0]
    	  if 'detection_masks' in output_dict:
    		output_dict['detection_masks'] = output_dict['detection_masks'][0]
      return output_dict
    
    
    
    
    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)
      # Actual detection.
      output_dict = run_inference_for_single_image(image_np, detection_graph)
      # Visualization of the results of a detection.
      vis_util.visualize_boxes_and_labels_on_image_array(
    	  image_np,
    	  output_dict['detection_boxes'],
    	  output_dict['detection_classes'],
    	  output_dict['detection_scores'],
    	  category_index,
    	  instance_masks=output_dict.get('detection_masks'),
    	  use_normalized_coordinates=True,
    	  line_thickness=8)
      plt.figure(figsize=IMAGE_SIZE)
      print(1,image_np)
      plt.imshow(image_np)
      plt.show()
      global output_num
      global output_img_dic
      if not os.path.exists(output_img_dic):
    	  os.mkdir(output_img_dic)
      output_img_path = os.path.join(output_img_dic,str(output_num)+".png")
      plt.savefig(output_img_path)

> 运行上述代码需要安装`matplotlib`库，直接`pip install matplotlib`安装失败的可以去官网安装与python版本对应的whl文件。安装`matplotlib.whl`时需要先出pycharm。  
> 同时由于需要下载模型文件，需要在网络好的情况下进行测试。否则就会报`HTTP ERROR`

## 运行效果图 ##

![7.png][]  
![8.png][]

## 声明 ##

以上就是本次教程的所有内容，后续还会有系列教程，原创作品，转载请联系2391527690@qq.com  
欢迎大家多多上机操作，指出本教程的不足之处，如有问题，可加群交流，群号码: 861016679

[Link 1]: https://www.jianshu.com/p/9c9b908a2b73
[https_github.com_tensorflow_models.git]: https://github.com/tensorflow/models.git
[https_github.com_tensorflow_models]: https://github.com/tensorflow/models
[https_blog.csdn.net_ygdxt_article_details_82825013]: https://blog.csdn.net/ygdxt/article/details/82825013
[https_github.com_google_protobuf_releases]: https://github.com/google/protobuf/releases
[1.png]: /images/20220412/18fedcce6d874e758f8159e43c262366.png
[2.png]: /images/20220412/be1e9d8a1f204d8a9cb72097e096e574.png
[3.png]: /images/20220412/7389f324b1ad46c5aed9f6255cb70cac.png
[4.png]: /images/20220412/e1967a5baede450393c79f9a6e5fd0cf.png
[5.png]: /images/20220412/0118c939d1be45c58f6d3077aee7f1da.png
[6.png]: /images/20220412/104c4d6798f64daf937255acc5a774da.png
[7.png]: /images/20220412/e761eee29034428ebb049a72e4a4065d.png
[8.png]: /images/20220412/e5cea44c993e4ec1a6630c77cc3948b6.png