Tensorflow object_detection demo 注释

# coding: utf-8

# # Object Detection Demo
# Welcome to the object detection inference walkthrough!This notebook will walk you step by step through the process of using a pre-trained model to detect objects in an image. Make sure to follow the [installation instructions](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md) before you start.

# # Imports

# In[ ]:


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

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("..")#使python遍历函数时，包括上一层objection里的API。
from object_detection.utils import ops as utils_ops
#if tf.__version__ < '1.4.0':
    #raise ImportError('Please upgrade your tensorflow installation to v1.4.* or later!')


# ## Env setup

# In[ ]:


# This is needed to display the images.
get_ipython().run_line_magic('matplotlib', 'inline')
#魔法函数，有了他可以省掉plt.show()


# ## Object detection imports
# Here are the imports from the object detection module.

# In[ ]:


from utils import label_map_util

from utils import visualization_utils as vis_util


# # Model preparation准备 

# ## Variables
# 
# Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_CKPT` to point to a new .pb file.  
# 
# By default we use an "SSD with Mobilenet" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies.

# In[ ]:


# 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_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
PATH_TO_CKPT="/home/jdmking/jupyter_notebook/0918_same.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')
PATH_TO_LABELS="/home/jdmking/jupyter_notebook/num_label_map.pbtxt"

NUM_CLASSES = 21


# ## Download Model

# In[ ]:


#opener = urllib.request.URLopener()#打开网址URL,这可以是一个字符串或一个 Request对象。
#opener.retrieve(DOWNLOAD_BASE + MODEL_FILE, MODEL_FILE)#打开网址，保存在MOEDL_FILE中。
#tar_file = tarfile.open(MODEL_FILE)#解压tar_file为<tarfile.TarFile object at 0x7f57e8055358>
#for file in tar_file.getmembers():#file为<TarInfo 'ssd_mobilenet_v1_coco_2017_11_17' at 0x7f57e8037818>
    #file_name = os.path.basename(file.name)#获取对应路径的文件名ssd_mobilenet_v1_coco_2017_11_17
    #if 'frozen_inference_graph.pb' in file_name:
        #tar_file.extract(file, os.getcwd())#解压放在当前文件夹，名字为file


# ## Load a (frozen) Tensorflow model into memory.

# In[ ]:


detection_graph = tf.Graph()#创建新的计算图。
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()#将计算图进行序列化，用操作
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()#读pb文件
        od_graph_def.ParseFromString(serialized_graph)#解析文件,解析为结构化数据。
        tf.import_graph_def(od_graph_def, name='')#将图形从od_graph_def导入当前的默认Graph


# ## Loading label map
# Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine

# In[ ]:


label_map = label_map_util.load_labelmap(PATH_TO_LABELS)#将pbtxt进行proto编译
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)#将种类变成序列号


# ## Helper code

# In[ ]:


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

# In[ ]:


# 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 = "/home/jdmking/image_data/0731/0731_images"
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR,filename) for filename in 
                    os.listdir(PATH_TO_TEST_IMAGES_DIR)
                   ]
# Size, in inches, of the output images.
IMAGE_SIZE = (20,20)


# In[ ]:


def run_inference_for_single_image(image, graph):
    with graph.as_default():
        with tf.Session() as sess:
            ops = tf.get_default_graph().get_operations()#返回默认图中的操作节点列表
            all_tensor_names = {output.name for op in ops for output in op.outputs}#先是获得op，然后获得output，
        #最后得到output.name
            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)#根据名称返回tensor数据,Tensor("num_detections:0", dtype=float32)
                                #Tensor("detection_boxes:0", dtype=float32)
                                #Tensor("detection_scores:0", dtype=float32)
                                #Tensor("detection_classes:0", dtype=float32)
            if 'detection_masks' in tensor_dict:
            # The following processing is only for single image(下面的处理只是针对单个图像)
                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)})
            print(output_dict)
      # 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


# In[ ]:


for image_path in TEST_IMAGE_PATHS[0:1]:
    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)#图像变为数组和imread一样，类型为np.unit8。
  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
    image_np_expanded = np.expand_dims(image_np, axis=0)#用于扩展数组的形状，添加在0的位置。
    #因为模型的维度为[1,none,none,3].可能因为模型中第一个为batch_size
  # Actual detection.
    output_dict = run_inference_for_single_image(image_np, detection_graph)#output为字典
  # Visualization of the results of a detection.(检测结果的可视化。)
    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)
    plt.imshow(image_np)