Build your own application based on Google's open source tensorflow object detection API video object recognition system (I)

Based on the first part ​​ Install and run Google open source TensorFlow Object Detection API Video object recognition system ​​, Build your own application .

Replace the test image

Analysis of the source code ：

The official test pictures are placed in test_images Under the table of contents , The name format is image{}.jpg（image+ Digital format ）, Cycle two （image1.jpg、image2.jpg）, To replace your own test image, just delete the original test_images Picture of catalog , Change your picture to image{}.jpg Format , If there are more than two pictures, modify range(1,?) that will do .

Model replacement

Analysis of the source code ：

​ ​ Model description address ​​, As shown in the figure below, select the model you need to download ：

The source code will be MODEL_NAME Replace it with the model you need , Pay attention to adding a timestamp

Integrate into your own PYTHON project

newly build PYTHON project , Any project name , The catalog results are as follows ：

The whole compiled in the previous article object_detection Copy the directory to object_detection\object_detection\ Next ,

newly build test_images Store test pictures , The compiled object_detection/data Copy the directory to object_detection\ Next ,

Transfer the downloaded model ssd_mobilenet_v2_coco_2018_03_29.tar.gz copy to object_detection\ Next ,

newly build ImageTest.py.

So much nonsense , Start coding ：

Log in and copy

       

        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("..")
        
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!')
        

        
# This is needed to display the images.
        
from object_detection.utils import label_map_util
        

        
from object_detection.utils import visualization_utils as vis_util
        

        
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
        
##Model preparation##
        

        
# What model to download.
        
MODEL_NAME = 'ssd_mobilenet_v2_coco_2018_03_29'
        
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('data', 'mscoco_label_map.pbtxt')
        

        
NUM_CLASSES = 90
        

        
## Download Model##
        
#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())
        

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

        
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)
        

        
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)
        
  plt.imshow(image_np)
        
  plt.show()
       
       

        
1.
        
2.
        
3.
        
4.
        
5.
        
6.
        
7.
        
8.
        
9.
        
10.
        
11.
        
12.
        
13.
        
14.
        
15.
        
16.
        
17.
        
18.
        
19.
        
20.
        
21.
        
22.
        
23.
        
24.
        
25.
        
26.
        
27.
        
28.
        
29.
        
30.
        
31.
        
32.
        
33.
        
34.
        
35.
        
36.
        
37.
        
38.
        
39.
        
40.
        
41.
        
42.
        
43.
        
44.
        
45.
        
46.
        
47.
        
48.
        
49.
        
50.
        
51.
        
52.
        
53.
        
54.
        
55.
        
56.
        
57.
        
58.
        
59.
        
60.
        
61.
        
62.
        
63.
        
64.
        
65.
        
66.
        
67.
        
68.
        
69.
        
70.
        
71.
        
72.
        
73.
        
74.
        
75.
        
76.
        
77.
        
78.
        
79.
        
80.
        
81.
        
82.
        
83.
        
84.
        
85.
        
86.
        
87.
        
88.
        
89.
        
90.
        
91.
        
92.
        
93.
        
94.
        
95.
        
96.
        
97.
        
98.
        
99.
        
100.
        
101.
        
102.
        
103.
        
104.
        
105.
        
106.
        
107.
        
108.
        
109.
        
110.
        
111.
        
112.
        
113.
        
114.
        
115.
        
116.
        
117.
        
118.
        
119.
        
120.
        
121.
        
122.
        
123.
        
124.
        
125.
        
126.
        
127.
        
128.
        
129.
        
130.
        
131.
        
132.
        
133.
        
134.
        
135.
        
136.
        
137.
        
138.
        
139.
        
140.
        
141.
        
142.
        
143.
        
144.
        
145.
        
146.
        
147.
       

The above code will modify the source code ：

Change it to

Change it to （ The model has been downloaded and put , No need to download again ）

Change it to （ New addition plt.show(), You can't show it without pictures ）

Since then , The TensorFlow Object Detection API Integrate into your own project .