Step 1

Object Detection API configuration: in this step, the model is downloaded to prepare the object detection methodology, also are registered some operations to leave the entire environment configured.



In [0]:

    
!git clone https://github.com/tensorflow/models.git
!apt-get -qq install libprotobuf-java protobuf-compiler
!protoc ./models/research/object_detection/protos/string_int_label_map.proto --python_out=.
!cp -R models/research/object_detection/ object_detection/
!rm -rf models

Step 2

Imports necessary to execute the demonstration of Object Detection API



In [0]:

    
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

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

Step 3

Configuration of the model to be used, route to the pre-trained model and additional configuration elements for the Object Detection API implementation.



In [0]:

    
MODEL_NAME = 'faster_rcnn_inception_resnet_v2_atrous_coco_2018_01_28'
MODEL_FILE = MODEL_NAME + '.tar.gz'
DOWNLOAD_BASE = 'http://download.tensorflow.org/models/object_detection/'
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
PATH_TO_LABELS = os.path.join('object_detection/data', 'mscoco_label_map.pbtxt')
NUM_CLASSES = 90

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_CKPT, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')
    
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)

Step 4

Section with demonstration images



In [ ]:

    
!mkdir images
# replace image-url
!wget https://storage.googleapis.com/demostration_images/image.jpg -O images/image_1.jpg
# end replace

PATH_TO_TEST_IMAGES_DIR = 'images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image_{}.jpg'.format(i)) for i in range(1, 2) ]
IMAGE_SIZE = (15, 11)

Step 5

Implementation part that represents the specific detection, calling the TF session



In [0]:

    
with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
    detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
    detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
    detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
    num_detections = detection_graph.get_tensor_by_name('num_detections:0')
    for image_path in TEST_IMAGE_PATHS:
      image = Image.open(image_path)
      image_np = load_image_into_numpy_array(image)
      image_np_expanded = np.expand_dims(image_np, axis=0)
      (boxes, scores, classes, num) = sess.run(
          [detection_boxes, detection_scores, detection_classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})
      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=3)
      plt.figure(figsize=IMAGE_SIZE)
      plt.imshow(image_np)