使用 tensorflow API 计算检测到的对象

Question

我正在使用 tensorflow 对象检测教程并且一切正常。我得到了正确数量的检测到的对象。我在尝试找到一种方法来计算检测到的对象并打印出数量时遇到了一些问题。

我环顾了社区，发现有人用 boxes.shape[0] 做到了，但是，我无法让它工作。

我将教程转换为 python 并删除了对 matplotlib 的调用。我不需要它来输出带有框的图像我只需要它来打印检测到的对象的数量。

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 to display the images.
#get_ipython().magic('matplotlib inline')

# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")



from utils import label_map_util

from utils import visualization_utils as vis_util



# What model to download.
MODEL_NAME = 'test_inference_graph'

# 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('training', 'object- detection.pbtxt')

NUM_CLASSES = 1





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)



# 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, 'IMG_{}.PNG'.format(i)) for i in range(7464, 7483) ]
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'test-latest.jpg') ]

# Size, in inches, of the output images.
#IMAGE_SIZE = (20, 16)



with detection_graph.as_default():
  with tf.Session(graph=detection_graph) as sess:
    # Definite input and output Tensors for detection_graph
    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.
    detection_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.
    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)
      # 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.
      (boxes, scores, classes, num) = sess.run(
          [detection_boxes, detection_scores, detection_classes, num_detections],
          feed_dict={image_tensor: image_np_expanded})

'''
     # Visualization of the results of a detection.
      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=1)
      plt.figure(figsize=IMAGE_SIZE)
      plt.imshow(image_np)
 '''
###Below always print 1
#print(boxes.shape[0])
taco = [category_index.get(value) for index,value in enumerate(classes[0]) if scores[0,index] > 0.5]
print(len(taco))

Answer 1

num 变量应包含检测到的框数。

Answer 2

taco = [category_index.get(value) for index,value in enumerate(classes[0]) if scores[0,index] > 0.5]
print(len(taco))

使用 tensorflow API 计算检测到的对象

Counting detected objects with tensorflow API

python

object

tensorflow

detection