我将Python 3.6与Anaconda结合使用，并在系统上使用Spyder编辑器，该系统是Windows 10的标准桌面。我按照中的说明设置了TensorFlow对象检测API
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md。
由于正式的安装说明是Linux性质的，所以我也得到了
的帮助https://medium.com/@rohitrpatil/how-to-use-tensorflow-object-detection-api-on-windows-102ec8097699。
最后，我想通过在Jupyter笔记本上运行一个已经受支持的测试文件“ object_detection_tutorial.pynb”来测试已经设置的系统。立即出现错误：
ModuleNotFoundError Traceback (most recent call last)
<ipython-input-10-34f5cdda911a> in <module>
15 # This is needed since the notebook is stored in the object_detection folder.
16 sys.path.append("..")
---> 17 from object_detection.utils import ops as utils_ops
18
19 if StrictVersion(tf.__version__) < StrictVersion('1.12.0'):
ModuleNotFoundError: No module named 'object_detection'
即使在Github和此处进行了很多次讨论，我也找不到错误的解决方案。我决定与Spyder一起使用，并在那里测试代码。它为该行提供了错误
%matplotlib inline
。经过研究，我发现这是Jupyter式的命令，因此我将其注释掉。相反，我添加了
matplotlib.use('TkAgg')
plt.show()
我在Spyder上测试过的官方测试代码的最终结构是
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
import matplotlib
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('1.12.0'):
raise ImportError('Please upgrade your TensorFlow installation to v1.12.*.')
# This is needed to display the images.
# %matplotlib inline
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)
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[1], image.shape[2])
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: image})
# 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.int64)
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_expanded, 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)
matplotlib.use('TkAgg')
plt.show()
您可以看到我添加的最后两行。
当我运行这段代码时，它没有给出任何错误，但是，一个图形窗口打开并且从不显示图形。当我将鼠标悬停在其上时，它一直显示为忙碌。
我尝试了很多建议，但无法解决。我已经创建了系统环境变量
PYTHON_PATH
以及
的附加值C:\Users\user\models;
C:\Users\user\models\research;
C:\Users\user\models\research\slim;
C:\Users\user\models\research\object_detection;
C:\Users\user\models\research\object_detection\utils;
C:\Neon-ProgramData\Anaconda3;
C:\Neon-ProgramData\Anaconda3\Scripts;
C:\Neon-ProgramData\Anaconda3\Library\bin;
我还使用protoc.exe正确编译了proto文件，并确认.py文件位于其中。
在Anaconda中，我为TensorFlow工作创建了一个环境，而TF也可以正常工作。
我完全迷失了这个问题。我认为我正确安装了该软件，并尝试使用互联网给我的所有建议。我想测试和使用此API，并且需要有关卡住位置的帮助。