od_graph_def = tf。GraphDef() AttributeError： module 'tensorflow' 没有属性'GraphDef'

Question

我有一个Mac，我正在使用tensorflow 2.0，python 3.7。 我正在按照教程为实时应用程序创建对象检测模型。 但是我收到以下错误：

"Downloads/models/research/object_detection/object_detection_tutorial.py", line 43, in <module>
od_graph_def = tf
od_graph_def = tf.GraphDef()
AttributeError: module 'tensorflow' has no attribute 'GraphDef'

以下是教程链接：

我检查了环境，我已经在蟒蛇中拥有张量流环境

import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image

sys.path.append("..")
from object_detection.utils import ops as utils_ops

from utils import label_map_util

from utils import visualization_utils as vis_util
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_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

PATH_TO_LABELS = os.path.join('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='')

Answer 1

是的，语法在 T2.0 中发生了变化。这是正确的部分：

tf.compat.v1.GraphDef()   # -> instead of tf.GraphDef()
tf.compat.v2.io.gfile.GFile()   # -> instead of tf.gfile.GFile()

Answer 2

升级到 Python 3.7 和 Tensorflow 1.2.0 到 Tensorflow 2.0.0 时，我遇到了类似的问题

如果您不想接触您的代码，只需在带有 Tensorflow 代码的 main.py 文件中添加以下 2 行：

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

就是这样！！>NOW 一切都应该无缝运行:)

但是如果你写新代码，确实(如上所述(改变这些调用：

with tf.gfile.GFile(path, 'r') as fid:

自：

with tf.io.gfile.GFile(path, 'r') as fid:

Answer 3

from object_detection.utils import ops as utils_ops
utils_ops.tf = tf.compat.v1
tf.gfile = tf.io.gfile

添加这些行可能会解决您的问题