1

当我尝试在图像列表上循环运行 Google 的 Inception 模型时，在大约 100 张左右的图像之后出现以下问题。它似乎内存不足。我在 CPU 上运行。有没有其他人遇到过这个问题？

Traceback (most recent call last):
  File "clean_dataset.py", line 33, in <module>
    description, score = inception.run_inference_on_image(f.read())
  File "/Volumes/EXPANSION/research/dcgan-transfer/data/classify_image.py", line 178, in run_inference_on_image
    node_lookup = NodeLookup()
  File "/Volumes/EXPANSION/research/dcgan-transfer/data/classify_image.py", line 83, in __init__
    self.node_lookup = self.load(label_lookup_path, uid_lookup_path)
  File "/Volumes/EXPANSION/research/dcgan-transfer/data/classify_image.py", line 112, in load
    proto_as_ascii = tf.gfile.GFile(label_lookup_path).readlines()
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 110, in readlines
    self._prereadline_check()
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/lib/io/file_io.py", line 72, in _prereadline_check
    compat.as_bytes(self.__name), 1024 * 512, status)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/contextlib.py", line 24, in __exit__
    self.gen.next()
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/tensorflow/python/framework/errors.py", line 463, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors.ResourceExhaustedError: /tmp/imagenet/imagenet_2012_challenge_label_map_proto.pbtxt


real    6m32.403s
user    7m8.210s
sys     1m36.114s

https://github.com/tensorflow/models/tree/master/inception

4

1 回答 1

3

问题是您不能简单地在自己的代码中导入原始的“classify_image.py”（ https://github.com/tensorflow/tensorflow/blob/master/tensorflow/models/image/imagenet/classify_image.py ），尤其是在您将其放入一个巨大的循环中，以“批处理模式”对数千张图像进行分类。

看看这里的原始代码：

with tf.Session() as sess:
# Some useful tensors:
# 'softmax:0': A tensor containing the normalized prediction across
#   1000 labels.
# 'pool_3:0': A tensor containing the next-to-last layer containing 2048
#   float description of the image.
# 'DecodeJpeg/contents:0': A tensor containing a string providing JPEG
#   encoding of the image.
# Runs the softmax tensor by feeding the image_data as input to the graph.
softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
predictions = sess.run(softmax_tensor,
                       {'DecodeJpeg/contents:0': image_data})
predictions = np.squeeze(predictions)

# Creates node ID --> English string lookup.
node_lookup = NodeLookup()

top_k = predictions.argsort()[-FLAGS.num_top_predictions:][::-1]
for node_id in top_k:
  human_string = node_lookup.id_to_string(node_id)
  score = predictions[node_id]
  print('%s (score = %.5f)' % (human_string, score))

从上面您可以看到，对于每个分类任务，它都会生成一个新的“NodeLookup”类实例，该实例从以下文件中加载：

  • label_lookup="imagenet_2012_challenge_label_map_proto.pbtxt"
  • uid_lookup_path="imagenet_synset_to_human_label_map.txt"

所以这个实例会非常大，然后在你的代码循环中它会生成这个类的数百个实例，这会导致'tensorflow.python.framework.errors.ResourceExhaustedError'。

我建议解决这个问题的是编写一个新脚本并从“classify_image.py”修改这些类和函数，并避免为每个循环实例化 NodeLookup 类，只需实例化一次并在循环中使用它. 像这样的东西：

with tf.Session() as sess:
        softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
        print 'Making classifications:'

        # Creates node ID --> English string lookup.
        node_lookup = NodeLookup(label_lookup_path=self.Model_Save_Path + self.label_lookup,
                                 uid_lookup_path=self.Model_Save_Path + self.uid_lookup_path)

        current_counter = 1
        for (tensor_image, image) in self.tensor_files:
            print 'On ' + str(current_counter)

            predictions = sess.run(softmax_tensor, {'DecodeJpeg/contents:0': tensor_image})
            predictions = np.squeeze(predictions)

            top_k = predictions.argsort()[-int(self.filter_level):][::-1]

             for node_id in top_k:
                 human_string = node_lookup.id_to_string(node_id)
                 score = predictions[node_id]
于 2016-12-04T08:55:26.570 回答