Question

我复制了一个测试脚本，将图像目录加载到Tensorflow：

# Typical setup to include TensorFlow.
import tensorflow as tf
from sys import argv
# Make a queue of file names including all the JPEG images files in the relative
# image directory.
filename_queue = tf.train.string_input_producer(
    tf.train.match_filenames_once(argv[1] + "/*.jpg"))

# Read an entire image file which is required since they're JPEGs, if the images
# are too large they could be split in advance to smaller files or use the Fixed
# reader to split up the file.
image_reader = tf.WholeFileReader()

# Read a whole file from the queue, the first returned value in the tuple is the
# filename which we are ignoring.
_, image_file = image_reader.read(filename_queue)

# Decode the image as a JPEG file, this will turn it into a Tensor which we can
# then use in training.
image_orig = tf.image.decode_jpeg(image_file)
image = tf.image.resize_images(image_orig, [224, 224])
image.set_shape((224, 224, 3))

# Start a new session to show example output.
with tf.Session() as sess:

然而，当我运行脚本时，我收到了一个奇怪的错误：

OutOfRangeError (see above for traceback): FIFOQueue '_1_input_producer' is closed and has insufficient elements (requested 1, current size 0)

当我尝试查找解决方案时，我得到了几个不同的答案：

tf.initialize_all_variables().run()
tf.local_variables_initializer().run()
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)

我已经尝试了所有这些选项，但所有选项都失败了。原始脚本（https://gist.github.com/eerwitt/518b0c9564e500b4b50f）只有40行。我错过了什么解决方案？

更新
我现在正在运行这个：

# Start a new session to show example output.
with tf.Session() as sess:
    # Required to get the filename matching to run.
    sess.run(tf.local_variables_initializer())
    sess.run(tf.global_variables_initializer())

    # Coordinate the loading of image files.
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    # Get an image tensor and print its value.
    image_tensor = sess.run([image])
    print(image_tensor)

    # Finish off the filename queue coordinator.
    coord.request_stop()
    coord.join(threads)

错误仍然存在。

Answer 1

由于某种原因，您需要初始化本地和全局变量。我不确切地知道why。无论如何match_filenames_once返回一个仅使用tf.global_variables_initializer()初始化的局部变量。

所以，对你的问题添加：

with tf.Session() as sess:
    sess.run(tf.local_variables_initializer())
    sess.run(tf.global_variables_initializer())
    # actual code should go here
    coord.request_stop()
    coord.join(threads)

应该解决问题。

tf.initialize_all_variables()是旧的初始化方式，我认为它是初始化的合法方式时用于初始化全局变量和局部变量。现在它被认为已被弃用并仅初始化全局变量。因此，一些使用旧式编码的源在执行代码时不会报告任何问题，但在较新的tensorflow版本中，同样会发生故障。

无论使用哪个会话初始化程序，Tensorflow图像加载都会产生OutOfRangeError

1 个答案: