Something went wrong with the input pipeline in tensorflow - tensorflow

Question

I am trying to get a batch of 64 images each has [64,224,224,3] dimensions and labels have [64]. There are 8126 _img_class and _img_names. However, I am getting an unexpected output. Basically, I am getting nothing and script never terminate when I run it.
def _get_images(shuffle=True):
"""Gets the images and labels as a batch"""
#get image and label list
_img_names,_img_class = _get_list()
filename_queue = tf.train.string_input_producer(_img_names)
#reader
image_reader = tf.WholeFileReader()
_, image_file = image_reader.read(filename_queue)
#decode jpeg
image_original = tf.image.decode_jpeg(image_file)
label_original = tf.convert_to_tensor(_img_class,dtype=tf.int32)
#image preprocessing
image = tf.image.resize_images(image_original, [224,224])
float_image = tf.cast(image,dtype=tf.float32)
float_image = tf.image.per_image_standardization(image)
#set the shape
float_image.set_shape((224, 224, 3))
label_original.set_shape([8126])
#parameters for shuffle
batch_size = 64
num_preprocess_threads = 16
num_examples_per_epoch = 8000
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
if shuffle:
images_batch, label_batch = tf.train.shuffle_batch(
[float_image,label_original],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 *
batch_size,
min_after_dequeue=min_queue_examples)
else:
images_batch, label_batch = tf.train.batch(
[float_image,label_original],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size)
return images_batch,label_batch
with tf.Session() as sess:
tf.global_variables_initializer().run()
# Coordinate the loading of image files.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
images,labels = _get_images(shuffle=True)
# Get an image tensor and print its value.
image_tensor,labels = sess.run([images,labels])
# Finish off the filename queue coordinator.
coord.request_stop()
coord.join(threads)
When I set enqueue_many=True I am getting the following error.
TypeError: 'Tensor' object is not iterable.

Answer 1

You need to start the queue_runners after calling the _get_images function. As queue is defined in that function.
...
images,labels = _get_images(shuffle=True)
tf.global_variables_initializer().run()
tf.local_variables_initializer().run()
# Coordinate the loading of image files.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
image_tensor,labels = sess.run([images,labels])