Tensorflow multithreading image loading - multithreading

Question

So I have this toy example code;
import glob
from tqdm import tqdm
import tensorflow as tf
imgPaths = glob.glob("/home/msmith/imgs/*/*") # Some images
filenameQ = tf.train.string_input_producer(imgPaths)
reader = tf.WholeFileReader()
key, value = reader.read(filenameQ)
img = tf.image.decode_jpeg(value)
init_op = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in tqdm(range(10000)):
img.eval().mean()
which loads images and prints the mean of each one. How to I edit it so it's multithreading the loading part of the images, which is at the moment my bottleneck on my tf image scripts.

Answer 1

EDIT (2018/3/5): It's now easier to get the same results using the tf.data API.
import glob
from tqdm import tqdm
import tensorflow as tf
imgPaths = glob.glob("/home/msmith/imgs/*/*") # Some images
dataset = (tf.data.Dataset.from_tensor_slices(imgPaths)
.map(lambda x: tf.reduce_mean(tf.decode_jpeg(tf.read_file(x))),
num_parallel_calls=16)
.prefetch(128))
iterator = dataset.make_one_shot_iterator()
next_mean = iterator.get_next()
with tf.Session() as sess:
for i in tqdm(range(10000)):
sess.run(next_mean)
As sygi suggests in their comment, a tf.train.QueueRunner can be used to define some ops that run in a separate thread, and (typically) enqueue values into a TensorFlow queue.
import glob
from tqdm import tqdm
import tensorflow as tf
imgPaths = glob.glob("/home/msmith/imgs/*/*") # Some images
filenameQ = tf.train.string_input_producer(imgPaths)
# Define a subgraph that takes a filename, reads the file, decodes it, and
# enqueues it.
filename = filenameQ.dequeue()
image_bytes = tf.read_file(filename)
decoded_image = tf.image.decode_jpeg(image_bytes)
image_queue = tf.FIFOQueue(128, [tf.uint8], None)
enqueue_op = image_queue.enqueue(decoded_image)
# Create a queue runner that will enqueue decoded images into `image_queue`.
NUM_THREADS = 16
queue_runner = tf.train.QueueRunner(
image_queue,
[enqueue_op] * NUM_THREADS, # Each element will be run from a separate thread.
image_queue.close(),
image_queue.close(cancel_pending_enqueues=True))
# Ensure that the queue runner threads are started when we call
# `tf.train.start_queue_runners()` below.
tf.train.add_queue_runner(queue_runner)
# Dequeue the next image from the queue, for returning to the client.
img = image_queue.dequeue()
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in tqdm(range(10000)):
img.eval().mean()