Tensorflow mixes images and tags when creating a batch

Question

So, I am stuck in this problem for several weeks. I want to make a batch of images from a list of image file names. I insert a list of file names into the queue and use a reader to get the file. The reader then returns the file name and file of the read image.

My problem is that when I do batch processing using decoded jpg and shortcuts from the reader, tf.train.shuffle_batch () mixes images and file names, so now the labels are in the wrong order for image files. Is there something I'm doing wrong with queue / shuffle_batch and how can I fix it so that the package comes out with the correct labels for the correct files?

Many thanks!

import tensorflow as tf
from tensorflow.python.framework import ops


def preprocess_image_tensor(image_tf):
  image = tf.image.convert_image_dtype(image_tf, dtype=tf.float32)
  image = tf.image.resize_image_with_crop_or_pad(image, 300, 300)
  image = tf.image.per_image_standardization(image)
return image

# original image names and labels
image_paths = ["image_0.jpg", "image_1.jpg", "image_2.jpg", "image_3.jpg", "image_4.jpg", "image_5.jpg", "image_6.jpg", "image_7.jpg", "image_8.jpg"]

labels = [0, 1, 2, 3, 4, 5, 6, 7, 8]

# converting arrays to tensors
image_paths_tf = ops.convert_to_tensor(image_paths, dtype=tf.string, name="image_paths_tf")
labels_tf = ops.convert_to_tensor(labels, dtype=tf.int32, name="labels_tf")

# getting tensor slices
image_path_tf, label_tf = tf.train.slice_input_producer([image_paths_tf, labels_tf], shuffle=False)

# getting image tensors from jpeg and performing preprocessing
image_buffer_tf = tf.read_file(image_path_tf, name="image_buffer")
image_tf = tf.image.decode_jpeg(image_buffer_tf, channels=3, name="image")
image_tf = preprocess_image_tensor(image_tf)

# creating a batch of images and labels
batch_size = 5
num_threads = 4
images_batch_tf, labels_batch_tf = tf.train.batch([image_tf, label_tf], batch_size=batch_size, num_threads=num_threads)

# running testing session to check order of images and labels 
init = tf.global_variables_initializer()
with tf.Session() as sess:
  sess.run(init)

  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)

  print image_path_tf.eval()
  print label_tf.eval()

  coord.request_stop()
  coord.join(threads)

Run codeHide result

Answer 1

... tf ?

, :

  print image_path_tf.eval()
  print label_tf.eval()

image_path_tf label_tf, , , :

image_path_tf, label_tf = tf.train.slice_input_producer([image_paths_tf, labels_tf], shuffle=False)

, ?

image_paths, labels = sess.run([images_batch_tf, labels_batch_tf])
print(image_paths)
print(labels)

Answer 2

, / jpeg. , . , , image_paths labels, tf.train.slice_input_producer, , tf.train.batch.

import tensorflow as tf
from tensorflow.python.framework import ops

shuffle = True
batch_size = 128
num_threads = 8

def get_data():
    """
    Return image_paths, labels such that label[i] corresponds to image_paths[i].

    image_paths: list of strings
    labels: list/np array of labels
    """
    raise NotImplementedError()

def preprocess_image_tensor(image_tf):
    """Preprocess a single image."""
    image = tf.image.convert_image_dtype(image_tf, dtype=tf.float32)
    image = tf.image.resize_image_with_crop_or_pad(image, 300, 300)
    image = tf.image.per_image_standardization(image)
    return image

image_paths, labels = get_data()

image_paths_tf = ops.convert_to_tensor(image_paths, dtype=tf.string, name='image_paths')
labels_tf = ops.convert_to_tensor(image_paths, dtype=tf.int32, name='labels')
image_path_tf, label_tf = tf.train.slice_input_producer([image_paths_tf, labels_tf], shuffle=shuffle)

# preprocess single image paths
image_buffer_tf = tf.read_file(image_path_tf, name='image_buffer')
image_tf = tf.image.decode_jpeg(image_buffer_tf, channels=3, name='image')
image_tf = preprocess_image_tensor(image_tf)

# batch the results
image_batch_tf, labels_batch_tf = tf.train.batch([image_tf, label_tf], batch_size=batch_size, num_threads=num_threads)