How to set a number for epoch in tf.python_io.tf_record_iterator - tensorflow

Question

I was trying to iterate over my data set several times. I used a tf.python_io.tf_record_iterator. But, I used it as follows:
record_iterator = tf.python_io.tf_record_iterator(path=tfrecords_filename)
for z in range(4):
for k, string_record in enumerate(record_iterator):
....
Hence, the outer loop has no effect, and iteration finished just after the inner loop was done iterating over the dataset.
Any help is much appreciated!!

Answer 1

Finally, the new tensorflow Dataset api encoded this functionality. The full documentation is found at: https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset.
Long story short, this new api will enable the end user to iterate over his database multiple times using a for loop, or using the repeat() from the Dataset class.
Here is complete code on how I have used this API:
import tensorflow as tf
import numpy as np
import time
import cv2
num_epoch = 2
batch_size = 8 # This is set to 8 since
num_threads = 9
common = "C:/Users/user/PycharmProjects/AffectiveComputingNew/database/"
filenames = [(common + "train_1_db.tfrecords"), (common + "train_2_db.tfrecords"), (common + "train_3_db.tfrecords"),
(common + "train_4_db.tfrecords"), (common + "train_5_db.tfrecords"), (common + "train_6_db.tfrecords"),
(common + "train_7_db.tfrecords"), (common + "train_8_db.tfrecords"), (common + "train_9_db.tfrecords")]
# Transforms a scalar string `example_proto` into a pair of a scalar string and
# a scalar integer, representing an image and its label, respectively.
def _parse_function(example_proto):
features = {
'height': tf.FixedLenFeature([], tf.int64),
'width': tf.FixedLenFeature([], tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string),
'features': tf.FixedLenFeature([432], tf.float32)
}
parsed_features = tf.parse_single_example(example_proto, features)
# This is how we create one example, that is, extract one example from the database.
image = tf.decode_raw(parsed_features['image_raw'], tf.uint8)
# The height and the weights are used to
height = tf.cast(parsed_features['height'], tf.int32)
width = tf.cast(parsed_features['width'], tf.int32)
# The image is reshaped since when stored as a binary format, it is flattened. Therefore, we need the
# height and the weight to restore the original image back.
image = tf.reshape(image, [height, width, 3])
features = parsed_features['features']
return features, image
random_features = tf.Variable(tf.zeros([72, 432], tf.float32))
random_images = tf.Variable(tf.zeros([72, 112, 112, 3], tf.uint8))
datasets = []
for _ in filenames:
datasets.append(tf.contrib.data.TFRecordDataset(_).map(_parse_function))
dataset_ziped = tf.contrib.data.TFRecordDataset.zip((datasets[0], datasets[1], datasets[2], datasets[3],
datasets[4], datasets[5], datasets[6], datasets[7], datasets[8]))
dataset = dataset_ziped.batch(batch_size)
iterator = dataset.make_initializable_iterator()
next_batch = iterator.get_next() # This has shape: [9, 2]
features = tf.concat((next_batch[0][0], next_batch[1][0], next_batch[2][0], next_batch[3][0],
next_batch[4][0], next_batch[5][0], next_batch[6][0], next_batch[7][0],
next_batch[8][0]), axis=0)
images = tf.concat((next_batch[0][1], next_batch[1][1], next_batch[2][1], next_batch[3][1],
next_batch[4][1], next_batch[5][1], next_batch[6][1], next_batch[7][1],
next_batch[8][1]), axis=0)
def get_features(features, images):
with tf.control_dependencies([tf.assign(random_features, features), tf.assign(random_images, images)]):
features = tf.reshape(features, shape=[9, 8, 432]) # where 8 * 9 = 72
features = tf.transpose(features, perm=[1, 0, 2]) # shape becomes: [8, 9, 432]
features = tf.reshape(features, shape=[72, 432]) # Now frames will be: 1st frame from 1st video, second from second video...
images = tf.reshape(images, shape=[9, 8, 112, 112, 3])
images = tf.transpose(images, perm=[1, 0, 2, 3, 4])
images = tf.reshape(images, shape=[72, 112, 112, 3])
return features, images
condition1 = tf.equal(tf.shape(features)[0], batch_size * 9)
condition2 = tf.equal(tf.shape(images)[0], batch_size * 9)
condition = tf.logical_and(condition1, condition2)
features, images = tf.cond(condition,
lambda: get_features(features, images),
lambda: get_features(random_features, random_images))
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
# Initialize `iterator` with training data.
sess.run(init_op)
for _ in range(num_epoch):
sess.run(iterator.initializer)
# This while loop will run indefinitly until the end of the first epoch
while True:
try:
lst = []
features_np, images_np = sess.run([features, images])
for f in features_np:
lst.append(f[0])
print(lst)
except tf.errors.OutOfRangeError:
print('errorrrrr')
break
One thing, since the last retrieved could be truncated, and this will lead to a problem (Notice how I am doing resize operations on features), therefore, I used a temporary variable that will be equal to a batch whenever the batch size is equal to my (batch_size * 9) "This is not important for now".