在Tensorflow中使用tf.contrib.data.Datasets API时无法处理错误

Question

I have created tfrecords as my database. The database consists of 9 different tfrecord files. The purpose was to feed in a batch of samples from the 9 databases into the model. Therefore, I have used the zip function with TFRecordDataset . Each sample consists of a frame along with its feature set. Hence, I need to take 8 samples from each tfrecord file, which gives a total of 72 (features, image) in a batch. Hence, I extracted the features alone with images as shown in the code below.

Problem: When I reach the end of the 1st epoch, the remaining data as less than 72. As a result, the data from the second epoch as added to make up a batch of 72 samples. So, this is not desigrable in my case since I am training a Recurrent neural network, so I have a state that should be consistent (Not necessary to be discussed now).

Therefore, I didn't use the repeat function, instead, tries to implement what is mentioned in https://www.tensorflow.org/programmers_guide/datasets Under Processing multiple epochs, ie, use for loop with try and except.

# Compute for 100 epochs.
for _ in range(100):
  sess.run(iterator.initializer)
  while True:
    try:
      sess.run(next_element)
    except tf.errors.OutOfRangeError:
      break

  # [Perform end-of-epoch calculations here.]

Once I did that, I got into another problem. First here is my full code:

import tensorflow as tf
import numpy as np
import time
import cv2

num_epoch = 1
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]))

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.repeat(num_epoch)
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)
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.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)
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])

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 = sess.run([features])[0] # since the output is always: (1, 72, 432)

                for f in features_np:
                    lst.append(f[0])

            except tf.errors.OutOfRangeError:
                print('errorrrrr')

So, since the number of samples is no longer 72, I run into an error at line:

features = tf.reshape(features, shape=[9, 8, 432]) # where 8 * 9 = 72

So, I need a way to handle this error. I tried assertion as follows:

assert_op = tf.Assert(tf.equal(tf.shape(features[0]), batch_size * 9), [features])
with tf.control_dependencies([assert_op])... after features = tf.concat...

And it didn't work. I tried tf.cond as follows (and it didn't work as well):

tf.cond(tf.equal(tf.shape(features)[0], batch_size * 9),
        lambda: tf.assign(random_features, features),
        lambda: tf.assign(random_features, random_features))

features = tf.reshape(random_features, shape=[9, 8, 432]) # where 8 * 9 = 72
....

In conclusion, I need to way to iterate over epochs without interleaving samples from different iterations, and at the same time holding the issue of the feature while using the reshape function (where the batch size is less than 72 in my case).

Any help is much appreciated!!

Answer 1

So, since the last batch is truncated, I created a temporary variable that will be assigned the value of the initial batch whenever the batch size is equal to my batch_size specified in the code. Therefore, once the size of the current batch is not longer equal to batch_size , I used the temporary batch that I have created. Here is the following solution:

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
# Here is the temp var that I will use whenever the return batch from the dataset doesn't have a size of batch_size * 9 mentioned above. 
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

Please note that I was always mentioning batch_size * 9 since when zipping the datasets, that would create a sample data who's elements are fetched from 9 different datasets. Therefore, since I assigned the batch_size to be 8, to have 72 samples, I took 8 * 9.