When I used following codes
import tensorflow as tf # def input_pipeline(filenames, batch_size): # # Define a `tf.contrib.data.Dataset` for iterating over one epoch of the data. # dataset = (tf.contrib.data.TextLineDataset(filenames) # .map(lambda line: tf.decode_csv( # line, record_defaults=[['1'], ['1'], ['1']], field_delim='-')) # .shuffle(buffer_size=10) # Equivalent to min_after_dequeue=10. # .batch(batch_size)) # # Return an *initializable* iterator over the dataset, which will allow us to # # re-initialize it at the beginning of each epoch. # return dataset.make_initializable_iterator() def decode_func(line): record_defaults = [['1'],['1'],['1']] line = tf.decode_csv(line, record_defaults=record_defaults, field_delim='-') str_to_int = lambda r: tf.string_to_number(r, tf.int32) query = tf.string_split(line[:1], ",").values title = tf.string_split(line[1:2], ",").values query = tf.map_fn(str_to_int, query, dtype=tf.int32) title = tf.map_fn(str_to_int, title, dtype=tf.int32) label = line[2] return query, title, label def input_pipeline(filenames, batch_size): # Define a `tf.contrib.data.Dataset` for iterating over one epoch of the data. dataset = tf.contrib.data.TextLineDataset(filenames) dataset = dataset.map(decode_func) dataset = dataset.shuffle(buffer_size=10) # Equivalent to min_after_dequeue=10. dataset = dataset.batch(batch_size) # Return an *initializable* iterator over the dataset, which will allow us to # re-initialize it at the beginning of each epoch. return dataset.make_initializable_iterator() filenames=['2.txt'] batch_size = 3 num_epochs = 10 iterator = input_pipeline(filenames, batch_size) # `a1`, `a2`, and `a3` represent the next element to be retrieved from the iterator. a1, a2, a3 = iterator.get_next() with tf.Session() as sess: for _ in range(num_epochs): print(_) # Resets the iterator at the beginning of an epoch. sess.run(iterator.initializer) try: while True: a, b, c = sess.run([a1, a2, a3]) print(type(a[0]), b, c) except tf.errors.OutOfRangeError: print('stop') # This will be raised when you reach the end of an epoch (i.e. the # iterator has no more elements). pass # Perform any end-of-epoch computation here. print('Done training, epoch reached') The script crashed didn't return any results, and stop when reached a, b, c = sess.run([a1, a2, a3]), but when I commented
query = tf.map_fn(str_to_int, query, dtype=tf.int32) title = tf.map_fn(str_to_int, title, dtype=tf.int32) It works and return the results.
In 2.txt, the data format is like
1,2,3-4,5-0 1-2,3,4-1 4,5,6,7,8-9-0 In addition, why the return results are byte-like object rather than str?