当我使用以下代码时
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')
崩溃的脚本没有返回任何结果,到达a, b, c = sess.run([a1, a2, a3])
时停止,但是当我评论时
query = tf.map_fn(str_to_int, query, dtype=tf.int32)
title = tf.map_fn(str_to_int, title, dtype=tf.int32)
它起作用并返回结果。
在2.txt
中,数据格式类似于
1,2,3-4,5-0
1-2,3,4-1
4,5,6,7,8-9-0
此外,为什么返回结果是byte-like
对象而不是str
?
答案 0 :(得分:1)
我看了一下,看来如果你更换:
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]
通过
query = tf.string_to_number(query, out_type=tf.int32)
title = tf.string_to_number(title, out_type=tf.int32)
label = tf.string_to_number(line[2], out_type=tf.int32)
它运作得很好。
看来有两个嵌套的TensorFlow lambda函数(tf.map_fn
和DataSet.map
)不起作用。幸运的是,它过于复杂。
关于你的第二个问题,我把它作为输出:
[(array([4, 5, 6, 7, 8], dtype=int32), array([9], dtype=int32), 0)]
<type 'numpy.ndarray'>