import tensorflow as tf 
# 設(shè)計(jì)Graph 
x1 = tf.constant([2, 3, 4]) 
x2 = tf.constant([4, 0, 1]) 
y = tf.add(x1, x2) 
# 打開一個(gè)session --> 計(jì)算y 
with tf.Session() as sess: 
  print sess.run(y) 

import tensorflow as tf 
# 設(shè)計(jì)Graph 
x1 = tf.placeholder(tf.int16) 
x2 = tf.placeholder(tf.int16) 
y = tf.add(x1, x2) 
# 用Python產(chǎn)生數(shù)據(jù) 
li1 = [2, 3, 4] 
li2 = [4, 0, 1] 
# 打開一個(gè)session --> 喂數(shù)據(jù) --> 計(jì)算y 
with tf.Session() as sess: 
  print sess.run(y, feed_dict={x1: li1, x2: li2}) 

$ echo -e "Alpha1,A1\nAlpha2,A2\nAlpha3,A3" > A.csv 
$ echo -e "Bee1,B1\nBee2,B2\nBee3,B3" > B.csv 
$ echo -e "Sea1,C1\nSea2,C2\nSea3,C3" > C.csv 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
# 生成一個(gè)先入先出隊(duì)列和一個(gè)QueueRunner,生成文件名隊(duì)列 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
# 定義Reader 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
# 定義Decoder 
example, label = tf.decode_csv(value, record_defaults=[['null'], ['null']]) 
#example_batch, label_batch = tf.train.shuffle_batch([example,label], batch_size=1, capacity=200, min_after_dequeue=100, num_threads=2) 
# 運(yùn)行Graph 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() #創(chuàng)建一個(gè)協(xié)調(diào)器，管理線程 
  threads = tf.train.start_queue_runners(coord=coord) #啟動(dòng)QueueRunner, 此時(shí)文件名隊(duì)列已經(jīng)進(jìn)隊(duì)。 
  for i in range(10): 
    print example.eval(),label.eval() 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
# 生成一個(gè)先入先出隊(duì)列和一個(gè)QueueRunner,生成文件名隊(duì)列 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
# 定義Reader 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
# 定義Decoder 
example, label = tf.decode_csv(value, record_defaults=[['null'], ['null']]) 
example_batch, label_batch = tf.train.shuffle_batch([example,label], batch_size=1, capacity=200, min_after_dequeue=100, num_threads=2) 
# 運(yùn)行Graph 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() #創(chuàng)建一個(gè)協(xié)調(diào)器，管理線程 
  threads = tf.train.start_queue_runners(coord=coord) #啟動(dòng)QueueRunner, 此時(shí)文件名隊(duì)列已經(jīng)進(jìn)隊(duì)。 
  for i in range(10): 
    e_val,l_val = sess.run([example_batch, label_batch]) 
    print e_val,l_val 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
example, label = tf.decode_csv(value, record_defaults=[['null'], ['null']]) 
# 使用tf.train.batch()會(huì)多加了一個(gè)樣本隊(duì)列和一個(gè)QueueRunner。 
#Decoder解后數(shù)據(jù)會(huì)進(jìn)入這個(gè)隊(duì)列，再批量出隊(duì)。 
# 雖然這里只有一個(gè)Reader，但可以設(shè)置多線程，相應(yīng)增加線程數(shù)會(huì)提高讀取速度，但并不是線程越多越好。 
example_batch, label_batch = tf.train.batch( 
   [example, label], batch_size=5) 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() 
  threads = tf.train.start_queue_runners(coord=coord) 
  for i in range(10): 
    e_val,l_val = sess.run([example_batch,label_batch]) 
    print e_val,l_val 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
example, label = tf.decode_csv(value, record_defaults=[['null'], ['null']]) 
# 使用tf.train.batch()會(huì)多加了一個(gè)樣本隊(duì)列和一個(gè)QueueRunner。 
#Decoder解后數(shù)據(jù)會(huì)進(jìn)入這個(gè)隊(duì)列，再批量出隊(duì)。 
# 雖然這里只有一個(gè)Reader，但可以設(shè)置多線程，相應(yīng)增加線程數(shù)會(huì)提高讀取速度，但并不是線程越多越好。 
example_batch, label_batch = tf.train.batch( 
   [example, label], batch_size=5) 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() 
  threads = tf.train.start_queue_runners(coord=coord) 
  for i in range(10): 
    print example_batch.eval(), label_batch.eval() 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
record_defaults = [['null'], ['null']] 
#定義了多種解碼器,每個(gè)解碼器跟一個(gè)reader相連 
example_list = [tf.decode_csv(value, record_defaults=record_defaults) 
         for _ in range(2)] # Reader設(shè)置為2 
# 使用tf.train.batch_join()，可以使用多個(gè)reader，并行讀取數(shù)據(jù)。每個(gè)Reader使用一個(gè)線程。 
example_batch, label_batch = tf.train.batch_join( 
   example_list, batch_size=5) 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() 
  threads = tf.train.start_queue_runners(coord=coord) 
  for i in range(10): 
    e_val,l_val = sess.run([example_batch,label_batch]) 
    print e_val,l_val 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
filenames = ['A.csv', 'B.csv', 'C.csv'] 
#num_epoch: 設(shè)置迭代數(shù) 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False,num_epochs=3) 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
record_defaults = [['null'], ['null']] 
#定義了多種解碼器,每個(gè)解碼器跟一個(gè)reader相連 
example_list = [tf.decode_csv(value, record_defaults=record_defaults) 
         for _ in range(2)] # Reader設(shè)置為2 
# 使用tf.train.batch_join()，可以使用多個(gè)reader，并行讀取數(shù)據(jù)。每個(gè)Reader使用一個(gè)線程。 
example_batch, label_batch = tf.train.batch_join( 
   example_list, batch_size=1) 
#初始化本地變量 
init_local_op = tf.initialize_local_variables() 
with tf.Session() as sess: 
  sess.run(init_local_op) 
  coord = tf.train.Coordinator() 
  threads = tf.train.start_queue_runners(coord=coord) 
  try: 
    while not coord.should_stop(): 
      e_val,l_val = sess.run([example_batch,label_batch]) 
      print e_val,l_val 
  except tf.errors.OutOfRangeError: 
      print('Epochs Complete!') 
  finally: 
      coord.request_stop() 
  coord.join(threads) 
  coord.request_stop() 
  coord.join(threads) 

#-*- coding:utf-8 -*- 
import tensorflow as tf 
# 生成一個(gè)先入先出隊(duì)列和一個(gè)QueueRunner,生成文件名隊(duì)列 
filenames = ['A.csv'] 
filename_queue = tf.train.string_input_producer(filenames, shuffle=False) 
# 定義Reader 
reader = tf.TextLineReader() 
key, value = reader.read(filename_queue) 
# 定義Decoder 
record_defaults = [[1], [1], [1], [1], [1]] 
col1, col2, col3, col4, col5 = tf.decode_csv(value,record_defaults=record_defaults) 
features = tf.pack([col1, col2, col3]) 
label = tf.pack([col4,col5]) 
example_batch, label_batch = tf.train.shuffle_batch([features,label], batch_size=2, capacity=200, min_after_dequeue=100, num_threads=2) 
# 運(yùn)行Graph 
with tf.Session() as sess: 
  coord = tf.train.Coordinator() #創(chuàng)建一個(gè)協(xié)調(diào)器，管理線程 
  threads = tf.train.start_queue_runners(coord=coord) #啟動(dòng)QueueRunner, 此時(shí)文件名隊(duì)列已經(jīng)進(jìn)隊(duì)。 
  for i in range(10): 
    e_val,l_val = sess.run([example_batch, label_batch]) 
    print e_val,l_val 
  coord.request_stop() 
  coord.join(threads) 

record_defaults = [[1], [1], [1], [1], [1]]

 def next_batch(self, batch_size, fake_data=False):
  """Return the next `batch_size` examples from this data set."""
  if fake_data:
   fake_image = [1] * 784
   if self.one_hot:
    fake_label = [1] + [0] * 9
   else:
    fake_label = 0
   return [fake_image for _ in xrange(batch_size)], [
     fake_label for _ in xrange(batch_size)
   ]
  start = self._index_in_epoch
  self._index_in_epoch += batch_size
  if self._index_in_epoch > self._num_examples: # epoch中的句子下標(biāo)是否大于所有語(yǔ)料的個(gè)數(shù)，如果為True,開始新一輪的遍歷
   # Finished epoch
   self._epochs_completed += 1
   # Shuffle the data
   perm = numpy.arange(self._num_examples) # arange函數(shù)用于創(chuàng)建等差數(shù)組
   numpy.random.shuffle(perm) # 打亂
   self._images = self._images[perm]
   self._labels = self._labels[perm]
   # Start next epoch
   start = 0
   self._index_in_epoch = batch_size
   assert batch_size <= self._num_examples
  end = self._index_in_epoch
  return self._images[start:end], self._labels[start:end]

def ptb_iterator(raw_data, batch_size, num_steps):
 """Iterate on the raw PTB data.

 This generates batch_size pointers into the raw PTB data, and allows
 minibatch iteration along these pointers.

 Args:
  raw_data: one of the raw data outputs from ptb_raw_data.
  batch_size: int, the batch size.
  num_steps: int, the number of unrolls.

 Yields:
  Pairs of the batched data, each a matrix of shape [batch_size, num_steps].
  The second element of the tuple is the same data time-shifted to the
  right by one.

 Raises:
  ValueError: if batch_size or num_steps are too high.
 """
 raw_data = np.array(raw_data, dtype=np.int32)

 data_len = len(raw_data)
 batch_len = data_len // batch_size #有多少個(gè)batch
 data = np.zeros([batch_size, batch_len], dtype=np.int32) # batch_len 有多少個(gè)單詞
 for i in range(batch_size): # batch_size 有多少個(gè)batch
  data[i] = raw_data[batch_len * i:batch_len * (i + 1)]

 epoch_size = (batch_len - 1) // num_steps # batch_len 是指一個(gè)batch中有多少個(gè)句子
 #epoch_size = ((len(data) // model.batch_size) - 1) // model.num_steps # // 表示整數(shù)除法
 if epoch_size == 0:
  raise ValueError("epoch_size == 0, decrease batch_size or num_steps")

 for i in range(epoch_size):
  x = data[:, i*num_steps:(i+1)*num_steps]
  y = data[:, i*num_steps+1:(i+1)*num_steps+1]
  yield (x, y)

  def next(self, batch_size):
    """ Return a batch of data. When dataset end is reached, start over.
    """
    if self.batch_id == len(self.data):
      self.batch_id = 0
    batch_data = (self.data[self.batch_id:min(self.batch_id +
                         batch_size, len(self.data))])
    batch_labels = (self.labels[self.batch_id:min(self.batch_id +
                         batch_size, len(self.data))])
    batch_seqlen = (self.seqlen[self.batch_id:min(self.batch_id +
                         batch_size, len(self.data))])
    self.batch_id = min(self.batch_id + batch_size, len(self.data))
    return batch_data, batch_labels, batch_seqlen

def batch_iter(sourceData, batch_size, num_epochs, shuffle=True):
  data = np.array(sourceData) # 將sourceData轉(zhuǎn)換為array存儲(chǔ)
  data_size = len(sourceData)
  num_batches_per_epoch = int(len(sourceData) / batch_size) + 1
  for epoch in range(num_epochs):
    # Shuffle the data at each epoch
    if shuffle:
      shuffle_indices = np.random.permutation(np.arange(data_size))
      shuffled_data = sourceData[shuffle_indices]
    else:
      shuffled_data = sourceData

    for batch_num in range(num_batches_per_epoch):
      start_index = batch_num * batch_size
      end_index = min((batch_num + 1) * batch_size, data_size)

      yield shuffled_data[start_index:end_index]