tensorflow学习笔记（四十二）：输入流水线

# Thread body: loop until the coordinator indicates a stop was requested.
# If some condition becomes true, ask the coordinator to stop.
#将coord传入到线程中,来帮助它们同时停止工作
def MyLoop(coord):
  while not coord.should_stop():
    ...do something...
    if ...some condition...:
      coord.request_stop()

# Main thread: create a coordinator.
coord = tf.train.Coordinator()

# Create 10 threads that run 'MyLoop()'
threads = [threading.Thread(target=MyLoop, args=(coord,)) for i in xrange(10)]

# Start the threads and wait for all of them to stop.
for t in threads:
  t.start()
coord.join(threads)

example = ...ops to create one example...
# Create a queue, and an op that enqueues examples one at a time in the queue.
queue = tf.RandomShuffleQueue(...)
enqueue_op = queue.enqueue(example)
#当enqueue_many中的数量多余`Queue`中剩余的数量时,会阻塞
#init = q.enqueue_many(([1.2,2.1,3.3],))
# Create a training graph that starts by dequeuing a batch of examples.
inputs = queue.dequeue_many(batch_size)
train_op = ...use 'inputs' to build the training part of the graph...

# Create a queue runner that will run 4 threads in parallel to enqueue
# examples.
#定义了四个`enqueue`线程,但是还没有执行
qr = tf.train.QueueRunner(queue, [enqueue_op] * 4)

# Launch the graph.
sess = tf.Session()
# Create a coordinator, launch the queue runner threads.
coord = tf.train.Coordinator()
#执行 enqueue线程,像queue中放数据
enqueue_threads = qr.create_threads(sess, coord=coord, start=True)
# Run the training loop, controlling termination with the coordinator.
for step in xrange(1000000):
    if coord.should_stop():
        break
    sess.run(train_op)
# When done, ask the threads to stop.
coord.request_stop()
# And wait for them to actually do it.
coord.join(enqueue_threads)

import tensorflow as tf
#一个Queue,用来保存文件名字.对此Queue,只读取,不dequeue
filename_queue = tf.train.string_input_producer(["file0.csv", "file1.csv"])

#用来从文件中读取数据, LineReader,每次读一行
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)

# Default values, in case of empty columns. Also specifies the type of the
# decoded result.
record_defaults = [[1], [1], [1], [1], [1]]
col1, col2, col3, col4, col5 = tf.decode_csv(
    value, record_defaults=record_defaults)
features = tf.stack([col1, col2, col3, col4])

with tf.Session() as sess:
  # Start populating the filename queue.
  coord = tf.train.Coordinator()
  #在调用run或eval执行读取之前，必须
  #用tf.train.start_queue_runners来填充队列
  threads = tf.train.start_queue_runners(coord=coord)

  for i in range(10):
    # Retrieve a single instance:
    example, label = sess.run([features, col5])
    print(example, label)
  coord.request_stop()
  coord.join(threads)

q = data_flow_ops.FIFOQueue(capacity=capacity,
                                dtypes=[input_tensor.dtype.base_dtype],
                                shapes=[element_shape],
                                shared_name=shared_name, name=name)
enq = q.enqueue_many([input_tensor])
queue_runner.add_queue_runner(
    queue_runner.QueueRunner(
        q, [enq], cancel_op=cancel_op))
if summary_name is not None:
  summary.scalar(summary_name,
                 math_ops.cast(q.size(), dtypes.float32) * (1. / capacity))
return q

reader = tf.TextLineReader() #创建一个读取数据的对象
key, value = reader.read(filename_queue)# 开始读取数据

record_defaults = [[1], [1], [1], [1], [1]]
col1, col2, col3, col4, col5 = tf.decode_csv(
    value, record_defaults=record_defaults)

#定义数据的读取与解析规则
def read_my_file_format(filename_queue):
  reader = tf.SomeReader()
  key, record_string = reader.read(filename_queue)
  example, label = tf.some_decoder(record_string)
  processed_example = some_processing(example)
  return processed_example, label

def input_pipeline(filenames, batch_size, num_epochs=None):
  filename_queue = tf.train.string_input_producer(
      filenames, num_epochs=num_epochs, shuffle=True)
  example, label = read_my_file_format(filename_queue)
  # min_after_dequeue defines how big a buffer we will randomly sample
  #   from -- bigger means better shuffling but slower start up and more
  #   memory used.
  # capacity must be larger than min_after_dequeue and the amount larger
  #   determines the maximum we will prefetch.  Recommendation:
  #   min_after_dequeue + (num_threads + a small safety margin) * batch_size
  #dequeue后的所剩数据的最小值
  min_after_dequeue = 10000
  #queue的容量
  capacity = min_after_dequeue + 3 * batch_size
  example_batch, label_batch = tf.train.shuffle_batch(
      [example, label], batch_size=batch_size, capacity=capacity,
      min_after_dequeue=min_after_dequeue)
  return example_batch, label_batch

#制作时期
tf.train.Feature(int64_list=tf.train.Int64List(value=[1.0]))
#解码时期
tf.FixedLenFeature([],tf.int64)  # 返回 1.0
tf.FixedLenFeature([1],tf.int64) # 返回 [1.0]
#对于之前的制作代码,这两种解码策略都是可以的,只不过返回的不同.

#制作时期
tf.train.Feature(int64_list=tf.train.Int64List(value=[1.0, 2.0]))
#解码时期
tf.FixedLenFeature([2],tf.int64) # 返回[1.0, 2.0]

#对于bytes,制作时期
tf.train.Feature(bytes_list=tf.train.BytesList(value=[bytestring]))
#解码时期
tf.FixedLenFeature([],tf.string)
tf.FixedLenFeature([1],tf.string)

# 如果在制作过程中, value 的长度是变化的话,解码的时候是需要用tf.VarLenFeature(dtype)了
# 上述只是说 value的长度变化, 而不是说 bytestring 的大小变化,如果bytestring变化的话,是不需要担心的,
# 一个例子就是,如果制作tfrecords的图片大小是变化的,这时候改变的只是bytestring的大小,但是value的长度
# 还是1,这时候用FixedLenFeature解码是可以正确还原数据的.