tf API 研读4：Inputs and Readers

#读取文件队列，使用reader中read的方法，返回key与value
filename_queue = tf.train.string_input_producer(["file0.csv", "file1.csv"])
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)

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, col4])

with tf.Session() as sess:
  # Start populating the filename queue.
  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(coord=coord)

  for i in range(1200):
    # Retrieve a single instance:
    example, label = sess.run([features, col5])

  coord.request_stop()
  coord.join(threads)

#tf.parse_example的使用举例
#输入序列化数据如下： 
serialized = [
  features
    { feature { key: "ft" value { float_list { value: [1.0, 2.0] } } } },
  features
    { feature []},
  features
    { feature { key: "ft" value { float_list { value: [3.0] } } }
]
#那么输出为一个字典(dict),如下：
{"ft": SparseTensor(indices=[[0, 0], [0, 1], [2, 0]],
                    values=[1.0, 2.0, 3.0],
                    shape=(3, 2)) }
#########
#再来看一个例子，给定两个序列化的原始输入样本：
[
  features {
    feature { key: "kw" value { bytes_list { value: [ "knit", "big" ] } } }
    feature { key: "gps" value { float_list { value: [] } } }
  },
  features {
    feature { key: "kw" value { bytes_list { value: [ "emmy" ] } } }
    feature { key: "dank" value { int64_list { value: [ 42 ] } } }
    feature { key: "gps" value { } }
  }
]
#相关参数如下：
example_names: ["input0", "input1"],
features: {
    "kw": VarLenFeature(tf.string),
    "dank": VarLenFeature(tf.int64),
    "gps": VarLenFeature(tf.float32),
}
#那么有如下输出：
{
  "kw": SparseTensor(
      indices=[[0, 0], [0, 1], [1, 0]],
      values=["knit", "big", "emmy"]
      shape=[2, 2]),
  "dank": SparseTensor(
      indices=[[1, 0]],
      values=[42],
      shape=[2, 1]),
  "gps": SparseTensor(
      indices=[],
      values=[],
      shape=[2, 0]),
}
#########
#对于两个样本的输出稠密结果情况
[
  features {
    feature { key: "age" value { int64_list { value: [ 0 ] } } }
    feature { key: "gender" value { bytes_list { value: [ "f" ] } } }
   },
   features {
    feature { key: "age" value { int64_list { value: [] } } }
    feature { key: "gender" value { bytes_list { value: [ "f" ] } } }
  }
]
#我们可以使用以下参数
example_names: ["input0", "input1"],
features: {
    "age": FixedLenFeature([], dtype=tf.int64, default_value=-1),
    "gender": FixedLenFeature([], dtype=tf.string),
}
#期望的结果如下
{
  "age": [[0], [-1]],
  "gender": [["f"], ["f"]],
}

##Example protocol buffer相关使用的例子
#将mnist的数据转换为TFRecords文件格式
import os
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets import mnist
SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'

TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'  # MNIST filenames
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'

tf.app.flags.DEFINE_string('directory', '/tmp/data',
                           'Directory to download data files and write the '
                           'converted result')
tf.app.flags.DEFINE_integer('validation_size', 5000,
                            'Number of examples to separate from the training '
                            'data for the validation set.')
FLAGS = tf.app.flags.FLAGS

def _int64_feature(value):
  return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

def _bytes_feature(value):
  return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

def convert_to(data_set, name):
  images = data_set.images
  labels = data_set.labels
  num_examples = data_set.num_examples

  if images.shape[0] != num_examples:
    raise ValueError('Images size %d does not match label size %d.' %
                     (images.shape[0], num_examples))
  rows = images.shape[1]
  cols = images.shape[2]
  depth = images.shape[3]

  filename = os.path.join(FLAGS.directory, name + '.tfrecords')
  print('Writing', filename)
  writer = tf.python_io.TFRecordWriter(filename)
  for index in range(num_examples):
    image_raw = images[index].tostring()
    example = tf.train.Example(features=tf.train.Features(feature={
        'height': _int64_feature(rows),
        'width': _int64_feature(cols),
        'depth': _int64_feature(depth),
        'label': _int64_feature(int(labels[index])),
        'image_raw': _bytes_feature(image_raw)}))
    writer.write(example.SerializeToString())
  writer.close()

def main(argv):
  # Get the data.
  data_sets = mnist.read_data_sets(FLAGS.directory,
                                   dtype=tf.uint8,
                                   reshape=False)

  # Convert to Examples and write the result to TFRecords.
  convert_to(data_sets.train, 'train')
  convert_to(data_sets.validation, 'validation')
  convert_to(data_sets.test, 'test')

if __name__ == '__main__':
  tf.app.run()

# 一个简单例子，使用tf.train.shuffle_batch创建一个具有32张图像和32个标签的batches.
image_batch, label_batch = tf.train.shuffle_batch(
      [single_image, single_label],
      batch_size=32,
      num_threads=4,
      capacity=50000,
      min_after_dequeue=10000)

#Batching函数相关例子，以函数tf.train.shuffle_batch为例
#为training, evaluation等操作将样本batching，以下代码使用随机顺序打包样本
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
  min_after_dequeue = 10000
  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

#如果需要跟多的并行或文件之间的样本乱序操作，可以使用函数tf.train.shuffle_batch_join多实例化reader
def read_my_file_format(filename_queue):
  # 与上例子相同

def input_pipeline(filenames, batch_size, read_threads, num_epochs=None):
  filename_queue = tf.train.string_input_producer(
      filenames, num_epochs=num_epochs, shuffle=True)
  example_list = [read_my_file_format(filename_queue)
                  for _ in range(read_threads)]
  min_after_dequeue = 10000
  capacity = min_after_dequeue + 3 * batch_size
  example_batch, label_batch = tf.train.shuffle_batch_join(
      example_list, batch_size=batch_size, capacity=capacity,
      min_after_dequeue=min_after_dequeue)
  return example_batch, label_batch