接下来说cifar10_input.py这个文件。
从概念上来说,这部分主要是关于数据管道(data pipe)的构建,数据流向为“二进制文件->文件名队列->数据队列->读取出的data-batch”。数据块用于输入到深度学习网络中,进行信息的forward propagation,这部分在定义模型本身部分讨论。在定义整个数据管道的时候,会使用到TensorFlow的队列机制。另外,读原数据文件的时候,要结合文件本身的格式。
"""Routine for decoding the CIFAR-10 binary file format."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
# Process images of this size. Note that this differs from the original CIFAR
# image size of 32 x 32. If one alters this number, then the entire model
# architecture will change and any model would need to be retrained.
# 图像中间的24*24作为裁剪后的新图像
IMAGE_SIZE = 24
# Global constants describing the CIFAR-10 data set.
NUM_CLASSES = 10
# 训练数据集和评估数据集的数量常量
NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN = 50000
NUM_EXAMPLES_PER_EPOCH_FOR_EVAL = 10000
def read_cifar10(filename_queue):
"""Reads and parses examples from CIFAR10 data files.
Recommendation: if you want N-way read parallelism, call this function
N times. This will give you N independent Readers reading different
files & positions within those files, which will give better mixing of
examples.
Args:
filename_queue: A queue of strings with the filenames to read from.
Returns:
An object representing a single example, with the following fields:
height: number of rows in the result (32)
width: number of columns in the result (32)
depth: number of color channels in the result (3)
key: a scalar string Tensor describing the filename & record number
for this example.
label: an int32 Tensor with the label in the range 0..9.
uint8image: a [height, width, depth] uint8 Tensor with the image data
"""
# 定义一个空的类对象,类似于c语言的结构体
class CIFAR10Record(object):
pass
result = CIFAR10Record()
# Dimensions of the images in the CIFAR-10 dataset.
# See http://www.cs.toronto.edu/~kriz/cifar.html for a description of the
# input format.
label_bytes = 1 # 2 for CIFAR-100
result.height = 32
result.width = 32
result.depth = 3
image_bytes = result.height * result.width * result.depth
# Every record consists of a label followed by the image, with a
# fixed number of bytes for each.
record_bytes = label_bytes + image_bytes
# Read a record, getting filenames from the filename_queue. No
# header or footer in the CIFAR-10 format, so we leave header_bytes
# and footer_bytes at their default of 0.
#定义一个reader,每次从文件中读取固定字节数
reader = tf.FixedLengthRecordReader(record_bytes=record_bytes)
# 返回从filename_queue中读取的(key, value)对,key和value都是字符串类型的tensor,并且当队列中的某一个文件读完成时,该文件名会dequeue
result.key, value = reader.read(filename_queue)
# Convert from a string to a vector of uint8 that is record_bytes long.
# 解码操作可以看作读二进制文件,把字符串中的字节转换为数值向量,每一个数值占用一个字节,在[0, 255]区间内,因此out_type要取uint8类型
record_bytes = tf.decode_raw(value, tf.uint8)
# The first bytes represent the label, which we convert from uint8->int32.
result.label = tf.cast(
tf.strided_slice(record_bytes, [0], [label_bytes]), tf.int32)
# The remaining bytes after the label represent the image, which we reshape
# from [depth * height * width] to [depth, height, width].
depth_major = tf.reshape(
tf.strided_slice(record_bytes, [label_bytes],
[label_bytes + image_bytes]),
[result.depth, result.height, result.width])
# Convert from [depth, height, width] to [height, width, depth].
#对data_mat的维度进行重新排列,返回值的第i个维度对应着data_mat的第perm[i]维
result.uint8image = tf.transpose(depth_major, [1, 2, 0])
return result
#生成训练图片和对应标签的队列
def _generate_image_and_label_batch(image, label, min_queue_examples,
batch_size, shuffle):
"""Construct a queued batch of images and labels.
Args:
image: 3-D Tensor of [height, width, 3] of type.float32.
label: 1-D Tensor of type.int32
min_queue_examples: int32, minimum number of samples to retain,
in the queue that provides of batches of examples.即一个batch包含的最小样本数量
batch_size: Number of images per batch.
shuffle: boolean indicating whether to use a shuffling queue.
Returns:
images: Images. 4D tensor of [batch_size, height, width, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
# Create a queue that shuffles the examples, and then
# read 'batch_size' images + labels from the example queue.
num_preprocess_threads = 16
if shuffle:
#tf.train.shuffle_batch()函数用于随机地shuffling 队列中的tensors来创建batches(也即每次可以读取多个data文件中的样例构成一个batch)。这个函数向当前Graph中添加了下列对象:
#*创建了一个shuffling queue,用于把‘tensors’中的tensors压入该队列;
#*一个dequeue_many操作,用于根据队列中的数据创建一个batch;
#*创建了一个QueueRunner对象,用于启动一个进程压数据到队列
#capacity参数用于控制shuffling queue的最大长度;min_after_dequeue参数表示进行一次dequeue操作后队列中元素的最小数量,可以用于确保batch中元素的随机性;num_threads参数用于指定多少个threads负责压tensors到队列;enqueue_many参数用于表征是否tensors中的每一个tensor都代表一个样例
#比如batch_size=5,capacity=10,min_after_dequeue=5,初始是有序的0,1,..,9(10条记录),然后打乱8,2,6,4,3,7,9,2,0,1(10条记录),队尾取出5条,剩下7,9,2,0,1(5条记录),然后又按顺序补充进来,变成7,9,2,0,1,10,11,12,13,14(10条记录),再打乱13,10,2,7,0,12...1(10条记录),再出队...
#tf.train.batch()与之类似,只不过顺序地出队列(也即每次只能从一个data文件中读取batch),少了随机性。
images, label_batch = tf.train.shuffle_batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size,
min_after_dequeue=min_queue_examples)
else:
images, label_batch = tf.train.batch(
[image, label],
batch_size=batch_size,
num_threads=num_preprocess_threads,
capacity=min_queue_examples + 3 * batch_size)
# Display the training images in the visualizer.
tf.summary.image('images', images)
return images, tf.reshape(label_batch, [batch_size])
#对训练数据进行'数据增强'操作,通过增加训练集的大小来防止过拟合
def distorted_inputs(data_dir, batch_size):
"""Construct distorted input for CIFAR training using the Reader ops.
Args:
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
for f in filenames:#检验训练数据集文件是否存在
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
## 把文件名输出到队列中,作为整个data pipe的第一阶段
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)#从文件名队列中读取一个tensor类型的图像
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for training the network. Note the many random
# distortions applied to the image.
# Randomly crop a [height, width] section of the image.
distorted_image = tf.random_crop(reshaped_image, [height, width, 3])#从原图像中切割出子图像
# Randomly flip the image horizontally.
distorted_image = tf.image.random_flip_left_right(distorted_image)#随机地左右翻转图像
# Because these operations are not commutative, consider randomizing
# the order their operation.
# NOTE: since per_image_standardization zeros the mean and makes
# the stddev unit, this likely has no effect see tensorflow#1458.
distorted_image = tf.image.random_brightness(distorted_image,
max_delta=63)#随机调节图像的亮度
distorted_image = tf.image.random_contrast(distorted_image,
lower=0.2, upper=1.8)#随机地调整图像对比度
# Subtract off the mean and divide by the variance of the pixels.
float_image = tf.image.per_image_standardization(distorted_image)#???
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN *
min_fraction_of_examples_in_queue)#设置batch的最小样本数量,即所有训练样本的2/5
print ('Filling queue with %d CIFAR images before starting to train. '
'This will take a few minutes.' % min_queue_examples)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=True)
def inputs(eval_data, data_dir, batch_size):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
data_dir: Path to the CIFAR-10 data directory.
batch_size: Number of images per batch.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
#一句话理解batche_size,iterations,epoch: 我有1000个数据,batch_size设置为500,那么我需要2次iterations,完成1次epoch。
if not eval_data:
filenames = [os.path.join(data_dir, 'data_batch_%d.bin' % i)
for i in xrange(1, 6)]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN #训练样本数量常量
else:
filenames = [os.path.join(data_dir, 'test_batch.bin')]
num_examples_per_epoch = NUM_EXAMPLES_PER_EPOCH_FOR_EVAL #评估样本数量常量
for f in filenames:
if not tf.gfile.Exists(f):
raise ValueError('Failed to find file: ' + f)
# Create a queue that produces the filenames to read.
filename_queue = tf.train.string_input_producer(filenames)
# Read examples from files in the filename queue.
read_input = read_cifar10(filename_queue)
reshaped_image = tf.cast(read_input.uint8image, tf.float32)
height = IMAGE_SIZE
width = IMAGE_SIZE
# Image processing for evaluation.
# Crop the central [height, width] of the image.
resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image,
height, width)
# Subtract off the mean and divide by the variance of the pixels.减均值然后除以标准差(图片标准化,平均数为0,标准差为1)
#具体可参考https://www.zhihu.com/question/21600637/answer/123780437
float_image = tf.image.per_image_standardization(resized_image)
# Set the shapes of tensors.
float_image.set_shape([height, width, 3])
read_input.label.set_shape([1])
# Ensure that the random shuffling has good mixing properties.
min_fraction_of_examples_in_queue = 0.4
min_queue_examples = int(num_examples_per_epoch *
min_fraction_of_examples_in_queue)
# Generate a batch of images and labels by building up a queue of examples.
return _generate_image_and_label_batch(float_image, read_input.label,
min_queue_examples, batch_size,
shuffle=False)