Tensorflow学习笔记（8）——input_data.py解析

这里学习一下前面用到的读取mnist数据库文件的代码。其实并没有用到Tensorlfow的东西，但是读取数据库文件是使用Tensorflow编程实现功能的基础，因此归到Tensorflow的学习笔记中。

这里需要注意的主要有以下几点：

1.dense_to_one_hot函数

2.DataSet类中next_batch函数

3.read_data_sets函数

这里有一个问题：

dense_to_one_hot函数里

def dense_to_one_hot(labels_dense, num_classes=10):
"""Convert class labels from scalars to one-hot vectors."""
num_labels = labels_dense.shape[0]
index_offset = numpy.arange(num_labels) * num_classes
labels_one_hot = numpy.zeros((num_labels, num_classes))
#labels_dense.ravel()将整个数组展成一个一维数组
#labels_dense.flat[i]即将labels_dense看成一个一维数组，取其第i个变量
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1#报错？
return labels_one_hot

注释有报错那一行，在整体程序运行的时候并没有出错，单独拿出来就出错，原因未知，还需要继续学习。

具体代码如下所示，解析如代码中注释所示：

#coding=utf-8

#input_data.py的详解
#学习读取数据文件的方法，以便读取自己需要的数据库文件（二进制文件）
"""Functions for downloading and reading MNIST data."""
from __future__ import print_function
import gzip
import os
import urllib
import numpy
SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'
def maybe_download(filename, work_directory):
"""Download the data from Yann's website, unless it's already here."""
#判断目录文件是否存在，不存在则创建该目录
if not os.path.exists(work_directory):
os.mkdir(work_directory)
#需要读取的文件路径
filepath = os.path.join(work_directory, filename)
if not os.path.exists(filepath):
filepath, _ = urllib.urlretrieve(SOURCE_URL + filename, filepath)
statinfo = os.stat(filepath)
print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
return filepath

def _read32(bytestream):
dt = numpy.dtype(numpy.uint32).newbyteorder('>')
return numpy.frombuffer(bytestream.read(4), dtype=dt)

def extract_images(filename):
"""Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
print('Extracting', filename)
with gzip.open(filename) as bytestream:
magic = _read32(bytestream)
if magic != 2051:
raise ValueError(
'Invalid magic number %d in MNIST image file: %s' %
(magic, filename))
num_images = _read32(bytestream)
rows = _read32(bytestream)
cols = _read32(bytestream)
buf = bytestream.read(rows * cols * num_images)
data = numpy.frombuffer(buf, dtype=numpy.uint8)
data = data.reshape(num_images, rows, cols, 1)
return data
#将稠密标签向量变成稀疏的标签矩阵
#eg：若原向量的第i行为3，则对应稀疏矩阵的第i行下标为3的值为1，其余为0
def dense_to_one_hot(labels_dense, num_classes=10):
"""Convert class labels from scalars to one-hot vectors."""
num_labels = labels_dense.shape[0]
index_offset = numpy.arange(num_labels) * num_classes
labels_one_hot = numpy.zeros((num_labels, num_classes))
#labels_dense.ravel()将整个数组展成一个一维数组
#labels_dense.flat[i]即将labels_dense看成一个一维数组，取其第i个变量
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1#报错？
return labels_one_hot

def extract_labels(filename, one_hot=False):
"""Extract the labels into a 1D uint8 numpy array [index]."""
print('Extracting', filename)
with gzip.open(filename) as bytestream:
magic = _read32(bytestream)
if magic != 2049:
raise ValueError(
'Invalid magic number %d in MNIST label file: %s' %
(magic, filename))
num_items = _read32(bytestream)
buf = bytestream.read(num_items)
labels = numpy.frombuffer(buf, dtype=numpy.uint8)
if one_hot:
return dense_to_one_hot(labels)
return labels
class DataSet(object):
def __init__(self, images, labels, fake_data=False):
if fake_data:
self._num_examples = 10000
else:
assert images.shape[0] == labels.shape[0], (
"images.shape: %s labels.shape: %s" % (images.shape,
labels.shape))
self._num_examples = images.shape[0]
# Convert shape from [num examples, rows, columns, depth]
# to [num examples, rows*columns] (assuming depth == 1)

assert images.shape[3] == 1
images = images.reshape(images.shape[0],
images.shape[1] * images.shape[2])
# Convert from [0, 255] -> [0.0, 1.0].
images = images.astype(numpy.float32)
images = numpy.multiply(images, 1.0 / 255.0)
self._images = images
self._labels = labels
self._epochs_completed = 0
self._index_in_epoch = 0
@property
def images(self):
return self._images
@property
def labels(self):
return self._labels
@property
def num_examples(self):
return self._num_examples
@property
def epochs_completed(self):
return self._epochs_completed
def next_batch(self, batch_size, fake_data=False):
"""Return the next `batch_size` examples from this data set."""
if fake_data:
fake_image = [1.0 for _ in xrange(784)]
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
#若当前训练读取的index>总体的images数时，则读取读取开始的batch_size大小的数据
if self._index_in_epoch > self._num_examples:
# Finished epoch
self._epochs_completed += 1
# Shuffle the data
perm = numpy.arange(self._num_examples)
numpy.random.shuffle(perm)
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 read_data_sets(train_dir, fake_data=False, one_hot=False):
class DataSets(object):
pass
data_sets = DataSets()
if fake_data:
data_sets.train = DataSet([], [], fake_data=True)
data_sets.validation = DataSet([], [], fake_data=True)
data_sets.test = DataSet([], [], fake_data=True)
return data_sets
TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
VALIDATION_SIZE = 5000
local_file = maybe_download(TRAIN_IMAGES, train_dir)
train_images = extract_images(local_file)
local_file = maybe_download(TRAIN_LABELS, train_dir)
train_labels = extract_labels(local_file, one_hot=one_hot)
local_file = maybe_download(TEST_IMAGES, train_dir)
test_images = extract_images(local_file)
local_file = maybe_download(TEST_LABELS, train_dir)
test_labels = extract_labels(local_file, one_hot=one_hot)
validation_images = train_images[:VALIDATION_SIZE]
validation_labels = train_labels[:VALIDATION_SIZE]
train_images = train_images[VALIDATION_SIZE:]
train_labels = train_labels[VALIDATION_SIZE:]
data_sets.train = DataSet(train_images, train_labels)
data_sets.validation = DataSet(validation_images, validation_labels)
data_sets.test = DataSet(test_images, test_labels)
return data_sets