tensorflow学习(2)MNIST机器学习入门

以一个softmax回归例子来讲解；

MNIST数据集的官网是Yann LeCun’s website。在这里，我们提供了一份python源代码用于自动下载和安装这个数据集。你可以直接复制粘贴到你的代码文件里面。

input_data.py:

#coding=utf-8
# Copyright 2015 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0 #
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import gzip
import os
import numpy
#from six.moves import urllib
import urllib.request
#from six.moves import xrange  # pylint: disable=redefined-builtin
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."""
if not os.path.exists(work_directory):
os.mkdir(work_directory)
filepath = os.path.join(work_directory, filename)
if not os.path.exists(filepath):
filepath, _ = urllib.request.urlretrieve(SOURCE_URL + filename, filepath)
statinfo = os.stat(filepath)
print('Successfully 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
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_one_hot.flat[index_offset + labels_dense.ravel()] = 1
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 range(784)]
fake_label = 0
return [fake_image for _ in range(batch_size)], [
fake_label for _ in range(batch_size)]
start = self._index_in_epoch
self._index_in_epoch += batch_size
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

通过以下两行代码自动下载。

import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

下载下来的数据集被分成两部分：60000行的训练数据集（mnist.train）和10000行的测试数据集（mnist.test）。这样的切分很重要，在机器学习模型设计时必须有一个单独的测试数据集不用于训练而是用来评估这个模型的性能，从而更加容易把设计的模型推广到其他数据集上（泛化）。

每一张图片包含28像素X28像素。我们可以用一个数字数组来表示这张图片。我们把这个数组展开成一个向量，长度是 28x28 = 784。

import tensorflow as tf
#我们通过操作符号变量来描述这些可交互的操作单元，可以用下面的方式创建一个。
x= tf.placeholder("float",[None,784])#占位符
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y= tf.nn.softmax(tf.matmul(x,W)+b)#只需一行代码

训练模型，代价函数：



y 是我们预测的概率分布, y’ 是实际的分布（我们输入的one-hot vector)。比较粗糙的理解是，交叉熵是用来衡量我们的预测用于描述真相的有效性。更详细的关于交叉熵的解释超出本教程的范畴，但是你很有必要好好理解它。

为了计算交叉熵，我们首先需要添加一个新的占位符用于输入正确值：

y_ =tf.placeholder("float",[None,10])

交叉熵计算：

cross_entropy = -tf.reduce_sum(y_*tf.log(y))#用 tf.reduce_sum 计算张量的所有元素的总和

我们要求TensorFlow用梯度下降算法（gradient descent algorithm）以0.01的学习速率最小化交叉熵。梯度下降算法（gradient descent algorithm）是一个简单的学习过程，TensorFlow只需将每个变量一点点地往使成本不断降低的方向移动。

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

初始化变量：

init = tf.initialize_all_variables()
sess= tf.Session()
sess.run(init)

训练，以随机梯度下降法来运行（1000次迭代）。

for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

衡量模型：

correct_prediction =tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

最终代码：

import tensorflow as tf
x= tf.placeholder("float",[None,784])#占位符
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))
y= tf.nn.softmax(tf.matmul(x,W)+b)#只需一行代码
#训练模型（成本函数：交叉熵，y'实际分布，y是预测分布）
y_ =tf.placeholder("float",[None,10])
cross_entropy = -tf.reduce_sum(y_*tf.log(y))#用 tf.reduce_sum 计算张量的所有元素的总和
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.initialize_all_variables()
sess= tf.Session()
sess.run(init)
#训练，迭代一千次
for i in range(1000):
batch_xs , batch_ys = mnist.train.next_batch(100)
sess.run(train_step,feed_dict={x:batch_xs,y_:batch_ys})#使用一小部分的随机数据来进行训练被称为随机训练（stochastic training）- 在这里更确切的说是随机梯度下降训练

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print (sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels}))