基于神经网络进行mnist手写数字识别

识别率可达99%，官网是py3.0版本以下，我改成了py3.0以上可用

数据集以及参考：http://www.tensorfly.cn/tfdoc/tutorials/mnist_pros.html

input_data.py

# #!/usr/bin/python
# # coding:utf-8

# 用于下载和读取MNIST数据的函数
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import gzip
import os
import tensorflow.python.platform
import numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf

SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'


# 若数据不存在，则从Yann的网站下载数据
def maybe_download(filename, work_directory):
    if not os.path.exists(work_directory):
        os.mkdir(work_directory)
    filepath = os.path.join(work_directory, filename)
    # 若指定路径不存在,则开始从原网站上下载
    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)[0]


# 将图像提取到一个4维uint8类型的numpy数组[index, y, x, depth]
def extract_images(filename):
    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


# 将类标签从标量转换为一个one-hot向量
def dense_to_one_hot(labels_dense, num_classes=10):
    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


# 将标签提取到一维uint8类型的numpy数组[index]中
def extract_labels(filename, one_hot=False):
    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


# 构造DataSet类
# one_hot arg仅在fake_data为true时使用
# `dtype`可以是`uint8`，将输入保留为`[0,255]`，或`float32`以重新调整为[0,1]。
class DataSet(object):
    def __init__(self, images, labels, fake_data=False, one_hot=False, dtype=tf.float32):
        dtype = tf.as_dtype(dtype).base_dtype
        if dtype not in (tf.uint8, tf.float32):
            raise TypeError('Invalid image dtype %r, expected uint8 or float32' % dtype)
        if fake_data:
            self._num_examples = 10000
            self.one_hot = one_hot
        else:
            assert images.shape[0] == labels.shape[0], (
                        'images.shape: %s labels.shape: %s' % (images.shape, labels.shape))
            self._num_examples = images.shape[0]
            # 将[num examples, rows, columns, depth]转换形状成[num examples, rows*columns] (assuming depth == 1)
            assert images.shape[3] == 1
            images = images.reshape(images.shape[0], images.shape[1] * images.shape[2])
            if dtype == tf.float32:
                # 将[0, 255]转换为[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

    # 从数据集返回下一个`batch_size`示例
    def next_batch(self, batch_size, fake_data=False):
        if fake_data:
            fake_image = [1] * 784
            if self.one_hot:
                fake_label = [1] + [0] * 9
            else:
                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
        # 完成一个epoch
        if self._index_in_epoch > self._num_examples:
            # 随机抽取数据
            self._epochs_completed += 1
            perm = numpy.arange(self._num_examples)
            numpy.random.shuffle(perm)
            self._images = self._images[perm]
            self._labels = self._labels[perm]
            # 开始下一个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]


# 读取训练数据
def read_data_sets(train_dir, fake_data=False, one_hot=False, dtype=tf.float32):
    class DataSets(object):
        pass

    data_sets = DataSets()
    # 若fake_data为true则返回空数据
    if fake_data:
        def fake():
            return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)

        data_sets.train = fake()
        data_sets.validation = fake()
        data_sets.test = fake()
        return data_sets
    # 训练和测试数据文件名
    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
    # 读取训练和测试数据
    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)
    # 取前5000个作为验证数据
    validation_images = train_images[:VALIDATION_SIZE]
    validation_labels = train_labels[:VALIDATION_SIZE]
    # 取前5000个以后的作为训练数据
    train_images = train_images[VALIDATION_SIZE:]
    train_labels = train_labels[VALIDATION_SIZE:]
    # 定义训练,验证和测试
    data_sets.train = DataSet(train_images, train_labels, dtype=dtype)
    data_sets.validation = DataSet(validation_images, validation_labels, dtype=dtype)
    data_sets.test = DataSet(test_images, test_labels, dtype=dtype)
    return data_sets

 

主程序

import input_data
import tensorflow as tf

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

sess=tf.InteractiveSession()

x=tf.placeholder(tf.float32,[None,784])
y_=tf.placeholder(tf.float32,[None,10])

W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))

def weight_variable(shape):
    initial=tf.truncated_normal(shape,stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial=tf.constant(0.1,shape=shape)
    return tf.Variable(initial)

def conv2d(x,W):
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

def max_pool_2x2(x):
    return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME')

W_conv1=weight_variable([5,5,1,32])
b_conv1=bias_variable([32])
x_image=tf.reshape(x,[-1,28,28,1])

h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1=max_pool_2x2(h_conv1)

W_conv2=weight_variable([5,5,32,64])
b_conv2=bias_variable([64])

h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2=max_pool_2x2(h_conv2)

W_fc1=weight_variable([7*7*64,1024])
b_fc1=bias_variable([1024])

h_pool2_flat=tf.reshape(h_pool2,[-1,7*7*64])
h_fc1=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)

keep_prob=tf.placeholder(tf.float32)
h_fc1_drop=tf.nn.dropout(h_fc1,keep_prob)

W_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])

y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)

cross_entropy=-tf.reduce_sum(y_*tf.log(y_conv))

train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction=tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

sess.run(tf.global_variables_initializer())

for i in range(20000):
    batch=mnist.train.next_batch(50)
    if i%100 == 0:
        train_accuravy=accuracy.eval(feed_dict={x:batch[0],y_:batch[1],keep_prob:1.0})
        print("step %d, training accuracy %g" %(i,train_accuravy))
    train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})

print("test accuracy %g"%accuracy.eval(feed_dict={x:mnist.test.images,y_:mnist.test.labels,keep_prob:1.0}))