簡介：本文主要是MNIST手寫數字分類問題的學習驗證筆記。對於已經親自動手操作的大神們，請自動略過

數據下載

http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz(沒有下載腳本或網絡不好，下載不下來時使用)

• 下載下來的數據集不是正規的圖片格式，而是帶有標籤的圖片編碼文件。如果需要看一下圖片的內容，可以通過一下的python程序 查看

# -*- coding: utf-8 -*-

from PIL import Image

import struct

def read_image(filename):

f = open(filename, 'rb')

index = 0

buf = f.read()

f.close()

magic, images, rows, columns = struct.unpack_from('>IIII' , buf , index)

index += struct.calcsize('>IIII')

for i in range(images):

#for i in xrange(2000):

image = Image.new('L', (columns, rows))

for x in range(rows):

for y in range(columns):

image.putpixel((y, x), int(struct.unpack_from('>B', buf, index)[0]))

index += struct.calcsize('>B')

print ('save ' + str(i) + 'image')

image.save('D:\data\\train-images-idx3-ubyte\\test\\' + str(i) + '.png')

def read_label(filename, saveFilename):

f = open(filename, 'rb')

index = 0

buf = f.read()

f.close()

magic, labels = struct.unpack_from('>II' , buf , index)

index += struct.calcsize('>II')

labelArr = [0] * labels

#labelArr = [0] * 2000

for x in range(labels):

#for x in xrange(2000):

labelArr[x] = int(struct.unpack_from('>B', buf, index)[0])

index += struct.calcsize('>B')

save = open(saveFilename, 'w')

save.write(','.join(map(lambda x: str(x), labelArr)))

save.write('\n')

save.close()

print ('save labels success')

if __name__ == '__main__':

read_image('D:\data\\train-images-idx3-ubyte\\train-images.idx3-ubyte')

read_label('D:\data\\train-images-idx3-ubyte\\train-images.idx3-ubyte', 'D:\data\\train-images-idx3-ubytetest\label.txt')

通過上述腳本可以將MNIST數據集中的圖片轉出為圖片格式，用於查看圖片內容。

腳本下載與使用

• 有一個python腳本，可以自動下載相關數據。input_data.py。但是該腳本在執行的時候一直報錯：

• 錯誤內容：only integer scalar arrays can be converted to a scalar

• 解決方法：def _read32(bytestream）方法中的return numpy.frombuffer(bytestream.read(4), dtype=dt)改為return numpy.frombuffer(bytestream.read(4), dtype=dt)[0] 說是因為最新版本的Numpy有所變動導致。

• 腳本內容：

# 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

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)[0]

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 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

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

引入上述腳本，可以對手寫圖片做一些簡單的測試，測試腳本如下：

import input_data

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

import tensorflow as tf

sess = tf.InteractiveSession()

x = tf.placeholder("float", shape=[None, 784])

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

print(x)

print(y_)

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

b = tf.Variable(tf.zeros([10]))

sess.run(tf.initialize_all_variables())

y = tf.nn.softmax(tf.matmul(x,W) + b)

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

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

for i in range(1000):

batch = mnist.train.next_batch(50)

train_step.run(feed_dict={x: batch[0], y_: batch[1]})

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))