平台信息:

PC：ubuntu18.04、i5、anaconda2、cuda9.0、cudnn7.0.5、tensorflow1.10、GTX1060

作者：庄泽彬(欢迎转载，请注明作者)

说明:本文是在tensorflow社区的学习笔记，MNIST 手写数据入门demo

一、MNIST数据的下载，使用代码的方式：

input_data.py文件内容：

# 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_importfrom __future__ import divisionfrom __future__ import print_functionimport gzipimport osimport numpyfrom six.moves import urllibfrom six.moves import xrange  # pylint: disable=redefined-builtinSOURCE_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 filepathdef _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 datadef 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_hotdef 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 labelsclass 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

新建test.py调用input_data.py进行下载手写识别的数据

#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Thu Oct 11 23:10:15 2018@author: zhuang"""import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

注意test.py与input_data.py要放在同一个目录下，运行test.py之后会在当前目录生成MNIST_data/  存放下载的数据，下载的内容如下图

二、使用tensorflow构建模型进行训练

新建mnist-test.py内容如下：

#!/usr/bin/env python2# -*- coding: utf-8 -*-"""Created on Fri Oct 12 11:43:37 2018@author: zhuang"""import input_dataimport tensorflow as tfmnist = input_data.read_data_sets("MNIST_data/", one_hot=True)x = tf.placeholder("float",[None,784])w = tf.Variable(tf.zeros([784,10]))b = tf.Variable(tf.zeros([10]))y = tf.nn.softmax(tf.matmul(x,w)+b)# 计算交叉熵y_ = tf.placeholder("float",[None,10])cross_entropy = -tf.reduce_sum(y_*tf.log(y))#梯度下降算法，以0.01的学习率更新参数train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)init = tf.initialize_all_variables()sess = tf.Session()sess.run(init)#训练模型1000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})#评估模型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})

我们构建的模型手写识别的准确率在91%z左右