深度学习之MNIST数据集的导入

实例描述:
从MNIST数据集中选择一副图,这幅图上有一个手写的数字,让机器模拟人眼来区分这个手写的数字到底是几。
实现步骤:
(1)导入MNIST数据集;
(2)分析MNIST样本特点定义变量;
(3)构建模型;
(4)训练模型并输出中间状态参数;
(5)测试模型;
(6)保存模型;
(7)读取模型;
使用工具:
操作系统win7, Spyder(Anaconda3),
准备工作:
若想实现实例功能,必须先导入MNIST数据集。MNIST数据集是一个入门级的计算机视觉数据集。其基础程度,相当于学编程时第一件事往往是学习打印Hello World。数据集里包含各种手写数字图片,可通过编写以下代码,自动下载数据集并解压到自定义的目录下。

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("D:/Anaconda3Project/MNIST_data/", one_hot=True)
# 路径为自定义,可根据实际情况选择数据集存放路径
# one_hot=True,表示将样本标签转化为one_hot编码。例如:一共10类,0的one_hot为1000000000,1的one_hot为0100000000.......以此类推,只有一个位为1,1所在的位置就代表着第几类。

但在实际操作中,自动下载并不能成功,会出现下面的错误:
在这里插入图片描述
所以,采用第二种方法,手动导入。在MNIST数据集官网[http://yann.lecun.com/exdb/mnist/]手动下载数据集。如图:

左下角四行红色链接依次下载即可,切记,不要解压!不要解压!不要解压!
将四个压缩包放在和你代码同级的目录下,比如:我把“MNIST数据集测试.py”文件存放在“D:/Anaconda3Project/”下,那么将四个压缩包也放在“D:/Anaconda3Project/”下,如图:
在这里插入图片描述
这还没完,还需要将如下代码命名为input_data.py。

# 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 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/'
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, one_hot=False,
               dtype=tf.float32):
    """Construct a DataSet.
    one_hot arg is used only if fake_data is true.  `dtype` can be either
    `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
    `[0, 1]`.
    """
    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]
      # 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])
      if dtype == tf.float32:
        # 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] * 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
    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, dtype=tf.float32):
  class DataSets(object):
    pass
  data_sets = DataSets()
  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
  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, 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

if __name__ == '__main__':
    path = "D:/Anaconda3Project/MNIST_data/"
    read_data_sets(path)

这串代码也是网上找的,只需要将倒数第二行的path路劲改为自己想要解压到的位置即可,我把它设置成和自动下载时自定义路径相同。然后将这串命名为input_data.py文件存放在自己安装的Anaconda程序文件的Lib文件下,如图:
在这里插入图片描述
此时,为防止导入失败,可以将input_data.py放在和自己编写的.py文件同级目录下,如图:
在这里插入图片描述
现在,应该就不会出现导入错误了,可以进行导入并验证,代码如下:

import input_data   # 此时的导入只需要这么写就可以
mnist = input_data.read_data_sets("D:/Anaconda3Project/MNIST_data/", one_hot=True)
print('输入数据:',mnist.train.images)   # 输出图片数据
print('训练数据集shape:',mnist.train.images.shape)   # 输出训练数据集里图片个数
import pylab
im = mnist.train.images[1]    # 导出数据集中第一幅图片
im = im.reshape(-1,28)   # 将图片的shape变为计算机计算行数,自己定义列数为28列
pylab.imshow(im)
pylab.show()
print('测试数据集shape:',mnist.test.images.shape)   # 输出测试数据集里图片个数
print('验证数据集shape:',mnist.validation.images.shape)   # 输出验证数据集里图片个数

结果为下图:
图一:
在这里插入图片描述
图二:
在这里插入图片描述
从图一可以看到四个压缩包被依次提取,而且可以看到训练集打印出来的信息为一个55000行,784列的矩阵。即,训练集中有55000张图片。并且测试数据集里有10000条样本图片,验证数据集里有5000个图片。图二展示了训练集中的第一幅图片。全部显示,说明导入成功。
路漫漫其修远兮,吾将上下而求索。
这只是MNIST数据集训练的第一步,深度学习才刚刚开始!

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值