python cnn代码详解图解_深度学习之卷积神经网络(CNN)详解与代码实现（二）

用Tensorflow实现卷积神经网络(CNN)

目录

1.踩过的坑(tensorflow)

2.tensorboard

3.代码实现(python3.5)

4.运行结果以及分析

1.踩过的坑(tensorflow)

上一章CNN中各个算法都是纯手工实现的，可能存在一些难以发现的问题，这也是准确率不高的一个原因，这章主要利用tensorflow框架来实现卷积神经网络，数据源还是cifar(具体下载见上一章)

在利用tensorflow框架实现CNN时，需要注意以下几点：

1.输入数据定义时，x只是起到占位符的作用(看不到真实值，只是为了能够运行代码，获取相应的tensor节点，这一点跟我们之前代码流程完全相反， 真正数据流的执行在session会话里)

x：输入数据，y_： 标签数据，keep_prob: 概率因子，防止过拟合。

定义，且是全局变量。

x = tf.placeholder(tf.float32, [None, 3072], name='x')

y_ = tf.placeholder(tf.float32, [None, 10], name='y_')

keep_prob = tf.placeholder(tf.float32)

后面在session里必须要初始化

sess.run(tf.global_variables_initializer())

在session run时必须要传得到该tensor节点含有参数值(x, y_, keep_prob)

train_accuracy = accuracy.eval(feed_dict={

x: batch[0], y_: batch[1], keep_prob: 1.0})

2.原始数据集标签要向量化；

例如cifar有10个类别，如果类别标签是 6 对应向量[0,0,0,0,0,1,0,0,0,0]

3.知道每一步操作的数据大小的变化，不然，报错的时候很难定位(个人认为这也是tensorflow的弊端，无法实时追踪定位)；

注意padding = 'SAME'和'VALID'的区别

padding = 'SAME' => Height_后 = Height_前/Strides 跟padding无关  向上取整

padding = 'VALID'=>  Height_后 = (Height_前 - Filter + 1)/Strides  向上取整

4.打印tensorboard流程图，可以直观看到每步操作数据大小的变化；

2. tensorboard

tensorboard就是一个数据结构流程图的可视化工具，通过tensorboard流程图，可以直观看到神经网络的每一步操作以及数据流的变化。

操作步骤：

1. 在session会话里加入如下代码，打印结果会在当前代码文件相同路径的tensorboard文件下，默认是

tf.summary.FileWriter("tensorboard/", sess.graph)

2. 在运行里输入cmd，然后输入(前提是安装好了tensorboard => pip install  tensorboard)

tensorboard --logdir=D:\Project\python\myProject\CNN\tensorflow\captchaIdentify\tensorboard --host=127.0.0.1

'D:\Project\python\myProject\CNN\tensorflow\captchaIdentify\tensorboard' 是我生成的tensorboard文件的绝对路径，你替换成你自己的就可以了。

正确运行后会显示 ‘Tensorboard at http://127.0.0.1:6006’，说明tensorboard服务已经起来了，在浏览器页面输入

http://127.0.0.1:6006即可显示流程图。

3.代码实现(python3.6)

代码逻辑实现相对比较简单，在一些重要逻辑实现上，我已做了注释，如果大家有什么疑义，可以留言给我，我们一起交流。

因为原始图片数据集太大，不好上传，大家可以直接在http://www.cs.toronto.edu/~kriz/cifar.html下载CIFAR-10 python version，

有163M，放在代码文件同路径下即可。

cifar放置路径

start.py

1 #coding=utf-8

2 #Disable linter warnings to maintain consistency with tutorial.

3 #pylint: disable=invalid-name

4 #pylint: disable=g-bad-import-order

5 from __future__ importabsolute_import6 from __future__ importdivision7 from __future__ importprint_function8 importargparse9 importsys10 importtempfile11 #from tensorflow.examples.tutorials.mnist import input_data

12 importtensorflow as tf13 '''

14 卷积神经网络实现10类(airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck)15 60000张图片的识别16 5000次，准确率有 58%；17 20000次，准确率有 68.89%；18 相比mnist数字图片识别准确度低，原因有：19 mnist训练图片是灰度图片，纹理简单，数字的可变性小，而cifar是彩色图片，纹理复杂，动物可变性大；20 '''

21 try:22 from . importdatesets23 exceptException:24 importdatesets25

26 FLAGS =None27

28 defdeepnn(x):29 with tf.name_scope('reshape'):30 x_image = tf.reshape(x, [-1, 32, 32, 3])31 ## 第一层卷积操作 ##

32 with tf.name_scope('conv1'):33 W_conv1 = weight_variable([5, 5, 3, 32])34 b_conv1 = bias_variable([32])35 h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) +b_conv1)36

37 with tf.name_scope('pool1'):38 h_pool1 =max_pool_2x2(h_conv1)39

40 #Second convolutional layer -- maps 32 feature maps to 64.

41 ## 第二层卷积操作 ##

42 with tf.name_scope('conv2'):43 W_conv2 = weight_variable([5, 5, 32, 64])44 b_conv2 = bias_variable([64])45 h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) +b_conv2)46

47 with tf.name_scope('pool2'):48 h_pool2 =max_pool_2x2(h_conv2)49

50 ## 第三层全连接操作 ##

51 with tf.name_scope('fc1'):52 W_fc1 = weight_variable([8 * 8 * 64, 1024])53 b_fc1 = bias_variable([1024])54 h_pool2_flat = tf.reshape(h_pool2, [-1, 8 * 8 * 64])55 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) +b_fc1)56

57 with tf.name_scope('dropout'):58 keep_prob =tf.placeholder(tf.float32)59 h_fc1_drop =tf.nn.dropout(h_fc1, keep_prob)60

61 ## 第四层输出操作 ##

62 with tf.name_scope('fc2'):63 W_fc2 = weight_variable([1024, 10])64 b_fc2 = bias_variable([10])65 y_conv = tf.matmul(h_fc1_drop, W_fc2) +b_fc266 returny_conv, keep_prob67

68 defconv2d(x, W):69 return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')70

71 defmax_pool_2x2(x):72 return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],73 strides=[1, 2, 2, 1], padding='SAME')74

75 defweight_variable(shape):76 initial = tf.truncated_normal(shape, stddev=0.1)77 returntf.Variable(initial)78

79 defbias_variable(shape):80 initial = tf.constant(0.1, shape=shape)81 returntf.Variable(initial)82

83 defmain(_):84 #Import data

85 mnist = datesets.read_data_sets(train_dir = '.\\cifar-10-batches-py\\', one_hot=True)86

87 #Create the model

88 #声明一个占位符，None表示输入图片的数量不定，28*28图片分辨率

89 x = tf.placeholder(tf.float32, [None, 3072], name='x')90

91 #类别是0-9总共10个类别，对应输出分类结果

92 y_ = tf.placeholder(tf.float32, [None, 10], name='y_')93 y_conv, keep_prob =deepnn(x)94 #通过softmax-loss求交叉熵

95 with tf.name_scope('loss'):96 cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)97 #求均值

98 cross_entropy =tf.reduce_mean(cross_entropy)99 #计算梯度，更新参数值

100 with tf.name_scope('adam_optimizer'):101 train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)102

103 with tf.name_scope('accuracy'):104 correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))105 correct_prediction =tf.cast(correct_prediction, tf.float32)106 accuracy =tf.reduce_mean(correct_prediction)107

108 #graph_location = tempfile.mkdtemp()

109 #print('Saving graph to: %s' % graph_location)

110 #train_writer.add_graph(tf.get_default_graph())

111

112 with tf.Session() as sess:113 #打印流程图

114 writer = tf.summary.FileWriter("tensorboard/", sess.graph)115 sess.run(tf.global_variables_initializer())116 for i in range(20000):117 batch = mnist.train.next_batch(50)118 if i % 1000 ==0:119 train_accuracy = accuracy.eval(feed_dict={120 x: batch[0], y_: batch[1], keep_prob: 1.0})121 print('step %d, training accuracy %g' %(i, train_accuracy))122 train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})123

124 print('test accuracy %g' % accuracy.eval(feed_dict={125 x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))126

127 if __name__ == '__main__':128 parser =argparse.ArgumentParser()129 parser.add_argument('--data_dir', type=str,130 default='/tmp/tensorflow/mnist/input_data',131 help='Directory for storing input data')132 FLAGS, unparsed =parser.parse_known_args()133 tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

View Code

datasets.py

1 importnumpy2 from tensorflow.python.framework importdtypes3 from tensorflow.python.framework importrandom_seed4 from six.moves importxrange5 from tensorflow.contrib.learn.python.learn.datasets importbase6 importpickle7 importos8

9 classDataSet(object):10 """Container class for a dataset (deprecated).11

12 THIS CLASS IS DEPRECATED. See13 [contrib/learn/README.md](https://www.tensorflow.org/code/tensorflow/contrib/learn/README.md)14 for general migration instructions.15 """

16 def __init__(self,17 images,18 labels,19 fake_data=False,20 one_hot=False,21 dtype=dtypes.float32,22 reshape=True,23 seed=None):24 """Construct a DataSet.25 one_hot arg is used only if fake_data is true. `dtype` can be either26 `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into27 `[0, 1]`. Seed arg provides for convenient deterministic testing.28 """

29 seed1, seed2 =random_seed.get_seed(seed)30 #If op level seed is not set, use whatever graph level seed is returned

31 numpy.random.seed(seed1 if seed is None elseseed2)32 dtype =dtypes.as_dtype(dtype).base_dtype33 if dtype not in(dtypes.uint8, dtypes.float32):34 raiseTypeError(35 'Invalid image dtype %r, expected uint8 or float32' %dtype)36 iffake_data:37 self._num_examples = 10000

38 self.one_hot =one_hot39 else:40 assert images.shape[0] ==labels.shape[0], (41 'images.shape: %s labels.shape: %s' %(images.shape, labels.shape))42 self._num_examples =images.shape[0]43

44 #Convert shape from [num examples, rows, columns, depth]

45 #to [num examples, rows*columns] (assuming depth == 1)

46 ifreshape:47 assert images.shape[3] == 3

48 images =images.reshape(images.shape[0],49 images.shape[1] * images.shape[2] * images.shape[3])50 if dtype ==dtypes.float32:51 #Convert from [0, 255] -> [0.0, 1.0].

52 images =images.astype(numpy.float32)53 images = numpy.multiply(images, 1.0 / 255.0)54 self._images =images55 self._labels =labels56 self._epochs_completed =057 self._index_in_epoch =058

59 @property60 defimages(self):61 returnself._images62

63 @property64 deflabels(self):65 returnself._labels66

67 @property68 defnum_examples(self):69 returnself._num_examples70

71 @property72 defepochs_completed(self):73 returnself._epochs_completed74

75 def next_batch(self, batch_size, fake_data=False, shuffle=True):76 """Return the next `batch_size` examples from this data set."""

77 iffake_data:78 fake_image = [1] * 784

79 ifself.one_hot:80 fake_label = [1] + [0] * 9

81 else:82 fake_label =083 return [fake_image for _ inxrange(batch_size)], [84 fake_label for _ inxrange(batch_size)85 ]86 start =self._index_in_epoch87 #Shuffle for the first epoch

88 if self._epochs_completed == 0 and start == 0 andshuffle:89 perm0 =numpy.arange(self._num_examples)90 numpy.random.shuffle(perm0)91 self._images =self.images[perm0]92 self._labels =self.labels[perm0]93 #Go to the next epoch

94 if start + batch_size >self._num_examples:95 #Finished epoch

96 self._epochs_completed += 1

97 #Get the rest examples in this epoch

98 rest_num_examples = self._num_examples -start99 images_rest_part =self._images[start:self._num_examples]100 labels_rest_part =self._labels[start:self._num_examples]101 #Shuffle the data

102 ifshuffle:103 perm =numpy.arange(self._num_examples)104 numpy.random.shuffle(perm)105 self._images =self.images[perm]106 self._labels =self.labels[perm]107 #Start next epoch

108 start =0109 self._index_in_epoch = batch_size -rest_num_examples110 end =self._index_in_epoch111 images_new_part =self._images[start:end]112 labels_new_part =self._labels[start:end]113 returnnumpy.concatenate(114 (images_rest_part, images_new_part), axis=0), numpy.concatenate(115 (labels_rest_part, labels_new_part), axis=0)116 else:117 self._index_in_epoch +=batch_size118 end =self._index_in_epoch119 returnself._images[start:end], self._labels[start:end]120

121 defread_data_sets(train_dir,122 one_hot=False,123 dtype=dtypes.float32,124 reshape=True,125 validation_size=5000,126 seed=None):127

128

129

130

131 train_images,train_labels,test_images,test_labels =load_CIFAR10(train_dir)132 if not 0 <= validation_size <=len(train_images):133 raise ValueError('Validation size should be between 0 and {}. Received: {}.'

134 .format(len(train_images), validation_size))135

136 validation_images =train_images[:validation_size]137 validation_labels =train_labels[:validation_size]138 validation_labels = dense_to_one_hot(validation_labels, 10)139 train_images =train_images[validation_size:]140 train_labels =train_labels[validation_size:]141 train_labels = dense_to_one_hot(train_labels, 10)142

143 test_labels = dense_to_one_hot(test_labels, 10)144

145 options = dict(dtype=dtype, reshape=reshape, seed=seed)146 train = DataSet(train_images, train_labels, **options)147 validation = DataSet(validation_images, validation_labels, **options)148 test = DataSet(test_images, test_labels, **options)149

150 return base.Datasets(train=train, validation=validation, test=test)151

152

153 defload_CIFAR_batch(filename):154 """load single batch of cifar"""

155 with open(filename, 'rb') as f:156 datadict = pickle.load(f, encoding='bytes')157 X = datadict[b'data']158 Y = datadict[b'labels']159 X = X.reshape(10000, 3, 32, 32).transpose(0,2,3,1).astype("float")160 Y =numpy.array(Y)161 returnX, Y162

163 defload_CIFAR10(ROOT):164 """load all of cifar"""

165 xs =[]166 ys =[]167 for b in range(1,6):168 f = os.path.join(ROOT, 'data_batch_%d' %(b, ))169 X, Y =load_CIFAR_batch(f)170 xs.append(X)171 ys.append(Y)172 Xtr =numpy.concatenate(xs)173 Ytr =numpy.concatenate(ys)174 delX, Y175 Xte, Yte = load_CIFAR_batch(os.path.join(ROOT, 'test_batch'))176 returnXtr, Ytr, Xte, Yte177

178 defdense_to_one_hot(labels_dense, num_classes):179 """Convert class labels from scalars to one-hot vectors."""

180 num_labels =labels_dense.shape[0]181 index_offset = numpy.arange(num_labels) *num_classes182 labels_one_hot =numpy.zeros((num_labels, num_classes))183 labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1

184 return labels_one_hot

View Code

4.运行结果以及分析

这里选取55000张图片作为训练样本，测试样本选取5000张。

tensorboard可视流程图

运行5000次，测试准确率：58%

运行20000次，测试准确率：68.89%

运行40000次，测试准确率71.95%

分析：由最后一张图片可以看出，20000 - 30000次时测试准确率=> 70.27% ->71.44%，30000 - 40000次时=> 71.44% -> 71.95%

而训练准确率已经达到100%，说明测试准确率已经趋于一个稳定值，再增加训练次数，测试准确率提高的可能性不大。

如果想要继续提高测试准确率，就只能增加训练样本。

不要让懒惰占据你的大脑，不要让妥协拖垮了你的人生。青春就是一张票，能不能赶上时代的快车，你的步伐就掌握在你的脚下。