pythoncnn代码详解图解_深度学习之卷积神经⽹络（CNN） ⽤Tensorflow实现卷积神经⽹络(CNN)
⽬录
1.踩过的坑(tensorflow)
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。
钢丝绳卷筒
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
剖分式骨架油封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
投注系统
tf.summary.FileWriter("tensorboard/", aph)
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。
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。
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_import
步进式加热炉
6 from __future__ importdivision
7 from __future__ importprint_function
8 importargparse
9 importsys10 importtempfile11 #ist 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 = lu(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 = lu(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 = lu(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 v2d(x, W, strides=[1, 1, 1, 1], padding='SAME')70
71 defmax_pool_2x2(x):72 ax_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 = ad_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__default_graph())
111
112 with tf.Session() as sess:113 #打印流程图
114 writer = tf.summary.FileWriter("tensorboard/", aph)115 sess.run(tf.global_variables_initializer())116 for i in range(20000):117 batch = _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: st.images, y_: st.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 importnumpy
2 from tensorflow.python.framework importdtypes
3 from tensorflow.python.framework
importrandom_seed4 ves importxrange5 ib.learn.python.learn.datasets importbase6 importpickle7 importos8
9 classDataSet(object):10 """Container class for a dataset (deprecated).11
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 =_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
_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
光触媒滤网
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 =shape(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
_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]atenate(114 (images_rest_part, images_new_part), axis=0), atenate(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管道渗漏检测
<=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 =atenate(xs)173 Ytr
=atenate(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
=s((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。
豫公网安备41160202000603
站长QQ:729038198
关于我们
投诉建议