tensorflow学习4-过拟合-over-fitting

  1 import tensorflow as tf 
  2 from sklearn.datasets import load_digits #从sklearn的数据集引入手写字体数据集
  3 from sklearn.model_selection import train_test_split # 作用：将数据集划分为 训练集和测试集
  4 from sklearn.preprocessing import LabelBinarizer  #数据的预处理
  5 #binarizer二值化
  6 
  7 
  8 ‘‘‘数据下载‘‘‘
  9 
 10 digits=load_digits() #导入手写字体的datasets
 11 X=digits.data  #获得其特征向量 
 12 y=digits.target  #获得样本label
 13 y=LabelBinarizer().fit_transform(y) #二值化[0,1,1....]
 14 ‘‘‘扩展sklearn.proprocessing.LabelBinarizer().fit_transform()‘‘‘
 15     #lb=preprocessing.LabelBinarizer()
 16     #>>> lb.fit_transform([‘yes‘, ‘no‘, ‘no‘, ‘yes‘])
 17     #array([[1],
 18     #       [0],
 19     #       [0],
 20     #       [1]])
 21 X_train,X_test,y_train,y_test =train_test_split(X,y,test_size=.3)
 22 # test_size：float-获得多大比重的测试样本 （默认：0.25）---int - 获得多少个测试样本
 23 #数据集被划分为训练集和测试集,label必须二值化因为分类的结果就是binarizer
 24 
 25       
 26 ‘‘‘生成层 函数‘‘‘
 27 def add_layer(input,in_size,out_size,n_layer=‘layer‘,activation_function=None):
 28     layer_name=‘layer %s‘ % n_layer
 29     ‘‘‘补充知识‘‘‘
 30     #tf.name_scope:Wrapper for Graph.name_scope() using the default graph.
 31     #scope名字的作用域
 32     #sprase:A string (not ending with ‘/‘) will create a new name scope, in which name is appended to the prefix of all operations created in the context. 
 33     #If name has been used before, it will be made unique by calling self.unique_name(name).
 34     with tf.name_scope(‘weights‘):
 35         Weights=tf.Variable(tf.random_normal([in_size,out_size]),name=‘w‘)
 36         tf.summary.histogram(layer_name+‘/wights‘,Weights)
 37         #tf.summary.histogram:output summary with histogram直方图
 38         #tf,random_normal正太分布
 39     with tf.name_scope(‘biases‘):
 40         biases=tf.Variable(tf.zeros([1,out_size])+0.1)
 41         tf.summary.histogram(layer_name+‘/biases‘,biases)
 42         #tf.summary.histogram:k
 43     with tf.name_scope(‘Wx_plus_b‘):
 44         Wx_plus_b=tf.matmul(input,Weights)+biases
 45         ‘‘‘引入dropout,dropout添加在每一层的激活函数前‘‘‘
 46         Wx_plus_b=tf.nn.dropout(Wx_plus_b,keep_prob)
 47         #keep_prob 每个元素被留下来的概率
 48     if activation_function==None:
 49         outputs=Wx_plus_b
 50     else:
 51         outputs=activation_function(Wx_plus_b)
 52     tf.summary.histogram(layer_name+‘/output‘,outputs)
 53     return outputs
 54 ‘‘‘准确率‘‘‘
 55 
 56 ‘‘‘占位符‘‘‘
 57 keep_prob = tf.placeholder(tf.float32)
 58 xs=tf.placeholder(tf.float32,[None,64])
 59 ys=tf.placeholder(tf.float32,[None,10])
 60 
 61 ‘‘‘添加层‘‘‘
 62 l1=add_layer(xs,64,50,‘l1‘,activation_function=tf.nn.softmax ) #据说其他激活函数会出错
 63 prediction=add_layer(l1,50,10,activation_function=tf.nn.softmax)
 64 #sotmax激活函数，用于分类函数
 65 
 66 ‘‘‘计算‘‘‘
 67 #交叉熵cross_entropy损失函数，参数分别为实际的预测值和实际的label值y，re
 68 ‘‘‘补充知识‘‘‘
 69 #reduce_mean()
 70 # ‘x‘ is [[1., 1. ]]
 71 #         [2., 2.]]
 72 #tf.reduce_mean(x) ==> 1.5
 73 #tf.reduce_mean(x, 0) ==> [1.5, 1.5]
 74 #tf.reduce_mean(x, 1) ==> [1.,  2.]
 75 cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
 76 tf.summary.scalar(‘loss‘,cross_entropy)
 77 ‘‘‘补充知识‘‘‘
 78 #reduce_sum
 79 # ‘x‘ is [[1, 1, 1]]
 80 #         [1, 1, 1]]
 81 #tf.reduce_sum(x) ==> 6
 82 #tf.reduce_sum(x, 0) ==> [2, 2, 2]
 83 #tf.reduce_sum(x, 1) ==> [3, 3]
 84 #tf.reduce_sum(x, 1, keep_dims=True) ==> [[3], [3]]
 85 #tf.reduce_sum(x, [0, 1]) ==> 6
 86 train_step=tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
 87 merged=tf.summary.merge_all()
 88 ‘‘‘Session_begin‘‘‘
 89 with tf.Session() as sess:
 90     
 91     #merged:tf.summary.merge_all:Merges all summaries collected in the default graph.
 92     print("merged initialize sunccessfulliy")
 93     train_writer=tf.summary.FileWriter(‘logs/train‘,sess.graph)
 94     print("train_writer initialize sunccessfulliy")
 95     test_writer=tf.summary.FileWriter(‘logs/test‘,sess.graph)
 96     print("test_writer  initialize sunccessfulliy")
 97     sess.run(tf.global_variables_initializer())
 98     print("variables initialize sunccessfulliy")
 99     for i in range(1000):
100         #batch_xs,batch_ys=mnist.train.next_batch(100) #逐个batch去取数据
101         sess.run(train_step,feed_dict={xs:X_train,ys:y_train,keep_prob:0.6})
102         if(i%50==0):
103             #print(compute_accuracy(mnist.test.images,mnist.test.labels))
104             #train_result=sess.run(merged,feed_dict={xs:X_train,ys:y_train,keep_prob:1})
105             #test_result=sess.run(merged,feed_dict={xs:X_test,ys:y_test,keep_prob:1})
106             #train_writer.add_summary(train_result,i)
107             #test_writer.add_summary(test_result,i)
108             print(sess.run(cross_entropy,feed_dict={xs:X_test,ys:y_test,keep_prob:1}))
109             print("the {}".format(i))
110