【tensorflow入门】13、dropout解决过拟合overfit

内心os：后期还需补代码。

一、使用原因： 当训练集不足够大时，过度学习会导致学习到的模型对本数据集几乎100%契合，但对别的符合条件的数据却无法get到。

训练深度神经网络的时候，总是会遇到两大缺点：

（1）容易过拟合

（2）费时

Dropout可以比较有效的缓解过拟合的发生，在一定程度上达到正则化的效果。

二、dropout：

其实就是让一部分神经元停止工作，避免神经网络获得的参数过多，导致结果过拟合。

三、代码：

import tensorflow as tf
from sklearn.datasets import load_digits
# from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split


# load data
digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)


def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    # add one more layer and return the output of this layer
    Weights = tf.Variable(tf.random_normal([in_size, out_size]))
    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )
    Wx_plus_b = tf.matmul(inputs, Weights) + biases
    Wx_plus_b = tf.nn.dropout(Wx_plus_b,keep_prob)  #加这行~~

    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, )
    tf.summary.histogram(layer_name + '/outputs', outputs)#不加这句有可能总报错
    return outputs


# define placeholder for inputs to network
keep_prob = tf.placeholder(tf.float32)  # 要保持多少的结果不被dropout掉（keep probablity）
xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs,64,50,'l1',activation_function=tf.nn.tanh)  #100改成50，数量太多容易报错
prediction = add_layer(l1,50,10,'l2',activation_function=tf.nn.softmax)


# the loss between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
tf.summary.scalar('loss', cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
merged = tf.summary.merge_all()
# summary writer goes in here
train_writer = tf.summary.FileWriter("logs/train",sess.graph)
test_writer = tf.summary.FileWriter("logs/test",sess.graph)


sess.run(tf.global_variables_initializer())

for i in range(500):
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train,keep_prob:0.5}) #50%被drop掉  若40%，则写0.6（保持60%的概率不被drop掉）
    if i % 50 == 0:
        # record loss
        train_result = sess.run(merged,feed_dict={xs:X_train,ys:y_train,keep_prob:1})#因为记录result过程中我不要drop掉任何东西
        test_result = sess.run(merged,feed_dict={xs:X_test,ys:y_test,keep_prob:0.5})

        #加载到summary的FileWriter之中
        train_writer.add_summary(train_result,i)  #第i次学习
        test_writer.add_summary(test_result,i)
    

效果：

 

目前我还看不太懂这意味着什么，希望后期我能深入的理解。立个flag~