tensorflow之dropout解决过拟合问题

dropout解决过拟合问题，对于hiton提出的dropout，我看过两篇文章解释比较详细，也有自己的理解，想要了解原理可以参看
http://blog.csdn.net/stdcoutzyx/article/details/49022443
https://yq.aliyun.com/articles/68901
这篇文章主要讲解在tensorflow中如何使用dropout方法来解决过拟合问题，具体的程序实现如下：

#encoding=utf-8
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import LabelBinarizer
# 加载数据
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)
#添加层
def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):
    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
    # dropout功能，keep_prob表示保留计算结果的百分比
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b, ) 
        tf.histogram_summary(layer_name + '/outputs', outputs)#变量跟踪
        return outputs
# 输入
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])
#添加隐藏层和输出层
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)
# 误差
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys *tf.log(prediction),reduction_indices=[1])) tf.scalar_summary('loss', cross_entropy)#误差跟踪
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()
merged = tf.merge_all_summaries()
#训练和测试误差的summary存储文件夹
train_writer = tf.train.SummaryWriter("logs/train", sess.graph)
test_writer = tf.train.SummaryWriter("logs/test", sess.graph)
sess.run(tf.initialize_all_variables())
for i in range(500):
    # dropout的保留百分比为0.5
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})#训练
    if i % 50 == 0:
        # record loss
        train_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})
        test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})
        train_writer.add_summary(train_result, i)
        test_writer.add_summary(test_result, i)