tensorflow 学习笔记8 dropout

    dropout用于解决过拟合问题。打个比方Dropout类似于性别在生物进化中的角色：物种为了生存往往会倾向于适应这种环境，环境突变则会导致物种难以做出及时反应，性别的出现可以繁衍出适应新环境的变种，有效的阻止过拟合，即避免环境改变时物种可能面临的灭绝。代码例子是sklearn数据集进行简单训练后的模型：

import tensorflow as tffrom sklearn.datasets import load_digitsfrom sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import LabelBinarizer# load datadigits = load_digits()X = digits.datay = digits.targety = 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    # here to dropout    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.summary.histogram(layer_name + '/outputs', outputs)    return outputs# define placeholder for inputs to network#保持多少的结果不被dropout掉keep_prob = tf.placeholder(tf.float32)xs = tf.placeholder(tf.float32, [None, 64])  # 8x8ys = tf.placeholder(tf.float32, [None, 10])# add output layerl1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)# the loss between prediction and real datacross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),                                              reduction_indices=[1]))  # losstf.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 heretrain_writer = tf.summary.FileWriter("桌面/logs/train", sess.graph)test_writer = tf.summary.FileWriter("桌面/logs/test", sess.graph)# tf.initialize_all_variables() no long valid frominit = tf.global_variables_initializer()sess.run(init)for i in range(500):    # here to determine the keeping probability，50%dropout掉    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})    if i % 50 == 0:        # record loss，记录的时候不需要dropout掉任何东西        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)

在终端执行：

tensorboard --logdir=~/桌面/logs

tensorboard可视化loss（橘色：testing sets 绿色：training sets）：

如果不用dropout就会出现过拟合，training sets效果特别好，而testing sets效果就不行了，这就是训练集训练的时候出现过拟合，对于测试集测试的时候误差就比较大，结果如下：