Dropout solve overfitting

# -*- coding: utf-8 -*-import tensorflow as tffrom sklearn.datasets import load_digitsfrom sklearn.cross_validation 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):    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)    if activation_function is None:        outputs = Wx_plus_b    else:        outputs = activation_function(Wx_plus_b)    tf.histogram_summary(layer_name + '/outputs', outputs)          # IMPORTANT    return outputsdef compute_accuracy(v_xs, v_ys):    global prediction    y_pre = sess.run(prediction, feed_dict={xs: v_xs})    correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(v_ys, 1))    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})    return  result# define placeholder for inputs to networkkeep_prob = tf.placeholder(tf.float32)xs = tf.placeholder(tf.float32, [None, 64])    # input: 8*8 = 64ys = tf.placeholder(tf.float32, [None, 10])    # output: 0~9l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)# error between prediction and real datacross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),                            reduction_indices=[1]))tf.scalar_summary('loss', cross_entropy)train_step = tf.train.GradientDescentOptimizer(0.6).minimize(cross_entropy)sess = tf.Session()merged = tf.merge_all_summaries()# summary writer goes heretrain_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):    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})  # keep 50%    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)