# TensorFlow利用dropout解決過擬合問題

在TensorFlow訓練樣本的資料中，有時會出現過擬合（overfiting）的問題，可以採取dropout的方法來解決，即隨機丟棄部分樣本。

下面是示例程式碼，通過tensorboard對結果進行了視覺化：

import tensorflow as tf
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
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):
with tf.name_scope('layer'):
with tf.name_scope('weights'):
W = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
with tf.name_scope('bias'):
b = tf.Variable(tf.zeros([1, out_size])   0.1, name='b')
with tf.name_scope('Wx_plus_b'):
Wx_plus_b = tf.matmul(inputs, W)   b
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
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32, [None, 64])  # 8x84
ys = tf.placeholder(tf.float32, [None, 10])
l1 = 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 data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
reduction_indices=[1]))
tf.summary.scalar('loss', cross_entropy)
sess = tf.Session()
merged = tf.summary.merge_all()
# summary writer goes in there
train_writer = tf.summary.FileWriter('logs2/train', sess.graph)
test_writer = tf.summary.FileWriter('log2/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})
# record los
if i % 50 == 0:
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})