Tensorflow 1.x学习记录（五）：Dropout避免过拟合

from __future__ import print_function
import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer

# 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
    # here to dropout
    Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)  # 进行dropout来避免过拟合的情况
    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])  # 8x8
ys = tf.placeholder(tf.float32, [None, 10])

# add output layer
l1 = add_layer(xs,64,50,'l1',activation_function=tf.nn.tanh)  #使用tanh避免报错
prediction = add_layer(l1,50,10,'l2',activation_function=tf.nn.softmax)   #100个输入值输出10个

# 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(0.2).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)  #记录两个值

# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
    init = tf.initialize_all_variables()
else:
    init = tf.global_variables_initializer()
sess.run(init)
for i in range(100):
    # here to determine the keeping probability
    sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})
    if i % 10 == 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)

运行tensorboard图形界面：

conda activate python35  #进入anconda环境
D:
cd D:\A文档\PY编程\venv  #logs文件所在目录
tensorboard --logdir=logs #每次运行完成需删除logs文件，不然会在原图上覆盖

![加入Dropout前](https://img-blog.csdnimg.cn/20210401165829101.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl81MDkxNDk2MQ==,size_16,color_FFFFFF,t_70)


![加入Dropout后](https://img-blog.csdnimg.cn/20210401165310472.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl81MDkxNDk2MQ==,size_16,color_FFFFFF,t_70)