# coding=utf-8
import tensorflow as tf
#导入数据集
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
#加载数据0-9的数字data
digits = load_digits()
X = digits.data
y = digits.target
#获取y并将其转化为binary类型label(若数字为2则在索引为2的位置置1)
y = LabelBinarizer().fit_transform(y)
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
#定义层
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操作
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)
return outputs
#定义输入层的placeholder
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32,[None,64])#8x8
ys = tf.placeholder(tf.float32,[None,10])
#添加输出层,隐藏层神经元数可能太多会导致tensorboard输出离散值
l1 = add_layer(xs,64,50,'l1',activation_function=tf.nn.tanh)
prediction = add_layer(l1,50,10,'l2',activation_function=tf.nn.softmax)
#计算交叉熵,计算公式为H(p.q)=-sum(p(x)logq(x)),其中p为期望输出,q为实际输出
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(prediction),reduction_indices=[1]))
tf.summary.scalar('loss',cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
merged = tf.summary.merge_all()
#记录两个summary,train&test
train_writer = tf.summary.FileWriter("logs/train",sess.graph)
test_writer = tf.summary.FileWriter("logs/test",sess.graph)
#训练
for i in range(500):
sess.run(train_step,feed_dict={xs:X_train,ys:y_train,keep_prob:0.5})
if i%50 ==0:
train_result = sess.run(merged,feed_dict={xs:X_train,ys:y_train,keep_prob:1})
test_refult = 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_refult,i)