import tensorflow as tf#导包
tf.name_scope:定义操作名称
with tf.name_scope('Weights'): #操作名称
Weights=tf.Variable(tf.random_normal([in_size,out_size]),name='W')
记录weights变化情况
tf.summary.histogram(layer_name+'/Weights',Weights)
定义占位符:
tf.placeholder(tf.float32,[None,1],name='x_input')
存储网络结构:
tf.summary.FileWriter('logs/', sess.graph)# 将网络结构图存储
合并所有summary
tf.summary.merge_all()
记录描点
rs=sess.run(merged, feed_dict={xs: x_data, ys: y_data})
writer.add_summary(rs,i) #每隔50步记录一个点
完整代码
import tensorflow as tf
import numpy as np
import matplotlib as mpl
mpl.use('TkAgg')
import matplotlib.pyplot as plt
def add_layer(input,in_size,out_size,n_layer,activation_function=None):
layer_name='layer%s'%n_layer
with tf.name_scope(layer_name):
with tf.name_scope('Weights'): #操作名称
Weights =tf.Variable(tf.random_normal([in_size,out_size]),name='W')# random_normal=>随机变量
tf.summary.histogram(layer_name+'/Weights',Weights)# 记录weight的变化情况
with tf.name_scope('biases'):
biases =tf.Variable(tf.zeros([1,out_size])+0.1,name='b')
tf.summary.histogram(layer_name + '/biases', biases)
with tf.name_scope('Wx_plus_b'):
Wx_plus_b=tf.matmul(input,Weights)+biases
if activation_function is None:
output= Wx_plus_b
else:
output=activation_function(Wx_plus_b)
tf.summary.histogram(layer_name + '/output', output)
return output
x_data =np.linspace(-1,1,300)[:,np.newaxis]
noise= np.random.normal(0,0.05,x_data.shape)
y_data =np.square(x_data)+noise
with tf.name_scope('inputs'):
xs=tf.placeholder(tf.float32,[None,1],name='x_input')
ys=tf.placeholder(tf.float32,[None,1],name='y_input')
l1=add_layer(xs,1,10,1,activation_function=tf.nn.relu)
prediction=add_layer(l1,10,1,n_layer=2,activation_function=None)
#prediction =add_layer(l1,10,1,activation_function=None)
with tf.name_scope('loss'):
loss =tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),
reduction_indices=[1]),name='mse')
tf.summary.scalar('loss', loss)
with tf.name_scope('train'):
train_step =tf.train.GradientDescentOptimizer(learning_rate=0.01)\
.minimize(loss)
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data, y_data)
plt.ion()
plt.show()
init =tf.initialize_all_variables()
with tf.Session() as sess:
writer = tf.summary.FileWriter('logs/', sess.graph)# 将网络结构图存储
merged = tf.summary.merge_all() #合并所有的summary
sess.run(init)
"""for i in range(1000):
sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
if i%50==0:
print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
prediction_value =sess.run(prediction,feed_dict={xs:x_data})
plt.plot(x_data,prediction_value,'r-',lw=5)
plt.show()
plt.pause(0.1)"""
for i in range(1000):
# training
sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
if i % 50 == 0:
# to visualize the result and improvement
rs=sess.run(merged, feed_dict={xs: x_data, ys: y_data})
writer.add_summary(rs,i) #每隔50步记录一个点
try:
ax.lines.remove(lines[0])
except Exception:
pass
prediction_value = sess.run(prediction, feed_dict={xs: x_data})
# plot the prediction
lines = ax.plot(x_data, prediction_value, 'r-', lw=5)
plt.pause(0.5)
参考:https://morvanzhou.github.io/tutorials/machine-learning/tensorflow