莫烦Python12例子结果可视化

# coding: utf-8  
import tensorflow as tf
import numpy as np
import time
import matplotlib.pyplot as plt
def add_layer(inputs, in_size, out_size, activation_function=None):##w*x+b
  Weights=tf.Variable(tf.random_normal([in_size,out_size]))
  bias=tf.Variable(tf.zeros([1,out_size])+0.1)
  Wx_plus_b=tf.matmul(inputs,Weights)+bias
  if activation_function is None:
    output=Wx_plus_b
  else:
    output=activation_function(Wx_plus_b)
  return output
#  初始化x，y
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)-0.5+noise

xs=tf.placeholder(tf.float32,[None,1])
ys=tf.placeholder(tf.float32,[None,1])
#两层，第一层输出是10，第二层输出是1
l1=add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction=add_layer(l1,10,1,activation_function=None)
#求平均损失
loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
#以0.1的学习率进行梯度下降优化
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)
#初始化所有变量
init=tf.initialize_all_variables()
sess=tf.Session()
sess.run(init)

fig=plt.figure()
ax=fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
##ion()交互，保持窗口
plt.ion()
#plt.ioff()
#block=False防止show完不动
plt.show(block=False)


for i in range(1000):
  sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
  if i%50==0:
    #每50次输出一个损失
    #print sess.run(loss,feed_dict={xs:x_data,ys:y_data})
    try:
      ax.lines.remove(lines[0])
    except Exception:
      pass
    prediction_value=sess.run(prediction,feed_dict={xs:x_data})
    lines=ax.plot(x_data,prediction_value,'r-',lw=5)
    plt.show()
    plt.pause(0.1)
    print i