1.tensorflow-- linear regression

 tensorflow

1. everything tf.

2. Only sess.run to take effect

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

######################################################
#data
nump_points=1000
vector_set=[]
for i in range(nump_points):
    x1=np.random.normal(0.0,0.55)
    y1=x1*0.1+0.3+np.random.normal(0.0,0.03)
    vector_set.append([x1,y1])

x_data=[v[0] for v in vector_set]
y_data=[v[1] for v in vector_set]

plt.scatter(x_data,y_data,c='r')
plt.show()
########################################################
#linear regression
#y=wx+b,initial value
w=tf.Variable(tf.random_uniform([1],-1.0,1.0),name='w')
b=tf.Variable(tf.zeros([1]))
#model
y=w*x_data+b
#trainer set up
loss=tf.reduce_mean(tf.square(y-y_data))
optimizer=tf.train.GradientDescentOptimizer(0.5)
train=optimizer.minimize(loss)


sess=tf.Session()
init=tf.global_variables_initializer()
sess.run(init)
#first step
print('w=',sess.run(w),'b=',"loss:",sess.run(loss))
for step in range(20):
    sess.run(train)
    print('w=', sess.run(w), 'b=', "loss:", sess.run(loss))