Linear Regression 구현

import tensorflow as tf
 
 
x_train = [1,2,3]
y_train = [1,2,3]
 
 
W = tf.Variable(tf.random_normal([1]), name = 'weight')
b= tf.Variable(tf.random_normal([1]), name = 'bias')
 
 
Hypothesis = x_train * W +b //define Hypothesis
 
 
cost = tf.reduce_mean(tf.square(Hypothesis - y_train)) // 평균값을 냄
 
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01) //경사 하강법 , 학습비율 0.1
train = optimizer.minimize(cost) // optimizer의 minimize 함수 호출 하여 cost를 minimize함                                      
sess = tf.Session()
 
sess.run(tf.global_variables_initializer()) //W,b 와 같은 Variable을 initialize 함. Variable들을 사용 할 수 있음 
 
for step in range(2001):
    sess.run(train)
 
    if step % 20 ==0:
    print(step,sess.run(cost),sess.run(W),sess.run(b)) ))